From 49749264ade8acf3112b96c0f052b691b2a49bb9 Mon Sep 17 00:00:00 2001 From: phamnazage-jpg Date: Wed, 13 May 2026 14:53:26 +0800 Subject: [PATCH] chore(repo): stop tracking generated artifacts --- .gitignore | 17 + ...ENTATION_PLAN.md.bak-corrupt-20260510-0905 | 1 - SESSION-STATE.md | 28 - memory/2026-05-11.md | 27 - memory/working-buffer.md | 11 - models.json | 2912 ----------------- .../2026/05/daily_report_2026-05-10.html | 33 - .../daily/2026/05/daily_report_2026-05-10.md | 57 - .../2026/05/daily_report_2026-05-11.html | 33 - .../daily/2026/05/daily_report_2026-05-11.md | 414 --- .../2026/05/daily_report_2026-05-12.html | 1241 ------- .../daily/2026/05/daily_report_2026-05-12.md | 350 -- .../2026/05/daily_report_2026-05-13.html | 1241 ------- .../daily/2026/05/daily_report_2026-05-13.md | 351 -- reports/daily/daily_report_2026-05-05.md | 27 - reports/daily/daily_report_2026-05-06.md | 27 - reports/daily/daily_report_2026-05-07.md | 27 - reports/daily/daily_report_2026-05-08.md | 27 - reports/daily/daily_report_2026-05-09.md | 27 - reports/daily/daily_report_2026-05-10.md | 409 --- reports/daily/daily_report_2026-05-11.md | 350 -- reports/daily/daily_report_2026-05-12.md | 351 -- reports/daily/daily_report_2026-05-13.md | 366 --- .../daily/html/daily_report_2026-05-10.html | 28 - .../daily/html/daily_report_2026-05-11.html | 1241 ------- .../daily/html/daily_report_2026-05-12.html | 1241 ------- .../daily/html/daily_report_2026-05-13.html | 1316 -------- reports/daily/models.json | 21 - reports/openclaw/2026-05-07-2250-review.md | 119 - reports/openclaw/2026-05-08-0905-review.md | 134 - reports/openclaw/2026-05-08-0912-review.md | 157 - reports/openclaw/2026-05-08-0936-review.md | 158 - reports/openclaw/2026-05-08-1430-review.md | 160 - reports/openclaw/2026-05-08-2130-review.md | 168 - reports/openclaw/2026-05-09-0930-review.md | 175 - reports/openclaw/2026-05-09-1430-review.md | 178 - reports/openclaw/2026-05-09-2130-review.md | 178 - reports/openclaw/2026-05-10-0930-review.md | 170 - reports/openclaw/2026-05-10-1430-review.md | 219 -- reports/openclaw/2026-05-10-2130-review.md | 222 -- reports/openclaw/2026-05-11-0930-review.md | 302 -- reports/openclaw/2026-05-11-1430-review.md | 330 -- reports/openclaw/2026-05-11-2130-review.md | 344 -- reports/openclaw/2026-05-12-2246-review.md | 132 - reports/openclaw/2026-05-13-0015-review.md | 145 - reports/openclaw/2026-05-13-0930-review.md | 128 - .../verification/phase6_status_2026-05-10.md | 53 - .../pre_phase6_status_2026-05-10.md | 92 - .../tencent_subscription_import_latest.txt | 1 - test.md | 1 - 50 files changed, 17 insertions(+), 15723 deletions(-) delete mode 100644 IMPLEMENTATION_PLAN.md.bak-corrupt-20260510-0905 delete mode 100644 SESSION-STATE.md delete mode 100644 memory/2026-05-11.md delete mode 100644 memory/working-buffer.md delete mode 100644 models.json delete mode 100644 reports/daily/2026/05/daily_report_2026-05-10.html delete mode 100644 reports/daily/2026/05/daily_report_2026-05-10.md delete mode 100644 reports/daily/2026/05/daily_report_2026-05-11.html delete mode 100644 reports/daily/2026/05/daily_report_2026-05-11.md delete mode 100644 reports/daily/2026/05/daily_report_2026-05-12.html delete mode 100644 reports/daily/2026/05/daily_report_2026-05-12.md delete mode 100644 reports/daily/2026/05/daily_report_2026-05-13.html delete mode 100644 reports/daily/2026/05/daily_report_2026-05-13.md delete mode 100644 reports/daily/daily_report_2026-05-05.md delete mode 100644 reports/daily/daily_report_2026-05-06.md delete mode 100644 reports/daily/daily_report_2026-05-07.md delete mode 100644 reports/daily/daily_report_2026-05-08.md delete mode 100644 reports/daily/daily_report_2026-05-09.md delete mode 100644 reports/daily/daily_report_2026-05-10.md delete mode 100644 reports/daily/daily_report_2026-05-11.md delete mode 100644 reports/daily/daily_report_2026-05-12.md delete mode 100644 reports/daily/daily_report_2026-05-13.md delete mode 100644 reports/daily/html/daily_report_2026-05-10.html delete mode 100644 reports/daily/html/daily_report_2026-05-11.html delete mode 100644 reports/daily/html/daily_report_2026-05-12.html delete mode 100644 reports/daily/html/daily_report_2026-05-13.html delete mode 100644 reports/daily/models.json delete mode 100644 reports/openclaw/2026-05-07-2250-review.md delete mode 100644 reports/openclaw/2026-05-08-0905-review.md delete mode 100644 reports/openclaw/2026-05-08-0912-review.md delete mode 100644 reports/openclaw/2026-05-08-0936-review.md delete mode 100644 reports/openclaw/2026-05-08-1430-review.md delete mode 100644 reports/openclaw/2026-05-08-2130-review.md delete mode 100644 reports/openclaw/2026-05-09-0930-review.md delete mode 100644 reports/openclaw/2026-05-09-1430-review.md delete mode 100644 reports/openclaw/2026-05-09-2130-review.md delete mode 100644 reports/openclaw/2026-05-10-0930-review.md delete mode 100644 reports/openclaw/2026-05-10-1430-review.md delete mode 100644 reports/openclaw/2026-05-10-2130-review.md delete mode 100644 reports/openclaw/2026-05-11-0930-review.md delete mode 100644 reports/openclaw/2026-05-11-1430-review.md delete mode 100644 reports/openclaw/2026-05-11-2130-review.md delete mode 100644 reports/openclaw/2026-05-12-2246-review.md delete mode 100644 reports/openclaw/2026-05-13-0015-review.md delete mode 100644 reports/openclaw/2026-05-13-0930-review.md delete mode 100644 reports/verification/phase6_status_2026-05-10.md delete mode 100644 reports/verification/pre_phase6_status_2026-05-10.md delete mode 100644 reports/verification/tencent_subscription_import_latest.txt delete mode 100644 test.md diff --git a/.gitignore b/.gitignore index b090539..0798d8a 100644 --- a/.gitignore +++ b/.gitignore @@ -17,7 +17,24 @@ frontend/dist/ /scripts/fetch_openrouter # Generated reports/media +reports/daily/ +reports/verification/ reports/daily/video/ +reports/openclaw/20*.md + +# Runtime / working memory +memory/*.md +!memory/README.md +SESSION-STATE.md + +# Generated data snapshots +models.json + +# Backup / scratch files +*.bak +*.bak-* +test.md # Runtime logs logs/*.log +*.log diff --git a/IMPLEMENTATION_PLAN.md.bak-corrupt-20260510-0905 b/IMPLEMENTATION_PLAN.md.bak-corrupt-20260510-0905 deleted file mode 100644 index 9daeafb..0000000 --- a/IMPLEMENTATION_PLAN.md.bak-corrupt-20260510-0905 +++ /dev/null @@ -1 +0,0 @@ -test diff --git a/SESSION-STATE.md b/SESSION-STATE.md deleted file mode 100644 index 602b577..0000000 --- a/SESSION-STATE.md +++ /dev/null @@ -1,28 +0,0 @@ -# llm-intelligence SESSION-STATE.md - -项目本地活动工作记忆。只保留当前最有用的任务状态，不作为长期存储。 - -## Current Focus -- Task: -- Goal / Task ID: -- User intent: - -## Current Facts -- Relevant files: -- Constraints: -- Latest verified status: - -## Decisions In Effect -- 项目任务真相来源是 `TASKS.md` -- 项目目标真相来源是 `GOALS.md` -- 高频状态先写本文件，不把项目 daily memory 当实时 WAL - -## Open Risks -- - -## Next Step -- - -## Flush Candidates -- 后续可归档到 `memory/YYYY-MM-DD.md` 或蒸馏到 `MEMORY.md`： - - diff --git a/memory/2026-05-11.md b/memory/2026-05-11.md deleted file mode 100644 index 718845e..0000000 --- a/memory/2026-05-11.md +++ /dev/null @@ -1,27 +0,0 @@ -# llm-intelligence Daily Memory - 2026-05-11 - -> 项目单日归档文件。 -> 记录高价值摘要、证据、结论，不记录每条实时对话。 -> 高频工作状态优先写 `SESSION-STATE.md`。 - -## Entries - -## 13:35 - main - project memory conventions initialized - -### Context -- 为 `llm-intelligence` 建立项目本地长期记忆、活动工作记忆和 daily memory 规则 -- 目标是让 cron / review / verifier 在项目内归档时有统一入口和统一格式 - -### Evidence -- `AGENTS.md` -- `MEMORY.md` -- `SESSION-STATE.md` -- `memory/README.md` -- `memory/working-buffer.md` - -### Outcome -- 项目级 memory routing 已明确 -- daily memory 初始化规则和统一 section 格式已落地 - -### Next -- 后续项目内自动归档统一按 `## HH:MM - - ` 格式追加 diff --git a/memory/working-buffer.md b/memory/working-buffer.md deleted file mode 100644 index 93bd802..0000000 --- a/memory/working-buffer.md +++ /dev/null @@ -1,11 +0,0 @@ -# working-buffer.md - -项目本地 compaction 危险区缓冲文件。 - -使用约定： -- 仅在接近 compaction 或明确需要 danger-zone 缓冲时使用 -- 记录短 bullet，不写长篇整理稿 -- compaction 恢复或 heartbeat 蒸馏后清空 / 重写 - -## Buffer -- diff --git a/models.json b/models.json deleted file mode 100644 index 964fa98..0000000 --- a/models.json +++ /dev/null @@ -1,2912 +0,0 @@ -{ - "free": 25, - "generated_at": "2026-05-13T09:42:02+08:00", - "models": [ - { - "id": "anthropic/claude-opus-4.7-fast", - "name": "Anthropic: Claude Opus 4.7 (Fast)", - "created": 1778613011, - "description": "Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "perceptron/perceptron-mk1", - "name": "Perceptron: Perceptron Mk1", - "created": 1778597029, - "description": "Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "inclusionai/ring-2.6-1t:free", - "name": "inclusionAI: Ring-2.6-1T (free)", - "created": 1778247440, - "description": "Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "google/gemini-3.1-flash-lite", - "name": "Google: Gemini 3.1 Flash Lite", - "created": 1778168828, - "description": "Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "baidu/cobuddy:free", - "name": "Baidu Qianfan: CoBuddy (free)", - "created": 1778035480, - "description": "CoBuddy is a code generation model from Baidu, optimized for coding tasks and AI Agent workflows. It features high inference throughput and low end-to-end latency, with native support for tool...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "openai/gpt-chat-latest", - "name": "OpenAI: GPT Chat Latest", - "created": 1778000212, - "description": "GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "x-ai/grok-4.3", - "name": "xAI: Grok 4.3", - "created": 1777591821, - "description": "Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "ibm-granite/granite-4.1-8b", - "name": "IBM: Granite 4.1 8B", - "created": 1777577071, - "description": "Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "mistralai/mistral-medium-3-5", - "name": "Mistral: Mistral Medium 3.5", - "created": 1777570439, - "description": "Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "openrouter/owl-alpha", - "name": "Owl Alpha", - "created": 1777398589, - "description": "Owl Alpha is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with strong performance in code generation, automated workflows, and complex instruction execution....", - "context_length": 1048756, - "pricing": {} - }, - { - "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", - "name": "NVIDIA: Nemotron 3 Nano Omni (free)", - "created": 1777393095, - "description": "NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...", - "context_length": 256000, - "pricing": {} - }, - { - "id": "poolside/laguna-xs.2:free", - "name": "Poolside: Laguna XS.2 (free)", - "created": 1777389604, - "description": "Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "poolside/laguna-m.1:free", - "name": "Poolside: Laguna M.1 (free)", - "created": 1777388504, - "description": "Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 128K...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "~anthropic/claude-haiku-latest", - "name": "Anthropic Claude Haiku Latest", - "created": 1777318492, - "description": "This model always redirects to the latest model in the Anthropic Claude Haiku family.", - "context_length": 200000, - "pricing": {} - }, - { - "id": "~openai/gpt-mini-latest", - "name": "OpenAI GPT Mini Latest", - "created": 1777318471, - "description": "This model always redirects to the latest model in the OpenAI GPT Mini family.", - "context_length": 400000, - "pricing": {} - }, - { - "id": "~google/gemini-pro-latest", - "name": "Google Gemini Pro Latest", - "created": 1777318451, - "description": "This model always redirects to the latest model in the Google Gemini Pro family.", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "~moonshotai/kimi-latest", - "name": "MoonshotAI Kimi Latest", - "created": 1777318428, - "description": "This model always redirects to the latest model in the MoonshotAI Kimi family.", - "context_length": 262142, - "pricing": {} - }, - { - "id": "~google/gemini-flash-latest", - "name": "Google Gemini Flash Latest", - "created": 1777318398, - "description": "This model always redirects to the latest model in the Google Gemini Flash family.", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "~anthropic/claude-sonnet-latest", - "name": "Anthropic Claude Sonnet Latest", - "created": 1777318368, - "description": "This model always redirects to the latest model in the Anthropic Claude Sonnet family.", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "~openai/gpt-latest", - "name": "OpenAI GPT Latest", - "created": 1777318334, - "description": "This model always redirects to the latest model in the OpenAI GPT family.", - "context_length": 1050000, - "pricing": {} - }, - { - "id": "qwen/qwen3.5-plus-20260420", - "name": "Qwen: Qwen3.5 Plus 2026-04-20", - "created": 1777261368, - "description": "Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "qwen/qwen3.6-flash", - "name": "Qwen: Qwen3.6 Flash", - "created": 1777261362, - "description": "Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "qwen/qwen3.6-35b-a3b", - "name": "Qwen: Qwen3.6 35B A3B", - "created": 1777260255, - "description": "Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "qwen/qwen3.6-max-preview", - "name": "Qwen: Qwen3.6 Max Preview", - "created": 1777260242, - "description": "Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "qwen/qwen3.6-27b", - "name": "Qwen: Qwen3.6 27B", - "created": 1777255064, - "description": "Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "openai/gpt-5.5-pro", - "name": "OpenAI: GPT-5.5 Pro", - "created": 1777051896, - "description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...", - "context_length": 1050000, - "pricing": {} - }, - { - "id": "openai/gpt-5.5", - "name": "OpenAI: GPT-5.5", - "created": 1777051893, - "description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...", - "context_length": 1050000, - "pricing": {} - }, - { - "id": "deepseek/deepseek-v4-pro", - "name": "DeepSeek: DeepSeek V4 Pro", - "created": 1777000679, - "description": "DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "deepseek/deepseek-v4-flash", - "name": "DeepSeek: DeepSeek V4 Flash", - "created": 1777000666, - "description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "inclusionai/ling-2.6-1t", - "name": "inclusionAI: Ling-2.6-1T", - "created": 1776948238, - "description": "Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "tencent/hy3-preview", - "name": "Tencent: Hy3 preview", - "created": 1776878150, - "description": "Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "xiaomi/mimo-v2.5-pro", - "name": "Xiaomi: MiMo-V2.5-Pro", - "created": 1776874273, - "description": "MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "xiaomi/mimo-v2.5", - "name": "Xiaomi: MiMo-V2.5", - "created": 1776874269, - "description": "MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "openai/gpt-5.4-image-2", - "name": "OpenAI: GPT-5.4 Image 2", - "created": 1776797528, - "description": "[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...", - "context_length": 272000, - "pricing": {} - }, - { - "id": "inclusionai/ling-2.6-flash", - "name": "inclusionAI: Ling-2.6-flash", - "created": 1776795886, - "description": "Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....", - "context_length": 262144, - "pricing": {} - }, - { - "id": "~anthropic/claude-opus-latest", - "name": "Anthropic: Claude Opus Latest", - "created": 1776795361, - "description": "This model always redirects to the latest model in the Claude Opus family.", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "openrouter/pareto-code", - "name": "Pareto Code Router", - "created": 1776747900, - "description": "The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...", - "context_length": 2000000, - "pricing": {} - }, - { - "id": "baidu/qianfan-ocr-fast:free", - "name": "Baidu: Qianfan-OCR-Fast (free)", - "created": 1776707472, - "description": "Qianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR training data while preserving versatile multimodal intelligence, it provides a powerful performance upgrade over Qianfan-OCR.", - "context_length": 65536, - "pricing": {} - }, - { - "id": "moonshotai/kimi-k2.6", - "name": "MoonshotAI: Kimi K2.6", - "created": 1776699402, - "description": "Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...", - "context_length": 262142, - "pricing": {} - }, - { - "id": "anthropic/claude-opus-4.7", - "name": "Anthropic: Claude Opus 4.7", - "created": 1776351100, - "description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "anthropic/claude-opus-4.6-fast", - "name": "Anthropic: Claude Opus 4.6 (Fast)", - "created": 1775592472, - "description": "Fast-mode variant of [Opus 4.6](/anthropic/claude-opus-4.6) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "z-ai/glm-5.1", - "name": "Z.ai: GLM 5.1", - "created": 1775578025, - "description": "GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...", - "context_length": 202752, - "pricing": {} - }, - { - "id": "google/gemma-4-26b-a4b-it:free", - "name": "Google: Gemma 4 26B A4B (free)", - "created": 1775227989, - "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "google/gemma-4-26b-a4b-it", - "name": "Google: Gemma 4 26B A4B ", - "created": 1775227989, - "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "google/gemma-4-31b-it:free", - "name": "Google: Gemma 4 31B (free)", - "created": 1775148486, - "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "google/gemma-4-31b-it", - "name": "Google: Gemma 4 31B", - "created": 1775148486, - "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "qwen/qwen3.6-plus", - "name": "Qwen: Qwen3.6 Plus", - "created": 1775133557, - "description": "Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "z-ai/glm-5v-turbo", - "name": "Z.ai: GLM 5V Turbo", - "created": 1775061458, - "description": "GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...", - "context_length": 202752, - "pricing": {} - }, - { - "id": "arcee-ai/trinity-large-thinking:free", - "name": "Arcee AI: Trinity Large Thinking (free)", - "created": 1775058318, - "description": "Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "arcee-ai/trinity-large-thinking", - "name": "Arcee AI: Trinity Large Thinking", - "created": 1775058318, - "description": "Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "x-ai/grok-4.20-multi-agent", - "name": "xAI: Grok 4.20 Multi-Agent", - "created": 1774979158, - "description": "Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...", - "context_length": 2000000, - "pricing": {} - }, - { - "id": "x-ai/grok-4.20", - "name": "xAI: Grok 4.20", - "created": 1774979019, - "description": "Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...", - "context_length": 2000000, - "pricing": {} - }, - { - "id": "google/lyria-3-pro-preview", - "name": "Google: Lyria 3 Pro Preview", - "created": 1774907286, - "description": "Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "google/lyria-3-clip-preview", - "name": "Google: Lyria 3 Clip Preview", - "created": 1774907255, - "description": "30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "kwaipilot/kat-coder-pro-v2", - "name": "Kwaipilot: KAT-Coder-Pro V2", - "created": 1774649310, - "description": "KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...", - "context_length": 256000, - "pricing": {} - }, - { - "id": "rekaai/reka-edge", - "name": "Reka Edge", - "created": 1774026965, - "description": "Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...", - "context_length": 16384, - "pricing": {} - }, - { - "id": "xiaomi/mimo-v2-omni", - "name": "Xiaomi: MiMo-V2-Omni", - "created": 1773863703, - "description": "MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agentic capability - visual grounding, multi-step...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "xiaomi/mimo-v2-pro", - "name": "Xiaomi: MiMo-V2-Pro", - "created": 1773863643, - "description": "MiMo-V2-Pro is Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M context length, deeply optimized for agentic scenarios. It is highly adaptable to general agent frameworks like...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "minimax/minimax-m2.7", - "name": "MiniMax: MiniMax M2.7", - "created": 1773836697, - "description": "MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...", - "context_length": 196608, - "pricing": {} - }, - { - "id": "openai/gpt-5.4-nano", - "name": "OpenAI: GPT-5.4 Nano", - "created": 1773748187, - "description": "GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "openai/gpt-5.4-mini", - "name": "OpenAI: GPT-5.4 Mini", - "created": 1773748178, - "description": "GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "mistralai/mistral-small-2603", - "name": "Mistral: Mistral Small 4", - "created": 1773695685, - "description": "Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "z-ai/glm-5-turbo", - "name": "Z.ai: GLM 5 Turbo", - "created": 1773583573, - "description": "GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...", - "context_length": 202752, - "pricing": {} - }, - { - "id": "nvidia/nemotron-3-super-120b-a12b:free", - "name": "NVIDIA: Nemotron 3 Super (free)", - "created": 1773245239, - "description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "nvidia/nemotron-3-super-120b-a12b", - "name": "NVIDIA: Nemotron 3 Super", - "created": 1773245239, - "description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "bytedance-seed/seed-2.0-lite", - "name": "ByteDance Seed: Seed-2.0-Lite", - "created": 1773157231, - "description": "Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "qwen/qwen3.5-9b", - "name": "Qwen: Qwen3.5-9B", - "created": 1773152396, - "description": "Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "openai/gpt-5.4-pro", - "name": "OpenAI: GPT-5.4 Pro", - "created": 1772734366, - "description": "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...", - "context_length": 1050000, - "pricing": {} - }, - { - "id": "openai/gpt-5.4", - "name": "OpenAI: GPT-5.4", - "created": 1772734352, - "description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...", - "context_length": 1050000, - "pricing": {} - }, - { - "id": "inception/mercury-2", - "name": "Inception: Mercury 2", - "created": 1772636275, - "description": "Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openai/gpt-5.3-chat", - "name": "OpenAI: GPT-5.3 Chat", - "created": 1772564061, - "description": "GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "google/gemini-3.1-flash-lite-preview", - "name": "Google: Gemini 3.1 Flash Lite Preview", - "created": 1772512673, - "description": "Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "bytedance-seed/seed-2.0-mini", - "name": "ByteDance Seed: Seed-2.0-Mini", - "created": 1772131107, - "description": "Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "google/gemini-3.1-flash-image-preview", - "name": "Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)", - "created": 1772119558, - "description": "Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...", - "context_length": 65536, - "pricing": {} - }, - { - "id": "qwen/qwen3.5-35b-a3b", - "name": "Qwen: Qwen3.5-35B-A3B", - "created": 1772053822, - "description": "The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "qwen/qwen3.5-27b", - "name": "Qwen: Qwen3.5-27B", - "created": 1772053810, - "description": "The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "qwen/qwen3.5-122b-a10b", - "name": "Qwen: Qwen3.5-122B-A10B", - "created": 1772053789, - "description": "The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "qwen/qwen3.5-flash-02-23", - "name": "Qwen: Qwen3.5-Flash", - "created": 1772053776, - "description": "The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "liquid/lfm-2-24b-a2b", - "name": "LiquidAI: LFM2-24B-A2B", - "created": 1772048711, - "description": "LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "google/gemini-3.1-pro-preview-customtools", - "name": "Google: Gemini 3.1 Pro Preview Custom Tools", - "created": 1772045923, - "description": "Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "openai/gpt-5.3-codex", - "name": "OpenAI: GPT-5.3-Codex", - "created": 1771959164, - "description": "GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "aion-labs/aion-2.0", - "name": "AionLabs: Aion-2.0", - "created": 1771881306, - "description": "Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....", - "context_length": 131072, - "pricing": {} - }, - { - "id": "google/gemini-3.1-pro-preview", - "name": "Google: Gemini 3.1 Pro Preview", - "created": 1771509627, - "description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "anthropic/claude-sonnet-4.6", - "name": "Anthropic: Claude Sonnet 4.6", - "created": 1771342990, - "description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "qwen/qwen3.5-plus-02-15", - "name": "Qwen: Qwen3.5 Plus 2026-02-15", - "created": 1771229416, - "description": "The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "qwen/qwen3.5-397b-a17b", - "name": "Qwen: Qwen3.5 397B A17B", - "created": 1771223018, - "description": "The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "minimax/minimax-m2.5:free", - "name": "MiniMax: MiniMax M2.5 (free)", - "created": 1770908502, - "description": "MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...", - "context_length": 196608, - "pricing": {} - }, - { - "id": "minimax/minimax-m2.5", - "name": "MiniMax: MiniMax M2.5", - "created": 1770908502, - "description": "MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...", - "context_length": 196608, - "pricing": {} - }, - { - "id": "z-ai/glm-5", - "name": "Z.ai: GLM 5", - "created": 1770829182, - "description": "GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...", - "context_length": 202752, - "pricing": {} - }, - { - "id": "qwen/qwen3-max-thinking", - "name": "Qwen: Qwen3 Max Thinking", - "created": 1770671901, - "description": "Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "anthropic/claude-opus-4.6", - "name": "Anthropic: Claude Opus 4.6", - "created": 1770219050, - "description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "qwen/qwen3-coder-next", - "name": "Qwen: Qwen3 Coder Next", - "created": 1770164101, - "description": "Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "openrouter/free", - "name": "Free Models Router", - "created": 1769917427, - "description": "The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "stepfun/step-3.5-flash", - "name": "StepFun: Step 3.5 Flash", - "created": 1769728337, - "description": "Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....", - "context_length": 262144, - "pricing": {} - }, - { - "id": "arcee-ai/trinity-large-preview", - "name": "Arcee AI: Trinity Large Preview", - "created": 1769552670, - "description": "Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routing. It excels in creative writing,...", - "context_length": 131000, - "pricing": {} - }, - { - "id": "moonshotai/kimi-k2.5", - "name": "MoonshotAI: Kimi K2.5", - "created": 1769487076, - "description": "Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "upstage/solar-pro-3", - "name": "Upstage: Solar Pro 3", - "created": 1769481200, - "description": "Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "minimax/minimax-m2-her", - "name": "MiniMax: MiniMax M2-her", - "created": 1769177239, - "description": "MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...", - "context_length": 65536, - "pricing": {} - }, - { - "id": "writer/palmyra-x5", - "name": "Writer: Palmyra X5", - "created": 1769003823, - "description": "Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...", - "context_length": 1040000, - "pricing": {} - }, - { - "id": "liquid/lfm-2.5-1.2b-thinking:free", - "name": "LiquidAI: LFM2.5-1.2B-Thinking (free)", - "created": 1768927527, - "description": "LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "liquid/lfm-2.5-1.2b-instruct:free", - "name": "LiquidAI: LFM2.5-1.2B-Instruct (free)", - "created": 1768927521, - "description": "LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support.", - "context_length": 32768, - "pricing": {} - }, - { - "id": "openai/gpt-audio", - "name": "OpenAI: GPT Audio", - "created": 1768862569, - "description": "The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openai/gpt-audio-mini", - "name": "OpenAI: GPT Audio Mini", - "created": 1768859419, - "description": "A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "z-ai/glm-4.7-flash", - "name": "Z.ai: GLM 4.7 Flash", - "created": 1768833913, - "description": "As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...", - "context_length": 202752, - "pricing": {} - }, - { - "id": "openai/gpt-5.2-codex", - "name": "OpenAI: GPT-5.2-Codex", - "created": 1768409315, - "description": "GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....", - "context_length": 400000, - "pricing": {} - }, - { - "id": "bytedance-seed/seed-1.6-flash", - "name": "ByteDance Seed: Seed 1.6 Flash", - "created": 1766505011, - "description": "Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "bytedance-seed/seed-1.6", - "name": "ByteDance Seed: Seed 1.6", - "created": 1766504997, - "description": "Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.", - "context_length": 262144, - "pricing": {} - }, - { - "id": "minimax/minimax-m2.1", - "name": "MiniMax: MiniMax M2.1", - "created": 1766454997, - "description": "MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...", - "context_length": 196608, - "pricing": {} - }, - { - "id": "z-ai/glm-4.7", - "name": "Z.ai: GLM 4.7", - "created": 1766378014, - "description": "GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...", - "context_length": 202752, - "pricing": {} - }, - { - "id": "google/gemini-3-flash-preview", - "name": "Google: Gemini 3 Flash Preview", - "created": 1765987078, - "description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "xiaomi/mimo-v2-flash", - "name": "Xiaomi: MiMo-V2-Flash", - "created": 1765731308, - "description": "MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "nvidia/nemotron-3-nano-30b-a3b:free", - "name": "NVIDIA: Nemotron 3 Nano 30B A3B (free)", - "created": 1765731275, - "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...", - "context_length": 256000, - "pricing": {} - }, - { - "id": "nvidia/nemotron-3-nano-30b-a3b", - "name": "NVIDIA: Nemotron 3 Nano 30B A3B", - "created": 1765731275, - "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "openai/gpt-5.2-chat", - "name": "OpenAI: GPT-5.2 Chat", - "created": 1765389783, - "description": "GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openai/gpt-5.2-pro", - "name": "OpenAI: GPT-5.2 Pro", - "created": 1765389780, - "description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "openai/gpt-5.2", - "name": "OpenAI: GPT-5.2", - "created": 1765389775, - "description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "mistralai/devstral-2512", - "name": "Mistral: Devstral 2 2512", - "created": 1765285419, - "description": "Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "relace/relace-search", - "name": "Relace: Relace Search", - "created": 1765213560, - "description": "The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...", - "context_length": 256000, - "pricing": {} - }, - { - "id": "z-ai/glm-4.6v", - "name": "Z.ai: GLM 4.6V", - "created": 1765207462, - "description": "GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "nex-agi/deepseek-v3.1-nex-n1", - "name": "Nex AGI: DeepSeek V3.1 Nex N1", - "created": 1765204393, - "description": "DeepSeek V3.1 Nex-N1 is the flagship release of the Nex-N1 series — a post-trained model designed to highlight agent autonomy, tool use, and real-world productivity. Nex-N1 demonstrates competitive performance across...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "essentialai/rnj-1-instruct", - "name": "EssentialAI: Rnj 1 Instruct", - "created": 1765094847, - "description": "Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained from scratch with a focus on programming, math, and scientific reasoning. The model demonstrates strong performance...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "openrouter/bodybuilder", - "name": "Body Builder (beta)", - "created": 1764903653, - "description": "Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openai/gpt-5.1-codex-max", - "name": "OpenAI: GPT-5.1-Codex-Max", - "created": 1764878934, - "description": "GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "amazon/nova-2-lite-v1", - "name": "Amazon: Nova 2 Lite", - "created": 1764696672, - "description": "Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "mistralai/ministral-14b-2512", - "name": "Mistral: Ministral 3 14B 2512", - "created": 1764681735, - "description": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "mistralai/ministral-8b-2512", - "name": "Mistral: Ministral 3 8B 2512", - "created": 1764681654, - "description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.", - "context_length": 262144, - "pricing": {} - }, - { - "id": "mistralai/ministral-3b-2512", - "name": "Mistral: Ministral 3 3B 2512", - "created": 1764681560, - "description": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.", - "context_length": 131072, - "pricing": {} - }, - { - "id": "mistralai/mistral-large-2512", - "name": "Mistral: Mistral Large 3 2512", - "created": 1764624472, - "description": "Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.", - "context_length": 262144, - "pricing": {} - }, - { - "id": "arcee-ai/trinity-mini", - "name": "Arcee AI: Trinity Mini", - "created": 1764601720, - "description": "Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "deepseek/deepseek-v3.2-speciale", - "name": "DeepSeek: DeepSeek V3.2 Speciale", - "created": 1764594837, - "description": "DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales post-training reinforcement learning...", - "context_length": 163840, - "pricing": {} - }, - { - "id": "deepseek/deepseek-v3.2", - "name": "DeepSeek: DeepSeek V3.2", - "created": 1764594642, - "description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "prime-intellect/intellect-3", - "name": "Prime Intellect: INTELLECT-3", - "created": 1764212534, - "description": "INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math,...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "anthropic/claude-opus-4.5", - "name": "Anthropic: Claude Opus 4.5", - "created": 1764010580, - "description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "allenai/olmo-3-32b-think", - "name": "AllenAI: Olmo 3 32B Think", - "created": 1763758276, - "description": "Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...", - "context_length": 65536, - "pricing": {} - }, - { - "id": "google/gemini-3-pro-image-preview", - "name": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)", - "created": 1763653797, - "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...", - "context_length": 65536, - "pricing": {} - }, - { - "id": "x-ai/grok-4.1-fast", - "name": "xAI: Grok 4.1 Fast", - "created": 1763587502, - "description": "Grok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window. Reasoning can be enabled/disabled using...", - "context_length": 2000000, - "pricing": {} - }, - { - "id": "deepcogito/cogito-v2.1-671b", - "name": "Deep Cogito: Cogito v2.1 671B", - "created": 1763071233, - "description": "Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openai/gpt-5.1", - "name": "OpenAI: GPT-5.1", - "created": 1763060305, - "description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "openai/gpt-5.1-chat", - "name": "OpenAI: GPT-5.1 Chat", - "created": 1763060302, - "description": "GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openai/gpt-5.1-codex", - "name": "OpenAI: GPT-5.1-Codex", - "created": 1763060298, - "description": "GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....", - "context_length": 400000, - "pricing": {} - }, - { - "id": "openai/gpt-5.1-codex-mini", - "name": "OpenAI: GPT-5.1-Codex-Mini", - "created": 1763057820, - "description": "GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex", - "context_length": 400000, - "pricing": {} - }, - { - "id": "moonshotai/kimi-k2-thinking", - "name": "MoonshotAI: Kimi K2 Thinking", - "created": 1762440622, - "description": "Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "amazon/nova-premier-v1", - "name": "Amazon: Nova Premier 1.0", - "created": 1761950332, - "description": "Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "perplexity/sonar-pro-search", - "name": "Perplexity: Sonar Pro Search", - "created": 1761854366, - "description": "Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "mistralai/voxtral-small-24b-2507", - "name": "Mistral: Voxtral Small 24B 2507", - "created": 1761835144, - "description": "Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...", - "context_length": 32000, - "pricing": {} - }, - { - "id": "openai/gpt-oss-safeguard-20b", - "name": "OpenAI: gpt-oss-safeguard-20b", - "created": 1761752836, - "description": "gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "nvidia/nemotron-nano-12b-v2-vl:free", - "name": "NVIDIA: Nemotron Nano 12B 2 VL (free)", - "created": 1761675565, - "description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "minimax/minimax-m2", - "name": "MiniMax: MiniMax M2", - "created": 1761252093, - "description": "MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...", - "context_length": 196608, - "pricing": {} - }, - { - "id": "qwen/qwen3-vl-32b-instruct", - "name": "Qwen: Qwen3 VL 32B Instruct", - "created": 1761231332, - "description": "Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "ibm-granite/granite-4.0-h-micro", - "name": "IBM: Granite 4.0 Micro", - "created": 1760927695, - "description": "Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...", - "context_length": 131000, - "pricing": {} - }, - { - "id": "microsoft/phi-4-mini-instruct", - "name": "Microsoft: Phi 4 Mini Instruct", - "created": 1760726049, - "description": "Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openai/gpt-5-image-mini", - "name": "OpenAI: GPT-5 Image Mini", - "created": 1760624583, - "description": "GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "anthropic/claude-haiku-4.5", - "name": "Anthropic: Claude Haiku 4.5", - "created": 1760547638, - "description": "Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "qwen/qwen3-vl-8b-thinking", - "name": "Qwen: Qwen3 VL 8B Thinking", - "created": 1760463746, - "description": "Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "qwen/qwen3-vl-8b-instruct", - "name": "Qwen: Qwen3 VL 8B Instruct", - "created": 1760463308, - "description": "Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "openai/gpt-5-image", - "name": "OpenAI: GPT-5 Image", - "created": 1760447986, - "description": "[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "openai/o3-deep-research", - "name": "OpenAI: o3 Deep Research", - "created": 1760129661, - "description": "o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.", - "context_length": 200000, - "pricing": {} - }, - { - "id": "openai/o4-mini-deep-research", - "name": "OpenAI: o4 Mini Deep Research", - "created": 1760129642, - "description": "o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.", - "context_length": 200000, - "pricing": {} - }, - { - "id": "nvidia/llama-3.3-nemotron-super-49b-v1.5", - "name": "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5", - "created": 1760101395, - "description": "Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "baidu/ernie-4.5-21b-a3b-thinking", - "name": "Baidu: ERNIE 4.5 21B A3B Thinking", - "created": 1760048887, - "description": "ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performance in logical puzzles, math, science, coding, text generation, and expert-level academic benchmarks.", - "context_length": 131072, - "pricing": {} - }, - { - "id": "google/gemini-2.5-flash-image", - "name": "Google: Nano Banana (Gemini 2.5 Flash Image)", - "created": 1759870431, - "description": "Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "qwen/qwen3-vl-30b-a3b-thinking", - "name": "Qwen: Qwen3 VL 30B A3B Thinking", - "created": 1759794479, - "description": "Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "qwen/qwen3-vl-30b-a3b-instruct", - "name": "Qwen: Qwen3 VL 30B A3B Instruct", - "created": 1759794476, - "description": "Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "openai/gpt-5-pro", - "name": "OpenAI: GPT-5 Pro", - "created": 1759776663, - "description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "z-ai/glm-4.6", - "name": "Z.ai: GLM 4.6", - "created": 1759235576, - "description": "Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...", - "context_length": 204800, - "pricing": {} - }, - { - "id": "anthropic/claude-sonnet-4.5", - "name": "Anthropic: Claude Sonnet 4.5", - "created": 1759161676, - "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "deepseek/deepseek-v3.2-exp", - "name": "DeepSeek: DeepSeek V3.2 Exp", - "created": 1759150481, - "description": "DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...", - "context_length": 163840, - "pricing": {} - }, - { - "id": "thedrummer/cydonia-24b-v4.1", - "name": "TheDrummer: Cydonia 24B V4.1", - "created": 1758931878, - "description": "Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.", - "context_length": 131072, - "pricing": {} - }, - { - "id": "relace/relace-apply-3", - "name": "Relace: Relace Apply 3", - "created": 1758891572, - "description": "Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...", - "context_length": 256000, - "pricing": {} - }, - { - "id": "google/gemini-2.5-flash-lite-preview-09-2025", - "name": "Google: Gemini 2.5 Flash Lite Preview 09-2025", - "created": 1758819686, - "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "qwen/qwen3-vl-235b-a22b-thinking", - "name": "Qwen: Qwen3 VL 235B A22B Thinking", - "created": 1758668690, - "description": "Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....", - "context_length": 131072, - "pricing": {} - }, - { - "id": "qwen/qwen3-vl-235b-a22b-instruct", - "name": "Qwen: Qwen3 VL 235B A22B Instruct", - "created": 1758668687, - "description": "Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "qwen/qwen3-max", - "name": "Qwen: Qwen3 Max", - "created": 1758662808, - "description": "Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "qwen/qwen3-coder-plus", - "name": "Qwen: Qwen3 Coder Plus", - "created": 1758662707, - "description": "Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "openai/gpt-5-codex", - "name": "OpenAI: GPT-5 Codex", - "created": 1758643403, - "description": "GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....", - "context_length": 400000, - "pricing": {} - }, - { - "id": "deepseek/deepseek-v3.1-terminus", - "name": "DeepSeek: DeepSeek V3.1 Terminus", - "created": 1758548275, - "description": "DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...", - "context_length": 163840, - "pricing": {} - }, - { - "id": "x-ai/grok-4-fast", - "name": "xAI: Grok 4 Fast", - "created": 1758240090, - "description": "Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model...", - "context_length": 2000000, - "pricing": {} - }, - { - "id": "alibaba/tongyi-deepresearch-30b-a3b", - "name": "Tongyi DeepResearch 30B A3B", - "created": 1758210804, - "description": "Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep information-seeking tasks...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "qwen/qwen3-coder-flash", - "name": "Qwen: Qwen3 Coder Flash", - "created": 1758115536, - "description": "Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "qwen/qwen3-next-80b-a3b-thinking", - "name": "Qwen: Qwen3 Next 80B A3B Thinking", - "created": 1757612284, - "description": "Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "qwen/qwen3-next-80b-a3b-instruct:free", - "name": "Qwen: Qwen3 Next 80B A3B Instruct (free)", - "created": 1757612213, - "description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "qwen/qwen3-next-80b-a3b-instruct", - "name": "Qwen: Qwen3 Next 80B A3B Instruct", - "created": 1757612213, - "description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "qwen/qwen-plus-2025-07-28:thinking", - "name": "Qwen: Qwen Plus 0728 (thinking)", - "created": 1757347599, - "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "qwen/qwen-plus-2025-07-28", - "name": "Qwen: Qwen Plus 0728", - "created": 1757347599, - "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "nvidia/nemotron-nano-9b-v2:free", - "name": "NVIDIA: Nemotron Nano 9B V2 (free)", - "created": 1757106807, - "description": "NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "nvidia/nemotron-nano-9b-v2", - "name": "NVIDIA: Nemotron Nano 9B V2", - "created": 1757106807, - "description": "NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "moonshotai/kimi-k2-0905", - "name": "MoonshotAI: Kimi K2 0905", - "created": 1757021147, - "description": "Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "qwen/qwen3-30b-a3b-thinking-2507", - "name": "Qwen: Qwen3 30B A3B Thinking 2507", - "created": 1756399192, - "description": "Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "x-ai/grok-code-fast-1", - "name": "xAI: Grok Code Fast 1", - "created": 1756238927, - "description": "Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality...", - "context_length": 256000, - "pricing": {} - }, - { - "id": "nousresearch/hermes-4-70b", - "name": "Nous: Hermes 4 70B", - "created": 1756236182, - "description": "Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "nousresearch/hermes-4-405b", - "name": "Nous: Hermes 4 405B", - "created": 1756235463, - "description": "Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "deepseek/deepseek-chat-v3.1", - "name": "DeepSeek: DeepSeek V3.1", - "created": 1755779628, - "description": "DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...", - "context_length": 163840, - "pricing": {} - }, - { - "id": "openai/gpt-4o-audio-preview", - "name": "OpenAI: GPT-4o Audio", - "created": 1755233061, - "description": "The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "mistralai/mistral-medium-3.1", - "name": "Mistral: Mistral Medium 3.1", - "created": 1755095639, - "description": "Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "baidu/ernie-4.5-21b-a3b", - "name": "Baidu: ERNIE 4.5 21B A3B", - "created": 1755034167, - "description": "A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heterogeneous MoE structures and modality-isolated routing. Supporting an...", - "context_length": 120000, - "pricing": {} - }, - { - "id": "baidu/ernie-4.5-vl-28b-a3b", - "name": "Baidu: ERNIE 4.5 VL 28B A3B", - "created": 1755032836, - "description": "A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with modality-isolated routing....", - "context_length": 30000, - "pricing": {} - }, - { - "id": "z-ai/glm-4.5v", - "name": "Z.ai: GLM 4.5V", - "created": 1754922288, - "description": "GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...", - "context_length": 65536, - "pricing": {} - }, - { - "id": "ai21/jamba-large-1.7", - "name": "AI21: Jamba Large 1.7", - "created": 1754669020, - "description": "Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context...", - "context_length": 256000, - "pricing": {} - }, - { - "id": "openai/gpt-5-chat", - "name": "OpenAI: GPT-5 Chat", - "created": 1754587837, - "description": "GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openai/gpt-5", - "name": "OpenAI: GPT-5", - "created": 1754587413, - "description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "openai/gpt-5-mini", - "name": "OpenAI: GPT-5 Mini", - "created": 1754587407, - "description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....", - "context_length": 400000, - "pricing": {} - }, - { - "id": "openai/gpt-5-nano", - "name": "OpenAI: GPT-5 Nano", - "created": 1754587402, - "description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...", - "context_length": 400000, - "pricing": {} - }, - { - "id": "openai/gpt-oss-120b:free", - "name": "OpenAI: gpt-oss-120b (free)", - "created": 1754414231, - "description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "openai/gpt-oss-120b", - "name": "OpenAI: gpt-oss-120b", - "created": 1754414231, - "description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "openai/gpt-oss-20b:free", - "name": "OpenAI: gpt-oss-20b (free)", - "created": 1754414229, - "description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "openai/gpt-oss-20b", - "name": "OpenAI: gpt-oss-20b", - "created": 1754414229, - "description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "anthropic/claude-opus-4.1", - "name": "Anthropic: Claude Opus 4.1", - "created": 1754411591, - "description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "mistralai/codestral-2508", - "name": "Mistral: Codestral 2508", - "created": 1754079630, - "description": "Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)", - "context_length": 256000, - "pricing": {} - }, - { - "id": "qwen/qwen3-coder-30b-a3b-instruct", - "name": "Qwen: Qwen3 Coder 30B A3B Instruct", - "created": 1753972379, - "description": "Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...", - "context_length": 160000, - "pricing": {} - }, - { - "id": "qwen/qwen3-30b-a3b-instruct-2507", - "name": "Qwen: Qwen3 30B A3B Instruct 2507", - "created": 1753806965, - "description": "Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "z-ai/glm-4.5", - "name": "Z.ai: GLM 4.5", - "created": 1753471347, - "description": "GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "z-ai/glm-4.5-air:free", - "name": "Z.ai: GLM 4.5 Air (free)", - "created": 1753471258, - "description": "GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "z-ai/glm-4.5-air", - "name": "Z.ai: GLM 4.5 Air", - "created": 1753471258, - "description": "GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "qwen/qwen3-235b-a22b-thinking-2507", - "name": "Qwen: Qwen3 235B A22B Thinking 2507", - "created": 1753449557, - "description": "Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "z-ai/glm-4-32b", - "name": "Z.ai: GLM 4 32B ", - "created": 1753376617, - "description": "GLM 4 32B is a cost-effective foundation language model. It can efficiently perform complex tasks and has significantly enhanced capabilities in tool use, online search, and code-related intelligent tasks. It...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "qwen/qwen3-coder:free", - "name": "Qwen: Qwen3 Coder 480B A35B (free)", - "created": 1753230546, - "description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...", - "context_length": 262000, - "pricing": {} - }, - { - "id": "qwen/qwen3-coder", - "name": "Qwen: Qwen3 Coder 480B A35B", - "created": 1753230546, - "description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "bytedance/ui-tars-1.5-7b", - "name": "ByteDance: UI-TARS 7B ", - "created": 1753205056, - "description": "UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "google/gemini-2.5-flash-lite", - "name": "Google: Gemini 2.5 Flash Lite", - "created": 1753200276, - "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "qwen/qwen3-235b-a22b-2507", - "name": "Qwen: Qwen3 235B A22B Instruct 2507", - "created": 1753119555, - "description": "Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "switchpoint/router", - "name": "Switchpoint Router", - "created": 1752272899, - "description": "Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an ever-evolving library. As the world of LLMs advances, our router gets smarter, ensuring you...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "moonshotai/kimi-k2", - "name": "MoonshotAI: Kimi K2 0711", - "created": 1752263252, - "description": "Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "mistralai/devstral-medium", - "name": "Mistral: Devstral Medium", - "created": 1752161321, - "description": "Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "mistralai/devstral-small", - "name": "Mistral: Devstral Small 1.1", - "created": 1752160751, - "description": "Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free", - "name": "Venice: Uncensored (free)", - "created": 1752094966, - "description": "Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "x-ai/grok-4", - "name": "xAI: Grok 4", - "created": 1752087689, - "description": "Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not...", - "context_length": 256000, - "pricing": {} - }, - { - "id": "tencent/hunyuan-a13b-instruct", - "name": "Tencent: Hunyuan A13B Instruct", - "created": 1751987664, - "description": "Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "morph/morph-v3-large", - "name": "Morph: Morph V3 Large", - "created": 1751910858, - "description": "Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: \u003cinstruction\u003e{instruction}\u003c/instruction\u003e \u003ccode\u003e{initial_code}\u003c/code\u003e...", - "context_length": 262144, - "pricing": {} - }, - { - "id": "morph/morph-v3-fast", - "name": "Morph: Morph V3 Fast", - "created": 1751910002, - "description": "Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: \u003cinstruction\u003e{instruction}\u003c/instruction\u003e \u003ccode\u003e{initial_code}\u003c/code\u003e \u003cupdate\u003e{edit_snippet}\u003c/update\u003e...", - "context_length": 81920, - "pricing": {} - }, - { - "id": "baidu/ernie-4.5-vl-424b-a47b", - "name": "Baidu: ERNIE 4.5 VL 424B A47B ", - "created": 1751300903, - "description": "ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...", - "context_length": 123000, - "pricing": {} - }, - { - "id": "baidu/ernie-4.5-300b-a47b", - "name": "Baidu: ERNIE 4.5 300B A47B ", - "created": 1751300139, - "description": "ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu as part of the ERNIE 4.5 series. It activates 47B parameters per token and supports text generation in...", - "context_length": 123000, - "pricing": {} - }, - { - "id": "mistralai/mistral-small-3.2-24b-instruct", - "name": "Mistral: Mistral Small 3.2 24B", - "created": 1750443016, - "description": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "minimax/minimax-m1", - "name": "MiniMax: MiniMax M1", - "created": 1750200414, - "description": "MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "google/gemini-2.5-flash", - "name": "Google: Gemini 2.5 Flash", - "created": 1750172488, - "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "google/gemini-2.5-pro", - "name": "Google: Gemini 2.5 Pro", - "created": 1750169544, - "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "openai/o3-pro", - "name": "OpenAI: o3 Pro", - "created": 1749598352, - "description": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "x-ai/grok-3-mini", - "name": "xAI: Grok 3 Mini", - "created": 1749583245, - "description": "A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.", - "context_length": 131072, - "pricing": {} - }, - { - "id": "x-ai/grok-3", - "name": "xAI: Grok 3", - "created": 1749582908, - "description": "Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "google/gemini-2.5-pro-preview", - "name": "Google: Gemini 2.5 Pro Preview 06-05", - "created": 1749137257, - "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "deepseek/deepseek-r1-0528", - "name": "DeepSeek: R1 0528", - "created": 1748455170, - "description": "May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...", - "context_length": 163840, - "pricing": {} - }, - { - "id": "anthropic/claude-opus-4", - "name": "Anthropic: Claude Opus 4", - "created": 1747931245, - "description": "Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "anthropic/claude-sonnet-4", - "name": "Anthropic: Claude Sonnet 4", - "created": 1747930371, - "description": "Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "google/gemma-3n-e4b-it", - "name": "Google: Gemma 3n 4B", - "created": 1747776824, - "description": "Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "mistralai/mistral-medium-3", - "name": "Mistral: Mistral Medium 3", - "created": 1746627341, - "description": "Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "google/gemini-2.5-pro-preview-05-06", - "name": "Google: Gemini 2.5 Pro Preview 05-06", - "created": 1746578513, - "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "arcee-ai/spotlight", - "name": "Arcee AI: Spotlight", - "created": 1746481552, - "description": "Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context window, enabling rich multimodal...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "arcee-ai/maestro-reasoning", - "name": "Arcee AI: Maestro Reasoning", - "created": 1746481269, - "description": "Maestro Reasoning is Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and chain‑of‑thought RL for step‑by‑step logic. Compared to the earlier 7 B...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "arcee-ai/virtuoso-large", - "name": "Arcee AI: Virtuoso Large", - "created": 1746478885, - "description": "Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "arcee-ai/coder-large", - "name": "Arcee AI: Coder Large", - "created": 1746478663, - "description": "Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "meta-llama/llama-guard-4-12b", - "name": "Meta: Llama Guard 4 12B", - "created": 1745975193, - "description": "Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...", - "context_length": 163840, - "pricing": {} - }, - { - "id": "qwen/qwen3-30b-a3b", - "name": "Qwen: Qwen3 30B A3B", - "created": 1745878604, - "description": "Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...", - "context_length": 40960, - "pricing": {} - }, - { - "id": "qwen/qwen3-8b", - "name": "Qwen: Qwen3 8B", - "created": 1745876632, - "description": "Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math,...", - "context_length": 40960, - "pricing": {} - }, - { - "id": "qwen/qwen3-14b", - "name": "Qwen: Qwen3 14B", - "created": 1745876478, - "description": "Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...", - "context_length": 40960, - "pricing": {} - }, - { - "id": "qwen/qwen3-32b", - "name": "Qwen: Qwen3 32B", - "created": 1745875945, - "description": "Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...", - "context_length": 40960, - "pricing": {} - }, - { - "id": "qwen/qwen3-235b-a22b", - "name": "Qwen: Qwen3 235B A22B", - "created": 1745875757, - "description": "Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "openai/o4-mini-high", - "name": "OpenAI: o4 Mini High", - "created": 1744824212, - "description": "OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "openai/o3", - "name": "OpenAI: o3", - "created": 1744823457, - "description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....", - "context_length": 200000, - "pricing": {} - }, - { - "id": "openai/o4-mini", - "name": "OpenAI: o4 Mini", - "created": 1744820942, - "description": "OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "openai/gpt-4.1", - "name": "OpenAI: GPT-4.1", - "created": 1744651385, - "description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...", - "context_length": 1047576, - "pricing": {} - }, - { - "id": "openai/gpt-4.1-mini", - "name": "OpenAI: GPT-4.1 Mini", - "created": 1744651381, - "description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...", - "context_length": 1047576, - "pricing": {} - }, - { - "id": "openai/gpt-4.1-nano", - "name": "OpenAI: GPT-4.1 Nano", - "created": 1744651369, - "description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...", - "context_length": 1047576, - "pricing": {} - }, - { - "id": "alfredpros/codellama-7b-instruct-solidity", - "name": "AlfredPros: CodeLLaMa 7B Instruct Solidity", - "created": 1744641874, - "description": "A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by PEFT library.", - "context_length": 4096, - "pricing": {} - }, - { - "id": "x-ai/grok-3-mini-beta", - "name": "xAI: Grok 3 Mini Beta", - "created": 1744240195, - "description": "Grok 3 Mini is a lightweight, smaller thinking model. Unlike traditional models that generate answers immediately, Grok 3 Mini thinks before responding. It’s ideal for reasoning-heavy tasks that don’t demand...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "x-ai/grok-3-beta", - "name": "xAI: Grok 3 Beta", - "created": 1744240068, - "description": "Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "meta-llama/llama-4-maverick", - "name": "Meta: Llama 4 Maverick", - "created": 1743881822, - "description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "meta-llama/llama-4-scout", - "name": "Meta: Llama 4 Scout", - "created": 1743881519, - "description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...", - "context_length": 327680, - "pricing": {} - }, - { - "id": "deepseek/deepseek-chat-v3-0324", - "name": "DeepSeek: DeepSeek V3 0324", - "created": 1742824755, - "description": "DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...", - "context_length": 163840, - "pricing": {} - }, - { - "id": "openai/o1-pro", - "name": "OpenAI: o1-pro", - "created": 1742423211, - "description": "The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "mistralai/mistral-small-3.1-24b-instruct", - "name": "Mistral: Mistral Small 3.1 24B", - "created": 1742238937, - "description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "google/gemma-3-4b-it", - "name": "Google: Gemma 3 4B", - "created": 1741905510, - "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "google/gemma-3-12b-it", - "name": "Google: Gemma 3 12B", - "created": 1741902625, - "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "cohere/command-a", - "name": "Cohere: Command A", - "created": 1741894342, - "description": "Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...", - "context_length": 256000, - "pricing": {} - }, - { - "id": "openai/gpt-4o-mini-search-preview", - "name": "OpenAI: GPT-4o-mini Search Preview", - "created": 1741818122, - "description": "GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openai/gpt-4o-search-preview", - "name": "OpenAI: GPT-4o Search Preview", - "created": 1741817949, - "description": "GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.", - "context_length": 128000, - "pricing": {} - }, - { - "id": "rekaai/reka-flash-3", - "name": "Reka Flash 3", - "created": 1741812813, - "description": "Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...", - "context_length": 65536, - "pricing": {} - }, - { - "id": "google/gemma-3-27b-it", - "name": "Google: Gemma 3 27B", - "created": 1741756359, - "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "thedrummer/skyfall-36b-v2", - "name": "TheDrummer: Skyfall 36B V2", - "created": 1741636566, - "description": "Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.", - "context_length": 32768, - "pricing": {} - }, - { - "id": "perplexity/sonar-reasoning-pro", - "name": "Perplexity: Sonar Reasoning Pro", - "created": 1741313308, - "description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "perplexity/sonar-pro", - "name": "Perplexity: Sonar Pro", - "created": 1741312423, - "description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "perplexity/sonar-deep-research", - "name": "Perplexity: Sonar Deep Research", - "created": 1741311246, - "description": "Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "google/gemini-2.0-flash-lite-001", - "name": "Google: Gemini 2.0 Flash Lite", - "created": 1740506212, - "description": "Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5),...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "mistralai/mistral-saba", - "name": "Mistral: Saba", - "created": 1739803239, - "description": "Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "meta-llama/llama-guard-3-8b", - "name": "Llama Guard 3 8B", - "created": 1739401318, - "description": "Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification)...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "openai/o3-mini-high", - "name": "OpenAI: o3 Mini High", - "created": 1739372611, - "description": "OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "google/gemini-2.0-flash-001", - "name": "Google: Gemini 2.0 Flash", - "created": 1738769413, - "description": "Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5). It...", - "context_length": 1048576, - "pricing": {} - }, - { - "id": "aion-labs/aion-1.0", - "name": "AionLabs: Aion-1.0", - "created": 1738697557, - "description": "Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as Tree...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "aion-labs/aion-1.0-mini", - "name": "AionLabs: Aion-1.0-Mini", - "created": 1738697107, - "description": "Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "aion-labs/aion-rp-llama-3.1-8b", - "name": "AionLabs: Aion-RP 1.0 (8B)", - "created": 1738696718, - "description": "Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "qwen/qwen2.5-vl-72b-instruct", - "name": "Qwen: Qwen2.5 VL 72B Instruct", - "created": 1738410311, - "description": "Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.", - "context_length": 32000, - "pricing": {} - }, - { - "id": "qwen/qwen-plus", - "name": "Qwen: Qwen-Plus", - "created": 1738409840, - "description": "Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.", - "context_length": 1000000, - "pricing": {} - }, - { - "id": "openai/o3-mini", - "name": "OpenAI: o3 Mini", - "created": 1738351721, - "description": "OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "mistralai/mistral-small-24b-instruct-2501", - "name": "Mistral: Mistral Small 3", - "created": 1738255409, - "description": "Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "deepseek/deepseek-r1-distill-qwen-32b", - "name": "DeepSeek: R1 Distill Qwen 32B", - "created": 1738194830, - "description": "DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "perplexity/sonar", - "name": "Perplexity: Sonar", - "created": 1738013808, - "description": "Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...", - "context_length": 127072, - "pricing": {} - }, - { - "id": "deepseek/deepseek-r1-distill-llama-70b", - "name": "DeepSeek: R1 Distill Llama 70B", - "created": 1737663169, - "description": "DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "deepseek/deepseek-r1", - "name": "DeepSeek: R1", - "created": 1737381095, - "description": "DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....", - "context_length": 64000, - "pricing": {} - }, - { - "id": "minimax/minimax-01", - "name": "MiniMax: MiniMax-01", - "created": 1736915462, - "description": "MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...", - "context_length": 1000192, - "pricing": {} - }, - { - "id": "microsoft/phi-4", - "name": "Microsoft: Phi 4", - "created": 1736489872, - "description": "[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...", - "context_length": 16384, - "pricing": {} - }, - { - "id": "sao10k/l3.1-70b-hanami-x1", - "name": "Sao10K: Llama 3.1 70B Hanami x1", - "created": 1736302854, - "description": "This is [Sao10K](/sao10k)'s experiment over [Euryale v2.2](/sao10k/l3.1-euryale-70b).", - "context_length": 16000, - "pricing": {} - }, - { - "id": "deepseek/deepseek-chat", - "name": "DeepSeek: DeepSeek V3", - "created": 1735241320, - "description": "DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...", - "context_length": 163840, - "pricing": {} - }, - { - "id": "sao10k/l3.3-euryale-70b", - "name": "Sao10K: Llama 3.3 Euryale 70B", - "created": 1734535928, - "description": "Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).", - "context_length": 131072, - "pricing": {} - }, - { - "id": "openai/o1", - "name": "OpenAI: o1", - "created": 1734459999, - "description": "The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "cohere/command-r7b-12-2024", - "name": "Cohere: Command R7B (12-2024)", - "created": 1734158152, - "description": "Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "meta-llama/llama-3.3-70b-instruct:free", - "name": "Meta: Llama 3.3 70B Instruct (free)", - "created": 1733506137, - "description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...", - "context_length": 65536, - "pricing": {} - }, - { - "id": "meta-llama/llama-3.3-70b-instruct", - "name": "Meta: Llama 3.3 70B Instruct", - "created": 1733506137, - "description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "amazon/nova-lite-v1", - "name": "Amazon: Nova Lite 1.0", - "created": 1733437363, - "description": "Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...", - "context_length": 300000, - "pricing": {} - }, - { - "id": "amazon/nova-micro-v1", - "name": "Amazon: Nova Micro 1.0", - "created": 1733437237, - "description": "Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "amazon/nova-pro-v1", - "name": "Amazon: Nova Pro 1.0", - "created": 1733436303, - "description": "Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...", - "context_length": 300000, - "pricing": {} - }, - { - "id": "openai/gpt-4o-2024-11-20", - "name": "OpenAI: GPT-4o (2024-11-20)", - "created": 1732127594, - "description": "The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance \u0026 readability. It’s also better at working with uploaded...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "mistralai/mistral-large-2411", - "name": "Mistral Large 2411", - "created": 1731978685, - "description": "Mistral Large 2 2411 is an update of [Mistral Large 2](/mistralai/mistral-large) released together with [Pixtral Large 2411](/mistralai/pixtral-large-2411) It provides a significant upgrade on the previous [Mistral Large 24.07](/mistralai/mistral-large-2407), with notable...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "mistralai/mistral-large-2407", - "name": "Mistral Large 2407", - "created": 1731978415, - "description": "This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....", - "context_length": 131072, - "pricing": {} - }, - { - "id": "mistralai/pixtral-large-2411", - "name": "Mistral: Pixtral Large 2411", - "created": 1731977388, - "description": "Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts and natural images. The model is...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "qwen/qwen-2.5-coder-32b-instruct", - "name": "Qwen2.5 Coder 32B Instruct", - "created": 1731368400, - "description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "thedrummer/unslopnemo-12b", - "name": "TheDrummer: UnslopNemo 12B", - "created": 1731103448, - "description": "UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.", - "context_length": 32768, - "pricing": {} - }, - { - "id": "anthropic/claude-3.5-haiku", - "name": "Anthropic: Claude 3.5 Haiku", - "created": 1730678400, - "description": "Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic...", - "context_length": 200000, - "pricing": {} - }, - { - "id": "anthracite-org/magnum-v4-72b", - "name": "Magnum v4 72B", - "created": 1729555200, - "description": "This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).", - "context_length": 16384, - "pricing": {} - }, - { - "id": "qwen/qwen-2.5-7b-instruct", - "name": "Qwen: Qwen2.5 7B Instruct", - "created": 1729036800, - "description": "Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "inflection/inflection-3-pi", - "name": "Inflection: Inflection 3 Pi", - "created": 1728604800, - "description": "Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like customer support and roleplay. Pi...", - "context_length": 8000, - "pricing": {} - }, - { - "id": "inflection/inflection-3-productivity", - "name": "Inflection: Inflection 3 Productivity", - "created": 1728604800, - "description": "Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent news. For emotional...", - "context_length": 8000, - "pricing": {} - }, - { - "id": "thedrummer/rocinante-12b", - "name": "TheDrummer: Rocinante 12B", - "created": 1727654400, - "description": "Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "meta-llama/llama-3.2-1b-instruct", - "name": "Meta: Llama 3.2 1B Instruct", - "created": 1727222400, - "description": "Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...", - "context_length": 60000, - "pricing": {} - }, - { - "id": "meta-llama/llama-3.2-3b-instruct:free", - "name": "Meta: Llama 3.2 3B Instruct (free)", - "created": 1727222400, - "description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "meta-llama/llama-3.2-3b-instruct", - "name": "Meta: Llama 3.2 3B Instruct", - "created": 1727222400, - "description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...", - "context_length": 80000, - "pricing": {} - }, - { - "id": "meta-llama/llama-3.2-11b-vision-instruct", - "name": "Meta: Llama 3.2 11B Vision Instruct", - "created": 1727222400, - "description": "Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "qwen/qwen-2.5-72b-instruct", - "name": "Qwen2.5 72B Instruct", - "created": 1726704000, - "description": "Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...", - "context_length": 32768, - "pricing": {} - }, - { - "id": "cohere/command-r-plus-08-2024", - "name": "Cohere: Command R+ (08-2024)", - "created": 1724976000, - "description": "command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "cohere/command-r-08-2024", - "name": "Cohere: Command R (08-2024)", - "created": 1724976000, - "description": "command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "sao10k/l3.1-euryale-70b", - "name": "Sao10K: Llama 3.1 Euryale 70B v2.2", - "created": 1724803200, - "description": "Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).", - "context_length": 131072, - "pricing": {} - }, - { - "id": "nousresearch/hermes-3-llama-3.1-70b", - "name": "Nous: Hermes 3 70B Instruct", - "created": 1723939200, - "description": "Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "nousresearch/hermes-3-llama-3.1-405b:free", - "name": "Nous: Hermes 3 405B Instruct (free)", - "created": 1723766400, - "description": "Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "nousresearch/hermes-3-llama-3.1-405b", - "name": "Nous: Hermes 3 405B Instruct", - "created": 1723766400, - "description": "Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "sao10k/l3-lunaris-8b", - "name": "Sao10K: Llama 3 8B Lunaris", - "created": 1723507200, - "description": "Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....", - "context_length": 8192, - "pricing": {} - }, - { - "id": "openai/gpt-4o-2024-08-06", - "name": "OpenAI: GPT-4o (2024-08-06)", - "created": 1722902400, - "description": "The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "meta-llama/llama-3.1-8b-instruct", - "name": "Meta: Llama 3.1 8B Instruct", - "created": 1721692800, - "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes \u0026 flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...", - "context_length": 16384, - "pricing": {} - }, - { - "id": "meta-llama/llama-3.1-70b-instruct", - "name": "Meta: Llama 3.1 70B Instruct", - "created": 1721692800, - "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes \u0026 flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "mistralai/mistral-nemo", - "name": "Mistral: Mistral Nemo", - "created": 1721347200, - "description": "A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...", - "context_length": 131072, - "pricing": {} - }, - { - "id": "openai/gpt-4o-mini", - "name": "OpenAI: GPT-4o-mini", - "created": 1721260800, - "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openai/gpt-4o-mini-2024-07-18", - "name": "OpenAI: GPT-4o-mini (2024-07-18)", - "created": 1721260800, - "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "google/gemma-2-27b-it", - "name": "Google: Gemma 2 27B", - "created": 1720828800, - "description": "Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...", - "context_length": 8192, - "pricing": {} - }, - { - "id": "sao10k/l3-euryale-70b", - "name": "Sao10k: Llama 3 Euryale 70B v2.1", - "created": 1718668800, - "description": "Euryale 70B v2.1 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). - Better prompt adherence. - Better anatomy / spatial awareness. - Adapts much better to unique and custom...", - "context_length": 8192, - "pricing": {} - }, - { - "id": "nousresearch/hermes-2-pro-llama-3-8b", - "name": "NousResearch: Hermes 2 Pro - Llama-3 8B", - "created": 1716768000, - "description": "Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced...", - "context_length": 8192, - "pricing": {} - }, - { - "id": "openai/gpt-4o", - "name": "OpenAI: GPT-4o", - "created": 1715558400, - "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openai/gpt-4o-2024-05-13", - "name": "OpenAI: GPT-4o (2024-05-13)", - "created": 1715558400, - "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "meta-llama/llama-3-8b-instruct", - "name": "Meta: Llama 3 8B Instruct", - "created": 1713398400, - "description": "Meta's latest class of model (Llama 3) launched with a variety of sizes \u0026 flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...", - "context_length": 8192, - "pricing": {} - }, - { - "id": "meta-llama/llama-3-70b-instruct", - "name": "Meta: Llama 3 70B Instruct", - "created": 1713398400, - "description": "Meta's latest class of model (Llama 3) launched with a variety of sizes \u0026 flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...", - "context_length": 8192, - "pricing": {} - }, - { - "id": "mistralai/mixtral-8x22b-instruct", - "name": "Mistral: Mixtral 8x22B Instruct", - "created": 1713312000, - "description": "Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...", - "context_length": 65536, - "pricing": {} - }, - { - "id": "microsoft/wizardlm-2-8x22b", - "name": "WizardLM-2 8x22B", - "created": 1713225600, - "description": "WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...", - "context_length": 65535, - "pricing": {} - }, - { - "id": "openai/gpt-4-turbo", - "name": "OpenAI: GPT-4 Turbo", - "created": 1712620800, - "description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.", - "context_length": 128000, - "pricing": {} - }, - { - "id": "anthropic/claude-3-haiku", - "name": "Anthropic: Claude 3 Haiku", - "created": 1710288000, - "description": "Claude 3 Haiku is Anthropic's fastest and most compact model for\nnear-instant responsiveness. Quick and accurate targeted performance.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)\n\n#multimodal", - "context_length": 200000, - "pricing": {} - }, - { - "id": "mistralai/mistral-large", - "name": "Mistral Large", - "created": 1708905600, - "description": "This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openai/gpt-3.5-turbo-0613", - "name": "OpenAI: GPT-3.5 Turbo (older v0613)", - "created": 1706140800, - "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.", - "context_length": 4095, - "pricing": {} - }, - { - "id": "openai/gpt-4-turbo-preview", - "name": "OpenAI: GPT-4 Turbo Preview", - "created": 1706140800, - "description": "The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...", - "context_length": 128000, - "pricing": {} - }, - { - "id": "openrouter/auto", - "name": "Auto Router", - "created": 1699401600, - "description": "Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used,...", - "context_length": 2000000, - "pricing": {} - }, - { - "id": "openai/gpt-4-1106-preview", - "name": "OpenAI: GPT-4 Turbo (older v1106)", - "created": 1699228800, - "description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to April 2023.", - "context_length": 128000, - "pricing": {} - }, - { - "id": "mistralai/mistral-7b-instruct-v0.1", - "name": "Mistral: Mistral 7B Instruct v0.1", - "created": 1695859200, - "description": "A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length.", - "context_length": 2824, - "pricing": {} - }, - { - "id": "openai/gpt-3.5-turbo-instruct", - "name": "OpenAI: GPT-3.5 Turbo Instruct", - "created": 1695859200, - "description": "This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.", - "context_length": 4095, - "pricing": {} - }, - { - "id": "openai/gpt-3.5-turbo-16k", - "name": "OpenAI: GPT-3.5 Turbo 16k", - "created": 1693180800, - "description": "This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...", - "context_length": 16385, - "pricing": {} - }, - { - "id": "mancer/weaver", - "name": "Mancer: Weaver (alpha)", - "created": 1690934400, - "description": "An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.", - "context_length": 8000, - "pricing": {} - }, - { - "id": "undi95/remm-slerp-l2-13b", - "name": "ReMM SLERP 13B", - "created": 1689984000, - "description": "A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge", - "context_length": 6144, - "pricing": {} - }, - { - "id": "gryphe/mythomax-l2-13b", - "name": "MythoMax 13B", - "created": 1688256000, - "description": "One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge", - "context_length": 4096, - "pricing": {} - }, - { - "id": "openai/gpt-4", - "name": "OpenAI: GPT-4", - "created": 1685232000, - "description": "OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...", - "context_length": 8191, - "pricing": {} - }, - { - "id": "openai/gpt-4-0314", - "name": "OpenAI: GPT-4 (older v0314)", - "created": 1685232000, - "description": "GPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 14. Training data: up to Sep 2021.", - "context_length": 8191, - "pricing": {} - }, - { - "id": "openai/gpt-3.5-turbo", - "name": "OpenAI: GPT-3.5 Turbo", - "created": 1685232000, - "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.", - "context_length": 16385, - "pricing": {} - } - ], - "paid": 0, - "total": 363 -} diff --git a/reports/daily/2026/05/daily_report_2026-05-10.html b/reports/daily/2026/05/daily_report_2026-05-10.html deleted file mode 100644 index 6045aa6..0000000 --- a/reports/daily/2026/05/daily_report_2026-05-10.html +++ /dev/null @@ -1,33 +0,0 @@ - -LLM Hub - 2026-05-10 - -

🤖 LLM Intelligence Hub

每日情报报告 - 2026-05-10

- -
-

📊 数据质量摘要

- - - - - - -
指标数值
模型总数14
数据新鲜12
CNY定价10
USD定价2
厂商总数13
- - -

💸 低价模型 TOP 10

- - -
排名模型厂商输入价格
1qwen/qwen3-vl-8b阿里巴巴$0.2
2qwen/qwen3-vl-32b阿里巴巴$0.5
3bytedance/doubao-pro字节跳动$0.8
4deepseek/deepseek-v3DeepSeek$1
5tencent/hunyuan-pro腾讯$1.5
6deepseek/deepseek-r1DeepSeek$2
7moonshotai/kimi-k2.5月之暗面$2
8baidu/ernie-4.0百度$2
9openai/gpt-4oOpenAI$2.5
10zhipuai/glm-5.1智谱AI$3
- - -

📌 本报告由 LLM Intelligence Hub 自动生成

- \ No newline at end of file diff --git a/reports/daily/2026/05/daily_report_2026-05-10.md b/reports/daily/2026/05/daily_report_2026-05-10.md deleted file mode 100644 index 29a81e8..0000000 --- a/reports/daily/2026/05/daily_report_2026-05-10.md +++ /dev/null @@ -1,57 +0,0 @@ -# 🤖 LLM Intelligence Hub - 每日情报报告 - -**报告日期**: 2026-05-10 -**生成时间**: 2026-05-10T18:31:19+08:00 - -## 📊 数据质量摘要 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 14 | -| 数据新鲜 | 12 | -| 数据待补 | 2 | -| CNY定价 | 10 | -| USD定价 | 2 | -| 厂商总数 | 13 | - -## 🆓 免费模型 TOP 10 - -| 模型 | 厂商 | 上下文 | -|------|------|--------| -| anthropic/claude-3.5-sonnet:free | Anthropic | 200000 | - -## 💸 低价模型 TOP 10 - -| 排名 | 模型 | 厂商 | 输入价格 | -|------|------|------|----------| -| 1 | qwen/qwen3-vl-8b | 阿里巴巴 | $0.2000 | -| 2 | qwen/qwen3-vl-32b | 阿里巴巴 | $0.5000 | -| 3 | bytedance/doubao-pro | 字节跳动 | $0.8000 | -| 4 | deepseek/deepseek-v3 | DeepSeek | $1.0000 | -| 5 | tencent/hunyuan-pro | 腾讯 | $1.5000 | -| 6 | deepseek/deepseek-r1 | DeepSeek | $2.0000 | -| 7 | moonshotai/kimi-k2.5 | 月之暗面 | $2.0000 | -| 8 | baidu/ernie-4.0 | 百度 | $2.0000 | -| 9 | openai/gpt-4o | OpenAI | $2.5000 | -| 10 | zhipuai/glm-5.1 | 智谱AI | $3.0000 | - -## 📏 大上下文模型 TOP 10 - -| 排名 | 模型 | 厂商 | 上下文长度 | -|------|------|------|------------| -| 1 | moonshotai/kimi-k2.6 | 月之暗面 | 256000 | -| 2 | anthropic/claude-3.5-sonnet:free | Anthropic | 200000 | -| 3 | zhipuai/glm-4.7 | 智谱AI | 128000 | -| 4 | openai/gpt-4o | OpenAI | 128000 | -| 5 | deepseek/deepseek-v4 | DeepSeek | 128000 | -| 6 | zhipuai/glm-5.1 | 智谱AI | 128000 | -| 7 | moonshotai/kimi-k2.5 | 月之暗面 | 128000 | -| 8 | deepseek/deepseek-r1 | DeepSeek | 64000 | -| 9 | deepseek/deepseek-v3 | DeepSeek | 64000 | -| 10 | qwen/qwen3-vl-8b | 阿里巴巴 | 32000 | - ---- - -📌 **说明**: 本报告由 LLM Intelligence Hub 自动生成。价格单位：USD/1M tokens。 - -_生成时间: 2026-05-10T18:31:19+08:00_ diff --git a/reports/daily/2026/05/daily_report_2026-05-11.html b/reports/daily/2026/05/daily_report_2026-05-11.html deleted file mode 100644 index 6d2cdb7..0000000 --- a/reports/daily/2026/05/daily_report_2026-05-11.html +++ /dev/null @@ -1,33 +0,0 @@ - -LLM Hub - 2026-05-11 - -

🤖 LLM Intelligence Hub

每日情报报告 - 2026-05-11

- -
-

📊 数据质量摘要

- - - - - - -
指标数值
模型总数377
数据新鲜368
CNY定价0
USD定价377
厂商总数60
- - -

💸 低价模型 TOP 10

- - -
排名模型厂商输入价格
1openai/gpt-4oOpenai$2.5
- - -

📌 本报告由 LLM Intelligence Hub 自动生成

- \ No newline at end of file diff --git a/reports/daily/2026/05/daily_report_2026-05-11.md b/reports/daily/2026/05/daily_report_2026-05-11.md deleted file mode 100644 index 94b1cdc..0000000 --- a/reports/daily/2026/05/daily_report_2026-05-11.md +++ /dev/null @@ -1,414 +0,0 @@ -# 🤖 LLM Intelligence Hub - 每日情报报告 - -**报告日期**: 2026-05-11 -**生成时间**: 2026-05-11T08:00:02+08:00 - -## 📊 数据质量摘要 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 377 | -| 数据新鲜 | 368 | -| 数据待补 | 9 | -| CNY定价 | 0 | -| USD定价 | 377 | -| 厂商总数 | 60 | - -## 🆓 免费模型 TOP 10 - -| 模型 | 厂商 | 上下文 | -|------|------|--------| -| anthropic/claude-3.5-sonnet:free | Anthropic | 200000 | -| deepseek/deepseek-r1 | Deepseek | 64000 | -| moonshotai/kimi-k2.6 | Moonshotai | 262144 | -| moonshotai/kimi-k2.5 | Moonshotai | 262144 | -| inclusionai/ring-2.6-1t:free | Inclusionai | 262144 | -| google/gemini-3.1-flash-lite | Google | 1048576 | -| baidu/cobuddy:free | Baidu | 131072 | -| openai/gpt-chat-latest | Openai | 400000 | -| x-ai/grok-4.3 | X Ai | 1000000 | -| ibm-granite/granite-4.1-8b | Ibm Granite | 131072 | -| mistralai/mistral-medium-3-5 | Mistralai | 262144 | -| openrouter/owl-alpha | Openrouter | 1048756 | -| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | Nvidia | 256000 | -| poolside/laguna-xs.2:free | Poolside | 131072 | -| poolside/laguna-m.1:free | Poolside | 131072 | -| ~anthropic/claude-haiku-latest | ~anthropic | 200000 | -| ~openai/gpt-mini-latest | ~openai | 400000 | -| ~google/gemini-pro-latest | ~google | 1048576 | -| ~moonshotai/kimi-latest | ~moonshotai | 262144 | -| ~google/gemini-flash-latest | ~google | 1048576 | -| ~anthropic/claude-sonnet-latest | ~anthropic | 1000000 | -| ~openai/gpt-latest | ~openai | 1050000 | -| qwen/qwen3.5-plus-20260420 | Qwen | 1000000 | -| qwen/qwen3.6-flash | Qwen | 1000000 | -| qwen/qwen3.6-35b-a3b | Qwen | 262144 | -| qwen/qwen3.6-max-preview | Qwen | 262144 | -| qwen/qwen3.6-27b | Qwen | 262144 | -| openai/gpt-5.5-pro | Openai | 1050000 | -| openai/gpt-5.5 | Openai | 1050000 | -| deepseek/deepseek-v4-pro | Deepseek | 1048576 | -| deepseek/deepseek-v4-flash | Deepseek | 1048576 | -| inclusionai/ling-2.6-1t | Inclusionai | 262144 | -| tencent/hy3-preview | Tencent | 262144 | -| xiaomi/mimo-v2.5-pro | Xiaomi | 1048576 | -| xiaomi/mimo-v2.5 | Xiaomi | 1048576 | -| openai/gpt-5.4-image-2 | Openai | 272000 | -| inclusionai/ling-2.6-flash | Inclusionai | 262144 | -| ~anthropic/claude-opus-latest | ~anthropic | 1000000 | -| openrouter/pareto-code | Openrouter | 2000000 | -| baidu/qianfan-ocr-fast:free | Baidu | 65536 | -| anthropic/claude-opus-4.7 | Anthropic | 1000000 | -| anthropic/claude-opus-4.6-fast | Anthropic | 1000000 | -| z-ai/glm-5.1 | Z Ai | 202752 | -| google/gemma-4-26b-a4b-it:free | Google | 262144 | -| google/gemma-4-26b-a4b-it | Google | 262144 | -| google/gemma-4-31b-it:free | Google | 262144 | -| google/gemma-4-31b-it | Google | 262144 | -| qwen/qwen3.6-plus | Qwen | 1000000 | -| z-ai/glm-5v-turbo | Z Ai | 202752 | -| arcee-ai/trinity-large-thinking | Arcee Ai | 262144 | -| x-ai/grok-4.20-multi-agent | X Ai | 2000000 | -| x-ai/grok-4.20 | X Ai | 2000000 | -| google/lyria-3-pro-preview | Google | 1048576 | -| google/lyria-3-clip-preview | Google | 1048576 | -| kwaipilot/kat-coder-pro-v2 | Kwaipilot | 256000 | -| rekaai/reka-edge | Rekaai | 16384 | -| xiaomi/mimo-v2-omni | Xiaomi | 262144 | -| xiaomi/mimo-v2-pro | Xiaomi | 1048576 | -| minimax/minimax-m2.7 | Minimax | 196608 | -| openai/gpt-5.4-nano | Openai | 400000 | -| openai/gpt-5.4-mini | Openai | 400000 | -| mistralai/mistral-small-2603 | Mistralai | 262144 | -| z-ai/glm-5-turbo | Z Ai | 202752 | -| nvidia/nemotron-3-super-120b-a12b:free | Nvidia | 262144 | -| nvidia/nemotron-3-super-120b-a12b | Nvidia | 262144 | -| bytedance-seed/seed-2.0-lite | Bytedance Seed | 262144 | -| qwen/qwen3.5-9b | Qwen | 262144 | -| openai/gpt-5.4-pro | Openai | 1050000 | -| openai/gpt-5.4 | Openai | 1050000 | -| inception/mercury-2 | Inception | 128000 | -| openai/gpt-5.3-chat | Openai | 128000 | -| google/gemini-3.1-flash-lite-preview | Google | 1048576 | -| bytedance-seed/seed-2.0-mini | Bytedance Seed | 262144 | -| google/gemini-3.1-flash-image-preview | Google | 65536 | -| qwen/qwen3.5-35b-a3b | Qwen | 262144 | -| qwen/qwen3.5-27b | Qwen | 262144 | -| qwen/qwen3.5-122b-a10b | Qwen | 262144 | -| qwen/qwen3.5-flash-02-23 | Qwen | 1000000 | -| liquid/lfm-2-24b-a2b | Liquid | 32768 | -| google/gemini-3.1-pro-preview-customtools | Google | 1048576 | -| openai/gpt-5.3-codex | Openai | 400000 | -| aion-labs/aion-2.0 | Aion Labs | 131072 | -| google/gemini-3.1-pro-preview | Google | 1048576 | -| anthropic/claude-sonnet-4.6 | Anthropic | 1000000 | -| qwen/qwen3.5-plus-02-15 | Qwen | 1000000 | -| qwen/qwen3.5-397b-a17b | Qwen | 262144 | -| minimax/minimax-m2.5:free | Minimax | 196608 | -| minimax/minimax-m2.5 | Minimax | 196608 | -| z-ai/glm-5 | Z Ai | 202752 | -| qwen/qwen3-max-thinking | Qwen | 262144 | -| anthropic/claude-opus-4.6 | Anthropic | 1000000 | -| qwen/qwen3-coder-next | Qwen | 262144 | -| openrouter/free | Openrouter | 200000 | -| stepfun/step-3.5-flash | Stepfun | 262144 | -| arcee-ai/trinity-large-preview | Arcee Ai | 131000 | -| upstage/solar-pro-3 | Upstage | 128000 | -| minimax/minimax-m2-her | Minimax | 65536 | -| writer/palmyra-x5 | Writer | 1040000 | -| liquid/lfm-2.5-1.2b-thinking:free | Liquid | 32768 | -| liquid/lfm-2.5-1.2b-instruct:free | Liquid | 32768 | -| openai/gpt-audio | Openai | 128000 | -| openai/gpt-audio-mini | Openai | 128000 | -| z-ai/glm-4.7-flash | Z Ai | 202752 | -| openai/gpt-5.2-codex | Openai | 400000 | -| bytedance-seed/seed-1.6-flash | Bytedance Seed | 262144 | -| bytedance-seed/seed-1.6 | Bytedance Seed | 262144 | -| minimax/minimax-m2.1 | Minimax | 196608 | -| z-ai/glm-4.7 | Z Ai | 202752 | -| google/gemini-3-flash-preview | Google | 1048576 | -| xiaomi/mimo-v2-flash | Xiaomi | 262144 | -| nvidia/nemotron-3-nano-30b-a3b:free | Nvidia | 256000 | -| nvidia/nemotron-3-nano-30b-a3b | Nvidia | 262144 | -| openai/gpt-5.2-chat | Openai | 128000 | -| openai/gpt-5.2-pro | Openai | 400000 | -| openai/gpt-5.2 | Openai | 400000 | -| mistralai/devstral-2512 | Mistralai | 262144 | -| relace/relace-search | Relace | 256000 | -| z-ai/glm-4.6v | Z Ai | 131072 | -| nex-agi/deepseek-v3.1-nex-n1 | Nex Agi | 131072 | -| essentialai/rnj-1-instruct | Essentialai | 32768 | -| openrouter/bodybuilder | Openrouter | 128000 | -| openai/gpt-5.1-codex-max | Openai | 400000 | -| amazon/nova-2-lite-v1 | Amazon | 1000000 | -| mistralai/ministral-14b-2512 | Mistralai | 262144 | -| mistralai/ministral-8b-2512 | Mistralai | 262144 | -| mistralai/ministral-3b-2512 | Mistralai | 131072 | -| mistralai/mistral-large-2512 | Mistralai | 262144 | -| arcee-ai/trinity-mini | Arcee Ai | 131072 | -| deepseek/deepseek-v3.2-speciale | Deepseek | 163840 | -| deepseek/deepseek-v3.2 | Deepseek | 131072 | -| prime-intellect/intellect-3 | Prime Intellect | 131072 | -| anthropic/claude-opus-4.5 | Anthropic | 200000 | -| allenai/olmo-3-32b-think | Allenai | 65536 | -| google/gemini-3-pro-image-preview | Google | 65536 | -| x-ai/grok-4.1-fast | X Ai | 2000000 | -| deepcogito/cogito-v2.1-671b | Deepcogito | 128000 | -| openai/gpt-5.1 | Openai | 400000 | -| openai/gpt-5.1-chat | Openai | 128000 | -| openai/gpt-5.1-codex | Openai | 400000 | -| openai/gpt-5.1-codex-mini | Openai | 400000 | -| moonshotai/kimi-k2-thinking | Moonshotai | 262144 | -| amazon/nova-premier-v1 | Amazon | 1000000 | -| perplexity/sonar-pro-search | Perplexity | 200000 | -| mistralai/voxtral-small-24b-2507 | Mistralai | 32000 | -| openai/gpt-oss-safeguard-20b | Openai | 131072 | -| nvidia/nemotron-nano-12b-v2-vl:free | Nvidia | 128000 | -| minimax/minimax-m2 | Minimax | 196608 | -| qwen/qwen3-vl-32b-instruct | Qwen | 131072 | -| ibm-granite/granite-4.0-h-micro | Ibm Granite | 131000 | -| microsoft/phi-4-mini-instruct | Microsoft | 128000 | -| openai/gpt-5-image-mini | Openai | 400000 | -| anthropic/claude-haiku-4.5 | Anthropic | 200000 | -| qwen/qwen3-vl-8b-thinking | Qwen | 131072 | -| qwen/qwen3-vl-8b-instruct | Qwen | 131072 | -| openai/gpt-5-image | Openai | 400000 | -| openai/o3-deep-research | Openai | 200000 | -| openai/o4-mini-deep-research | Openai | 200000 | -| nvidia/llama-3.3-nemotron-super-49b-v1.5 | Nvidia | 131072 | -| baidu/ernie-4.5-21b-a3b-thinking | Baidu | 131072 | -| google/gemini-2.5-flash-image | Google | 32768 | -| qwen/qwen3-vl-30b-a3b-thinking | Qwen | 131072 | -| qwen/qwen3-vl-30b-a3b-instruct | Qwen | 131072 | -| openai/gpt-5-pro | Openai | 400000 | -| z-ai/glm-4.6 | Z Ai | 204800 | -| anthropic/claude-sonnet-4.5 | Anthropic | 1000000 | -| deepseek/deepseek-v3.2-exp | Deepseek | 163840 | -| thedrummer/cydonia-24b-v4.1 | Thedrummer | 131072 | -| relace/relace-apply-3 | Relace | 256000 | -| google/gemini-2.5-flash-lite-preview-09-2025 | Google | 1048576 | -| qwen/qwen3-vl-235b-a22b-thinking | Qwen | 131072 | -| qwen/qwen3-vl-235b-a22b-instruct | Qwen | 262144 | -| qwen/qwen3-max | Qwen | 262144 | -| qwen/qwen3-coder-plus | Qwen | 1000000 | -| openai/gpt-5-codex | Openai | 400000 | -| deepseek/deepseek-v3.1-terminus | Deepseek | 163840 | -| x-ai/grok-4-fast | X Ai | 2000000 | -| alibaba/tongyi-deepresearch-30b-a3b | Alibaba | 131072 | -| qwen/qwen3-coder-flash | Qwen | 1000000 | -| qwen/qwen3-next-80b-a3b-thinking | Qwen | 131072 | -| qwen/qwen3-next-80b-a3b-instruct:free | Qwen | 262144 | -| qwen/qwen3-next-80b-a3b-instruct | Qwen | 262144 | -| qwen/qwen-plus-2025-07-28:thinking | Qwen | 1000000 | -| qwen/qwen-plus-2025-07-28 | Qwen | 1000000 | -| nvidia/nemotron-nano-9b-v2:free | Nvidia | 128000 | -| nvidia/nemotron-nano-9b-v2 | Nvidia | 131072 | -| moonshotai/kimi-k2-0905 | Moonshotai | 262144 | -| qwen/qwen3-30b-a3b-thinking-2507 | Qwen | 131072 | -| x-ai/grok-code-fast-1 | X Ai | 256000 | -| nousresearch/hermes-4-70b | Nousresearch | 131072 | -| nousresearch/hermes-4-405b | Nousresearch | 131072 | -| deepseek/deepseek-chat-v3.1 | Deepseek | 32768 | -| openai/gpt-4o-audio-preview | Openai | 128000 | -| mistralai/mistral-medium-3.1 | Mistralai | 131072 | -| baidu/ernie-4.5-21b-a3b | Baidu | 120000 | -| baidu/ernie-4.5-vl-28b-a3b | Baidu | 30000 | -| z-ai/glm-4.5v | Z Ai | 65536 | -| ai21/jamba-large-1.7 | Ai21 | 256000 | -| openai/gpt-5-chat | Openai | 128000 | -| openai/gpt-5 | Openai | 400000 | -| openai/gpt-5-mini | Openai | 400000 | -| openai/gpt-5-nano | Openai | 400000 | -| openai/gpt-oss-120b:free | Openai | 131072 | -| openai/gpt-oss-120b | Openai | 131072 | -| openai/gpt-oss-20b:free | Openai | 131072 | -| openai/gpt-oss-20b | Openai | 131072 | -| anthropic/claude-opus-4.1 | Anthropic | 200000 | -| mistralai/codestral-2508 | Mistralai | 256000 | -| qwen/qwen3-coder-30b-a3b-instruct | Qwen | 160000 | -| qwen/qwen3-30b-a3b-instruct-2507 | Qwen | 262144 | -| z-ai/glm-4.5 | Z Ai | 131072 | -| z-ai/glm-4.5-air:free | Z Ai | 131072 | -| z-ai/glm-4.5-air | Z Ai | 131072 | -| qwen/qwen3-235b-a22b-thinking-2507 | Qwen | 131072 | -| z-ai/glm-4-32b | Z Ai | 128000 | -| qwen/qwen3-coder:free | Qwen | 262000 | -| qwen/qwen3-coder | Qwen | 262144 | -| bytedance/ui-tars-1.5-7b | Bytedance | 128000 | -| google/gemini-2.5-flash-lite | Google | 1048576 | -| qwen/qwen3-235b-a22b-2507 | Qwen | 262144 | -| switchpoint/router | Switchpoint | 131072 | -| moonshotai/kimi-k2 | Moonshotai | 131072 | -| mistralai/devstral-medium | Mistralai | 131072 | -| mistralai/devstral-small | Mistralai | 131072 | -| cognitivecomputations/dolphin-mistral-24b-venice-edition:free | Cognitivecomputations | 32768 | -| x-ai/grok-4 | X Ai | 256000 | -| tencent/hunyuan-a13b-instruct | Tencent | 131072 | -| morph/morph-v3-large | Morph | 262144 | -| morph/morph-v3-fast | Morph | 81920 | -| baidu/ernie-4.5-vl-424b-a47b | Baidu | 123000 | -| baidu/ernie-4.5-300b-a47b | Baidu | 123000 | -| mistralai/mistral-small-3.2-24b-instruct | Mistralai | 128000 | -| minimax/minimax-m1 | Minimax | 1000000 | -| google/gemini-2.5-flash | Google | 1048576 | -| google/gemini-2.5-pro | Google | 1048576 | -| openai/o3-pro | Openai | 200000 | -| x-ai/grok-3-mini | X Ai | 131072 | -| x-ai/grok-3 | X Ai | 131072 | -| google/gemini-2.5-pro-preview | Google | 1048576 | -| deepseek/deepseek-r1-0528 | Deepseek | 163840 | -| anthropic/claude-opus-4 | Anthropic | 200000 | -| anthropic/claude-sonnet-4 | Anthropic | 1000000 | -| google/gemma-3n-e4b-it | Google | 32768 | -| mistralai/mistral-medium-3 | Mistralai | 131072 | -| google/gemini-2.5-pro-preview-05-06 | Google | 1048576 | -| arcee-ai/spotlight | Arcee Ai | 131072 | -| arcee-ai/maestro-reasoning | Arcee Ai | 131072 | -| arcee-ai/virtuoso-large | Arcee Ai | 131072 | -| arcee-ai/coder-large | Arcee Ai | 32768 | -| meta-llama/llama-guard-4-12b | Meta Llama | 163840 | -| qwen/qwen3-30b-a3b | Qwen | 40960 | -| qwen/qwen3-8b | Qwen | 40960 | -| qwen/qwen3-14b | Qwen | 40960 | -| qwen/qwen3-32b | Qwen | 40960 | -| qwen/qwen3-235b-a22b | Qwen | 131072 | -| openai/o4-mini-high | Openai | 200000 | -| openai/o3 | Openai | 200000 | -| openai/o4-mini | Openai | 200000 | -| openai/gpt-4.1 | Openai | 1047576 | -| openai/gpt-4.1-mini | Openai | 1047576 | -| openai/gpt-4.1-nano | Openai | 1047576 | -| alfredpros/codellama-7b-instruct-solidity | Alfredpros | 4096 | -| x-ai/grok-3-mini-beta | X Ai | 131072 | -| x-ai/grok-3-beta | X Ai | 131072 | -| meta-llama/llama-4-maverick | Meta Llama | 1048576 | -| meta-llama/llama-4-scout | Meta Llama | 327680 | -| deepseek/deepseek-chat-v3-0324 | Deepseek | 163840 | -| openai/o1-pro | Openai | 200000 | -| mistralai/mistral-small-3.1-24b-instruct | Mistralai | 128000 | -| google/gemma-3-4b-it | Google | 131072 | -| google/gemma-3-12b-it | Google | 131072 | -| cohere/command-a | Cohere | 256000 | -| openai/gpt-4o-mini-search-preview | Openai | 128000 | -| openai/gpt-4o-search-preview | Openai | 128000 | -| rekaai/reka-flash-3 | Rekaai | 65536 | -| google/gemma-3-27b-it | Google | 131072 | -| thedrummer/skyfall-36b-v2 | Thedrummer | 32768 | -| perplexity/sonar-reasoning-pro | Perplexity | 128000 | -| perplexity/sonar-pro | Perplexity | 200000 | -| perplexity/sonar-deep-research | Perplexity | 128000 | -| google/gemini-2.0-flash-lite-001 | Google | 1048576 | -| anthropic/claude-3.7-sonnet | Anthropic | 200000 | -| anthropic/claude-3.7-sonnet:thinking | Anthropic | 200000 | -| mistralai/mistral-saba | Mistralai | 32768 | -| meta-llama/llama-guard-3-8b | Meta Llama | 131072 | -| openai/o3-mini-high | Openai | 200000 | -| google/gemini-2.0-flash-001 | Google | 1000000 | -| qwen/qwen-vl-plus | Qwen | 131072 | -| aion-labs/aion-1.0 | Aion Labs | 131072 | -| aion-labs/aion-1.0-mini | Aion Labs | 131072 | -| aion-labs/aion-rp-llama-3.1-8b | Aion Labs | 32768 | -| qwen/qwen-vl-max | Qwen | 131072 | -| qwen/qwen-turbo | Qwen | 131072 | -| qwen/qwen2.5-vl-72b-instruct | Qwen | 32000 | -| qwen/qwen-plus | Qwen | 1000000 | -| qwen/qwen-max | Qwen | 32768 | -| openai/o3-mini | Openai | 200000 | -| mistralai/mistral-small-24b-instruct-2501 | Mistralai | 32768 | -| deepseek/deepseek-r1-distill-qwen-32b | Deepseek | 32768 | -| perplexity/sonar | Perplexity | 127072 | -| deepseek/deepseek-r1-distill-llama-70b | Deepseek | 131072 | -| minimax/minimax-01 | Minimax | 1000192 | -| microsoft/phi-4 | Microsoft | 16384 | -| sao10k/l3.1-70b-hanami-x1 | Sao10k | 16000 | -| deepseek/deepseek-chat | Deepseek | 163840 | -| sao10k/l3.3-euryale-70b | Sao10k | 131072 | -| openai/o1 | Openai | 200000 | -| cohere/command-r7b-12-2024 | Cohere | 128000 | -| meta-llama/llama-3.3-70b-instruct:free | Meta Llama | 65536 | -| meta-llama/llama-3.3-70b-instruct | Meta Llama | 131072 | -| amazon/nova-lite-v1 | Amazon | 300000 | -| amazon/nova-micro-v1 | Amazon | 128000 | -| amazon/nova-pro-v1 | Amazon | 300000 | -| openai/gpt-4o-2024-11-20 | Openai | 128000 | -| mistralai/mistral-large-2411 | Mistralai | 131072 | -| mistralai/mistral-large-2407 | Mistralai | 131072 | -| mistralai/pixtral-large-2411 | Mistralai | 131072 | -| qwen/qwen-2.5-coder-32b-instruct | Qwen | 32768 | -| thedrummer/unslopnemo-12b | Thedrummer | 32768 | -| anthropic/claude-3.5-haiku | Anthropic | 200000 | -| anthracite-org/magnum-v4-72b | Anthracite Org | 16384 | -| qwen/qwen-2.5-7b-instruct | Qwen | 32768 | -| inflection/inflection-3-productivity | Inflection | 8000 | -| inflection/inflection-3-pi | Inflection | 8000 | -| thedrummer/rocinante-12b | Thedrummer | 32768 | -| meta-llama/llama-3.2-3b-instruct:free | Meta Llama | 131072 | -| meta-llama/llama-3.2-3b-instruct | Meta Llama | 80000 | -| meta-llama/llama-3.2-1b-instruct | Meta Llama | 60000 | -| meta-llama/llama-3.2-11b-vision-instruct | Meta Llama | 131072 | -| qwen/qwen-2.5-72b-instruct | Qwen | 32768 | -| cohere/command-r-plus-08-2024 | Cohere | 128000 | -| cohere/command-r-08-2024 | Cohere | 128000 | -| sao10k/l3.1-euryale-70b | Sao10k | 131072 | -| nousresearch/hermes-3-llama-3.1-70b | Nousresearch | 131072 | -| nousresearch/hermes-3-llama-3.1-405b:free | Nousresearch | 131072 | -| nousresearch/hermes-3-llama-3.1-405b | Nousresearch | 131072 | -| sao10k/l3-lunaris-8b | Sao10k | 8192 | -| openai/gpt-4o-2024-08-06 | Openai | 128000 | -| meta-llama/llama-3.1-8b-instruct | Meta Llama | 16384 | -| meta-llama/llama-3.1-70b-instruct | Meta Llama | 131072 | -| mistralai/mistral-nemo | Mistralai | 131072 | -| openai/gpt-4o-mini-2024-07-18 | Openai | 128000 | -| openai/gpt-4o-mini | Openai | 128000 | -| google/gemma-2-27b-it | Google | 8192 | -| sao10k/l3-euryale-70b | Sao10k | 8192 | -| nousresearch/hermes-2-pro-llama-3-8b | Nousresearch | 8192 | -| openai/gpt-4o-2024-05-13 | Openai | 128000 | -| meta-llama/llama-3-8b-instruct | Meta Llama | 8192 | -| meta-llama/llama-3-70b-instruct | Meta Llama | 8192 | -| mistralai/mixtral-8x22b-instruct | Mistralai | 65536 | -| microsoft/wizardlm-2-8x22b | Microsoft | 65535 | -| openai/gpt-4-turbo | Openai | 128000 | -| anthropic/claude-3-haiku | Anthropic | 200000 | -| mistralai/mistral-large | Mistralai | 128000 | -| openai/gpt-4-turbo-preview | Openai | 128000 | -| openai/gpt-3.5-turbo-0613 | Openai | 4095 | -| alpindale/goliath-120b | Alpindale | 6144 | -| openrouter/auto | Openrouter | 2000000 | -| openai/gpt-4-1106-preview | Openai | 128000 | -| openai/gpt-3.5-turbo-instruct | Openai | 4095 | -| mistralai/mistral-7b-instruct-v0.1 | Mistralai | 2824 | -| openai/gpt-3.5-turbo-16k | Openai | 16385 | -| mancer/weaver | Mancer | 8000 | -| undi95/remm-slerp-l2-13b | Undi95 | 6144 | -| gryphe/mythomax-l2-13b | Gryphe | 4096 | -| openai/gpt-4-0314 | Openai | 8191 | -| openai/gpt-4 | Openai | 8191 | -| openai/gpt-3.5-turbo | Openai | 16385 | - -## 💸 低价模型 TOP 10 - -| 排名 | 模型 | 厂商 | 输入价格 | -|------|------|------|----------| -| 1 | openai/gpt-4o | Openai | $2.5000 | - -## 📏 大上下文模型 TOP 10 - -| 排名 | 模型 | 厂商 | 上下文长度 | -|------|------|------|------------| -| 1 | openrouter/auto | Openrouter | 2000000 | -| 2 | x-ai/grok-4.1-fast | X Ai | 2000000 | -| 3 | x-ai/grok-4.20 | X Ai | 2000000 | -| 4 | x-ai/grok-4.20-multi-agent | X Ai | 2000000 | -| 5 | openrouter/pareto-code | Openrouter | 2000000 | -| 6 | x-ai/grok-4-fast | X Ai | 2000000 | -| 7 | openai/gpt-5.4 | Openai | 1050000 | -| 8 | openai/gpt-5.4-pro | Openai | 1050000 | -| 9 | openai/gpt-5.5 | Openai | 1050000 | -| 10 | openai/gpt-5.5-pro | Openai | 1050000 | - ---- - -📌 **说明**: 本报告由 LLM Intelligence Hub 自动生成。价格单位：USD/1M tokens。 - -_生成时间: 2026-05-11T08:00:02+08:00_ diff --git a/reports/daily/2026/05/daily_report_2026-05-12.html b/reports/daily/2026/05/daily_report_2026-05-12.html deleted file mode 100644 index 70945ea..0000000 --- a/reports/daily/2026/05/daily_report_2026-05-12.html +++ /dev/null @@ -1,1241 +0,0 @@ - - - - - -LLM Intelligence Hub - 2026-05-12 - - - -
- -
-

🤖 LLM Intelligence Hub

-

每日情报报告 · 2026-05-12 · 501 模型覆盖

-
- - -
-
-
模型总数
-
501
-
-
-
免费模型
-
371
-
-
-
国际模型
-
5
-
-
-
国内模型
-
76
-
-
- - - - - -
-

🆓 免费模型(371 个)

-

代表性模型(前20个):

-
- -
-
xAI: Grok 4 Fast
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
Pareto Code Router
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.20 Multi-Agent
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.20
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
Auto Router
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.1 Fast
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
OpenAI: GPT-5.5
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.5 Pro
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI GPT Latest
-
~openai 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.4
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.4 Pro
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
Owl Alpha
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048756 tokens -
-
- -
-
Google: Lyria 3 Clip Preview
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 3 Flash Preview
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.5 Pro Preview 05-06
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Meta: Llama 4 Maverick
-
meta-llama 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Xiaomi: MiMo-V2.5
-
xiaomi 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google Gemini Pro Latest
-
~google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.5 Flash Lite Preview 09-2025
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google Gemini Flash Latest
-
~google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
- -

... 共 371 个免费模型,以上为前20个

- -
- - - - -
-

🌍 国际低价模型 TOP 5

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
排名模型厂商输入价格输出价格上下文
1Qwen3-VL-8BAlibaba$0.20$0.5032000
2Qwen3-VL-32BAlibaba$0.50$1.0032000
3GPT-5.4 MiniOpenAI$0.75$4.50200000
4Doubao-ProByteDance$0.80$2.0032000
5DeepSeek-V3DeepSeek$1.00$2.0064000
-
- - - - -
-

🇨🇳 国内模型 TOP 10

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
排名模型厂商输入价格输出价格上下文
1DeepSeek V4 FlashDeepSeek$0.14$0.281000000
2doubao-seed-1.6-flashByteDance$0.15$0.3032000
3GLM-4.6V-FlashXZhipu AI$0.15$1.508000
4GLM-Realtime-FlashZhipu AI$0.18$0.188000
5doubao-seed-2.0-miniByteDance$0.20$0.4032000
6doubao-seed-1.6-liteByteDance$0.30$0.6032000
7doubao-seed-1.6-flash-128kByteDance$0.30$0.60128000
8GLM-Realtime-AirZhipu AI$0.30$0.308000
9doubao-1.5-lite-32kByteDance$0.30$0.6032000
10doubao-seed-2.0-mini-128kByteDance$0.40$0.80128000
11DeepSeek V4 ProDeepSeek$0.43$0.871000000
12GLM-4.7-FlashXZhipu AI$0.50$3.00200000
13GLM-4-AirZhipu AI$0.50$0.25128000
14doubao-seed-1.6-lite-128kByteDance$0.60$1.20128000
15doubao-seed-1.6-flash-256kByteDance$0.60$1.20256000
16doubao-seed-2.0-liteByteDance$0.60$1.2032000
17doubao-seed-characterByteDance$0.80$1.6032000
18doubao-seed-1.8ByteDance$0.80$1.6032000
19doubao-seed-1.6ByteDance$0.80$1.6032000
20GLM-4.5-AirZhipu AI$0.80$2.0032000
21doubao-pro-32kByteDance$0.80$1.6032000
22doubao-seed-1.6-visionByteDance$0.80$1.6032000
23doubao-1.5-pro-32kByteDance$0.80$1.6032000
24doubao-seed-2.0-mini-256kByteDance$0.80$1.60256000
25doubao-seed-2.0-lite-128kByteDance$0.90$1.80128000
26GLM-4-LongZhipu AI$1.00$0.501000000
27doubao-seed-1.8-128kByteDance$1.20$2.40128000
28GLM-4.5-Air (32K+)Zhipu AI$1.20$8.00128000
29doubao-seed-codeByteDance$1.20$2.4032000
30doubao-seed-1.6-vision-128kByteDance$1.20$2.40128000
31doubao-seed-1.6-lite-256kByteDance$1.20$2.40256000
32doubao-seed-1.6-128kByteDance$1.20$2.40128000
33doubao-seed-character-128kByteDance$1.20$2.40128000
34doubao-seed-code-128kByteDance$1.40$2.80128000
35doubao-seed-2.0-lite-256kByteDance$1.80$3.60256000
36deepseek-v3ByteDance$2.00$4.0032000
37GLM-4.7Zhipu AI$2.00$8.0032000
38GLM-4.5VZhipu AI$2.00$6.0032000
39GLM-4.6VZhipu AI$2.00$6.008000
40Moonshot V1 8KMoonshot AI$2.00$10.008192
41deepseek-v3.2ByteDance$2.00$4.0032000
42GLM-TTSZhipu AI$2.00$0.008000
43glm-4.7ByteDance$2.00$4.0032000
44doubao-seed-1.6-vision-256kByteDance$2.40$4.80256000
45doubao-seed-1.8-256kByteDance$2.40$4.80256000
46doubao-seed-1.6-256kByteDance$2.40$4.80256000
47doubao-seed-code-256kByteDance$2.80$5.60256000
48doubao-1.5-vision-proByteDance$3.00$6.0032000
49doubao-seed-2.0-codeByteDance$3.20$6.4032000
50doubao-seed-2.0-proByteDance$3.20$6.4032000
51deepseek-v3.1ByteDance$4.00$8.0032000
52Kimi K2 0905 PreviewMoonshot AI$4.00$16.00262144
53glm-4.7-128kByteDance$4.00$8.00128000
54GLM-5Zhipu AI$4.00$18.0032000
55deepseek-v3.2-128kByteDance$4.00$8.00128000
56GLM-4.7 (32K+)Zhipu AI$4.00$16.00200000
57deepseek-r1ByteDance$4.00$8.0032000
58GLM-4V-PlusZhipu AI$4.00$4.008000
59doubao-seed-2.0-code-128kByteDance$4.80$9.60128000
60doubao-seed-2.0-pro-128kByteDance$4.80$9.60128000
61GLM-5-TurboZhipu AI$5.00$22.0032000
62GLM-TTS-CloneZhipu AI$6.00$0.008000
63GLM-5 (32K+)Zhipu AI$6.00$22.00200000
64GLM-5.1Zhipu AI$6.00$24.0032000
65Kimi K2.6Moonshot AI$6.50$27.00262144
66GLM-5-Turbo (32K+)Zhipu AI$7.00$26.00200000
67GLM-5.1 (32K+)Zhipu AI$8.00$28.00200000
68doubao-seed-2.0-code-256kByteDance$9.60$19.20256000
69doubao-seed-2.0-pro-256kByteDance$9.60$19.20256000
70GLM-4-AirXZhipu AI$10.00$10.008000
71GLM-ASR-2512Zhipu AI$16.00$0.008000
72ERNIE 5.1Baidu$22.00$22.000
73ERNIE 5.0Baidu$40.00$40.000
74GLM-4VZhipu AI$50.00$50.002000
75GLM-4-VoiceZhipu AI$80.00$80.008000
76GLM-4-0520Zhipu AI$100.00$50.00128000
-
- - - - -
-

☁️ 云厂商/官方平台(6 家)

- - - - - - - - - - - - - - - -
平台模型数最低价格平均价格
Zhipu29$0.18$10.99
ByteDance Volcano43$0.15$2.11
Moonshot3$2.00$4.17
DeepSeek2$0.14$0.29
OpenAI3$0.75$2.75
Baidu Qianfan44$0.00$1.41
-
- - - - -
-

🔀 中转/聚合平台(1 家)

- - - - - -
平台模型数最低价格平均价格
OpenRouter377$0.00$0.03
-
- - -
-

📌 本报告由 LLM Intelligence Hub 自动生成 · 2026-05-12

-

价格单位:USD/1M tokens

-
- -
- - \ No newline at end of file diff --git a/reports/daily/2026/05/daily_report_2026-05-12.md b/reports/daily/2026/05/daily_report_2026-05-12.md deleted file mode 100644 index f30544f..0000000 --- a/reports/daily/2026/05/daily_report_2026-05-12.md +++ /dev/null @@ -1,350 +0,0 @@ -# 🤖 LLM Intelligence Hub - 每日情报报告 - -**报告日期**: 2026-05-12 -**生成时间**: 2026-05-12T08:00:01+08:00 - -## 📊 数据质量摘要 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 501 | -| 数据新鲜 | 458 | -| CNY定价 | 126 | -| USD定价 | 375 | -| 厂商总数 | 81 | - -## 🆓 免费模型(共 371 个) - -**按国家分布**: US 144个, 国际 143个, CN 84个 - -**代表性模型(前20个)**: - -| 模型 | 厂商 | 国家 | 上下文 | -|------|------|------|--------| -| xAI: Grok 4 Fast | xAI | US | 2000000 | -| Pareto Code Router | OpenRouter | US | 2000000 | -| xAI: Grok 4.20 Multi-Agent | xAI | US | 2000000 | -| xAI: Grok 4.20 | xAI | US | 2000000 | -| Auto Router | OpenRouter | US | 2000000 | -| xAI: Grok 4.1 Fast | xAI | US | 2000000 | -| OpenAI: GPT-5.5 | OpenAI | US | 1050000 | -| OpenAI: GPT-5.5 Pro | OpenAI | US | 1050000 | -| OpenAI GPT Latest | ~openai | 国际 | 1050000 | -| OpenAI: GPT-5.4 | OpenAI | US | 1050000 | -| OpenAI: GPT-5.4 Pro | OpenAI | US | 1050000 | -| Owl Alpha | OpenRouter | US | 1048756 | -| Google: Lyria 3 Clip Preview | Google | US | 1048576 | -| Google: Gemini 3 Flash Preview | Google | US | 1048576 | -| Google: Gemini 2.5 Pro Preview 05-06 | Google | US | 1048576 | -| Meta: Llama 4 Maverick | meta-llama | 国际 | 1048576 | -| Xiaomi: MiMo-V2.5 | xiaomi | 国际 | 1048576 | -| Google Gemini Pro Latest | ~google | 国际 | 1048576 | -| Google: Gemini 2.5 Flash Lite Preview 09-2025 | Google | US | 1048576 | -| Google Gemini Flash Latest | ~google | 国际 | 1048576 | -| ... | ... | ... | ... | - -> 共 371 个免费模型,以上为前20个代表性模型 - -## 🌍 国际推荐模型 TOP 5 - -| 排名 | 模型 | 厂商 | 场景 | 输入(原价) | 输出(原价) | 上下文 | -|------|------|------|------|-----------|-----------|--------| -| 1 | Qwen3-VL-8B | Alibaba | 视觉 | ¥0.20 | ¥0.50 | 32000 | -| 2 | Qwen3-VL-32B | Alibaba | 视觉 | ¥0.50 | ¥1.00 | 32000 | -| 3 | GPT-5.4 Mini | OpenAI | 对话 | $0.75 | $4.50 | 200000 | -| 4 | Doubao-Pro | ByteDance | 视觉 | ¥0.80 | ¥2.00 | 32000 | -| 5 | DeepSeek-V3 | DeepSeek | 对话 | ¥1.00 | ¥2.00 | 64000 | - -## 🇨🇳 国内模型 TOP 10 - -| 排名 | 模型 | 厂商 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|------|------|-----------|-----------|--------| -| 1 | DeepSeek V4 Flash | DeepSeek | 对话 | ¥1.02 | ¥2.03 | 1000000 | -| 2 | doubao-seed-1.6-flash | ByteDance | 对话 | ¥0.15 | ¥0.30 | 32000 | -| 3 | GLM-4.6V-FlashX | Zhipu AI | 视觉 | ¥0.15 | ¥1.50 | 8000 | -| 4 | GLM-Realtime-Flash | Zhipu AI | 对话 | ¥0.18 | ¥0.18 | 8000 | -| 5 | doubao-seed-2.0-mini | ByteDance | 对话 | ¥0.20 | ¥0.40 | 32000 | -| 6 | doubao-seed-1.6-lite | ByteDance | 对话 | ¥0.30 | ¥0.60 | 32000 | -| 7 | doubao-seed-1.6-flash-128k | ByteDance | 对话 | ¥0.30 | ¥0.60 | 128000 | -| 8 | GLM-Realtime-Air | Zhipu AI | 对话 | ¥0.30 | ¥0.30 | 8000 | -| 9 | doubao-1.5-lite-32k | ByteDance | 对话 | ¥0.30 | ¥0.60 | 32000 | -| 10 | doubao-seed-2.0-mini-128k | ByteDance | 对话 | ¥0.40 | ¥0.80 | 128000 | -| 11 | DeepSeek V4 Pro | DeepSeek | 对话 | ¥3.15 | ¥6.31 | 1000000 | -| 12 | GLM-4.7-FlashX | Zhipu AI | 对话 | ¥0.50 | ¥3.00 | 200000 | -| 13 | GLM-4-Air | Zhipu AI | 对话 | ¥0.50 | ¥0.25 | 128000 | -| 14 | doubao-seed-1.6-lite-128k | ByteDance | 对话 | ¥0.60 | ¥1.20 | 128000 | -| 15 | doubao-seed-1.6-flash-256k | ByteDance | 对话 | ¥0.60 | ¥1.20 | 256000 | -| 16 | doubao-seed-2.0-lite | ByteDance | 对话 | ¥0.60 | ¥1.20 | 32000 | -| 17 | doubao-seed-character | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 18 | doubao-seed-1.8 | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 19 | doubao-seed-1.6 | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 20 | GLM-4.5-Air | Zhipu AI | 对话 | ¥0.80 | ¥2.00 | 32000 | -| 21 | doubao-pro-32k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 22 | doubao-seed-1.6-vision | ByteDance | 视觉 | ¥0.80 | ¥1.60 | 32000 | -| 23 | doubao-1.5-pro-32k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 24 | doubao-seed-2.0-mini-256k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 256000 | -| 25 | doubao-seed-2.0-lite-128k | ByteDance | 对话 | ¥0.90 | ¥1.80 | 128000 | -| 26 | GLM-4-Long | Zhipu AI | 对话 | ¥1.00 | ¥0.50 | 1000000 | -| 27 | doubao-seed-1.8-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 28 | GLM-4.5-Air (32K+) | Zhipu AI | 对话 | ¥1.20 | ¥8.00 | 128000 | -| 29 | doubao-seed-code | ByteDance | 代码 | ¥1.20 | ¥2.40 | 32000 | -| 30 | doubao-seed-1.6-vision-128k | ByteDance | 视觉 | ¥1.20 | ¥2.40 | 128000 | -| 31 | doubao-seed-1.6-lite-256k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 256000 | -| 32 | doubao-seed-1.6-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 33 | doubao-seed-character-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 34 | doubao-seed-code-128k | ByteDance | 代码 | ¥1.40 | ¥2.80 | 128000 | -| 35 | doubao-seed-2.0-lite-256k | ByteDance | 对话 | ¥1.80 | ¥3.60 | 256000 | -| 36 | deepseek-v3 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 37 | GLM-4.7 | Zhipu AI | 对话 | ¥2.00 | ¥8.00 | 32000 | -| 38 | GLM-4.5V | Zhipu AI | 视觉 | ¥2.00 | ¥6.00 | 32000 | -| 39 | GLM-4.6V | Zhipu AI | 视觉 | ¥2.00 | ¥6.00 | 8000 | -| 40 | Moonshot V1 8K | Moonshot AI | 对话 | ¥2.00 | ¥10.00 | 8192 | -| 41 | deepseek-v3.2 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 42 | GLM-TTS | Zhipu AI | 对话 | ¥2.00 | 免费 | 8000 | -| 43 | glm-4.7 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 44 | doubao-seed-1.6-vision-256k | ByteDance | 视觉 | ¥2.40 | ¥4.80 | 256000 | -| 45 | doubao-seed-1.8-256k | ByteDance | 对话 | ¥2.40 | ¥4.80 | 256000 | -| 46 | doubao-seed-1.6-256k | ByteDance | 对话 | ¥2.40 | ¥4.80 | 256000 | -| 47 | doubao-seed-code-256k | ByteDance | 代码 | ¥2.80 | ¥5.60 | 256000 | -| 48 | doubao-1.5-vision-pro | ByteDance | 视觉 | ¥3.00 | ¥6.00 | 32000 | -| 49 | doubao-seed-2.0-code | ByteDance | 代码 | ¥3.20 | ¥6.40 | 32000 | -| 50 | doubao-seed-2.0-pro | ByteDance | 对话 | ¥3.20 | ¥6.40 | 32000 | -| 51 | deepseek-v3.1 | ByteDance | 对话 | ¥4.00 | ¥8.00 | 32000 | -| 52 | Kimi K2 0905 Preview | Moonshot AI | 对话 | ¥4.00 | ¥16.00 | 262144 | -| 53 | glm-4.7-128k | ByteDance | 对话 | ¥4.00 | ¥8.00 | 128000 | -| 54 | GLM-5 | Zhipu AI | 对话 | ¥4.00 | ¥18.00 | 32000 | -| 55 | deepseek-v3.2-128k | ByteDance | 对话 | ¥4.00 | ¥8.00 | 128000 | -| 56 | GLM-4.7 (32K+) | Zhipu AI | 对话 | ¥4.00 | ¥16.00 | 200000 | -| 57 | deepseek-r1 | ByteDance | 推理 | ¥4.00 | ¥8.00 | 32000 | -| 58 | GLM-4V-Plus | Zhipu AI | 视觉 | ¥4.00 | ¥4.00 | 8000 | -| 59 | doubao-seed-2.0-code-128k | ByteDance | 代码 | ¥4.80 | ¥9.60 | 128000 | -| 60 | doubao-seed-2.0-pro-128k | ByteDance | 对话 | ¥4.80 | ¥9.60 | 128000 | -| 61 | GLM-5-Turbo | Zhipu AI | 对话 | ¥5.00 | ¥22.00 | 32000 | -| 62 | GLM-TTS-Clone | Zhipu AI | 对话 | ¥6.00 | 免费 | 8000 | -| 63 | GLM-5 (32K+) | Zhipu AI | 对话 | ¥6.00 | ¥22.00 | 200000 | -| 64 | GLM-5.1 | Zhipu AI | 对话 | ¥6.00 | ¥24.00 | 32000 | -| 65 | Kimi K2.6 | Moonshot AI | 视觉 | ¥6.50 | ¥27.00 | 262144 | -| 66 | GLM-5-Turbo (32K+) | Zhipu AI | 对话 | ¥7.00 | ¥26.00 | 200000 | -| 67 | GLM-5.1 (32K+) | Zhipu AI | 对话 | ¥8.00 | ¥28.00 | 200000 | -| 68 | doubao-seed-2.0-code-256k | ByteDance | 代码 | ¥9.60 | ¥19.20 | 256000 | -| 69 | doubao-seed-2.0-pro-256k | ByteDance | 对话 | ¥9.60 | ¥19.20 | 256000 | -| 70 | GLM-4-AirX | Zhipu AI | 对话 | ¥10.00 | ¥10.00 | 8000 | -| 71 | GLM-ASR-2512 | Zhipu AI | 对话 | ¥16.00 | 免费 | 8000 | -| 72 | ERNIE 5.1 | Baidu | 对话 | ¥22.00 | ¥22.00 | 0 | -| 73 | ERNIE 5.0 | Baidu | 对话 | ¥40.00 | ¥40.00 | 0 | -| 74 | GLM-4V | Zhipu AI | 视觉 | ¥50.00 | ¥50.00 | 2000 | -| 75 | GLM-4-Voice | Zhipu AI | 对话 | ¥80.00 | ¥80.00 | 8000 | -| 76 | GLM-4-0520 | Zhipu AI | 对话 | ¥100.00 | ¥50.00 | 128000 | - -## 📊 模型分类概览 - -### 🇨🇳 国内官方平台模型 - -**Baidu Qianfan** (2个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| ERNIE 5.1 | 对话 | ¥22.00 | ¥22.00 | 0 | -| ERNIE 5.0 | 对话 | ¥40.00 | ¥40.00 | 0 | - -**DeepSeek** (2个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| DeepSeek V4 Flash | 对话 | ¥1.02 | ¥2.03 | 1000000 | -| DeepSeek V4 Pro | 对话 | ¥3.15 | ¥6.31 | 1000000 | - -**ByteDance Volcano** (43个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| doubao-seed-1.6-flash | 对话 | ¥0.15 | ¥0.30 | 32000 | -| doubao-seed-2.0-mini | 对话 | ¥0.20 | ¥0.40 | 32000 | -| doubao-seed-1.6-lite | 对话 | ¥0.30 | ¥0.60 | 32000 | -| doubao-seed-1.6-flash-128k | 对话 | ¥0.30 | ¥0.60 | 128000 | -| doubao-1.5-lite-32k | 对话 | ¥0.30 | ¥0.60 | 32000 | -| doubao-seed-2.0-mini-128k | 对话 | ¥0.40 | ¥0.80 | 128000 | -| doubao-seed-1.6-lite-128k | 对话 | ¥0.60 | ¥1.20 | 128000 | -| doubao-seed-1.6-flash-256k | 对话 | ¥0.60 | ¥1.20 | 256000 | -| doubao-seed-2.0-lite | 对话 | ¥0.60 | ¥1.20 | 32000 | -| doubao-seed-character | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.8 | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.6 | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-pro-32k | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.6-vision | 视觉 | ¥0.80 | ¥1.60 | 32000 | -| doubao-1.5-pro-32k | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-2.0-mini-256k | 对话 | ¥0.80 | ¥1.60 | 256000 | -| doubao-seed-2.0-lite-128k | 对话 | ¥0.90 | ¥1.80 | 128000 | -| doubao-seed-1.8-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-code | 代码 | ¥1.20 | ¥2.40 | 32000 | -| doubao-seed-1.6-vision-128k | 视觉 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-1.6-lite-256k | 对话 | ¥1.20 | ¥2.40 | 256000 | -| doubao-seed-1.6-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-character-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-code-128k | 代码 | ¥1.40 | ¥2.80 | 128000 | -| doubao-seed-2.0-lite-256k | 对话 | ¥1.80 | ¥3.60 | 256000 | -| deepseek-v3 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| deepseek-v3.2 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| glm-4.7 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| doubao-seed-1.6-vision-256k | 视觉 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-1.8-256k | 对话 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-1.6-256k | 对话 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-code-256k | 代码 | ¥2.80 | ¥5.60 | 256000 | -| doubao-1.5-vision-pro | 视觉 | ¥3.00 | ¥6.00 | 32000 | -| doubao-seed-2.0-code | 代码 | ¥3.20 | ¥6.40 | 32000 | -| doubao-seed-2.0-pro | 对话 | ¥3.20 | ¥6.40 | 32000 | -| deepseek-v3.1 | 对话 | ¥4.00 | ¥8.00 | 32000 | -| glm-4.7-128k | 对话 | ¥4.00 | ¥8.00 | 128000 | -| deepseek-v3.2-128k | 对话 | ¥4.00 | ¥8.00 | 128000 | -| deepseek-r1 | 推理 | ¥4.00 | ¥8.00 | 32000 | -| doubao-seed-2.0-code-128k | 代码 | ¥4.80 | ¥9.60 | 128000 | -| doubao-seed-2.0-pro-128k | 对话 | ¥4.80 | ¥9.60 | 128000 | -| doubao-seed-2.0-code-256k | 代码 | ¥9.60 | ¥19.20 | 256000 | -| doubao-seed-2.0-pro-256k | 对话 | ¥9.60 | ¥19.20 | 256000 | - -**Zhipu** (26个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| GLM-4.6V-FlashX | 视觉 | ¥0.15 | ¥1.50 | 8000 | -| GLM-Realtime-Flash | 对话 | ¥0.18 | ¥0.18 | 8000 | -| GLM-Realtime-Air | 对话 | ¥0.30 | ¥0.30 | 8000 | -| GLM-4.7-FlashX | 对话 | ¥0.50 | ¥3.00 | 200000 | -| GLM-4-Air | 对话 | ¥0.50 | ¥0.25 | 128000 | -| GLM-4.5-Air | 对话 | ¥0.80 | ¥2.00 | 32000 | -| GLM-4-Long | 对话 | ¥1.00 | ¥0.50 | 1000000 | -| GLM-4.5-Air (32K+) | 对话 | ¥1.20 | ¥8.00 | 128000 | -| GLM-4.7 | 对话 | ¥2.00 | ¥8.00 | 32000 | -| GLM-4.5V | 视觉 | ¥2.00 | ¥6.00 | 32000 | -| GLM-4.6V | 视觉 | ¥2.00 | ¥6.00 | 8000 | -| GLM-TTS | 对话 | ¥2.00 | 免费 | 8000 | -| GLM-5 | 对话 | ¥4.00 | ¥18.00 | 32000 | -| GLM-4.7 (32K+) | 对话 | ¥4.00 | ¥16.00 | 200000 | -| GLM-4V-Plus | 视觉 | ¥4.00 | ¥4.00 | 8000 | -| GLM-5-Turbo | 对话 | ¥5.00 | ¥22.00 | 32000 | -| GLM-TTS-Clone | 对话 | ¥6.00 | 免费 | 8000 | -| GLM-5 (32K+) | 对话 | ¥6.00 | ¥22.00 | 200000 | -| GLM-5.1 | 对话 | ¥6.00 | ¥24.00 | 32000 | -| GLM-5-Turbo (32K+) | 对话 | ¥7.00 | ¥26.00 | 200000 | -| GLM-5.1 (32K+) | 对话 | ¥8.00 | ¥28.00 | 200000 | -| GLM-4-AirX | 对话 | ¥10.00 | ¥10.00 | 8000 | -| GLM-ASR-2512 | 对话 | ¥16.00 | 免费 | 8000 | -| GLM-4V | 视觉 | ¥50.00 | ¥50.00 | 2000 | -| GLM-4-Voice | 对话 | ¥80.00 | ¥80.00 | 8000 | -| GLM-4-0520 | 对话 | ¥100.00 | ¥50.00 | 128000 | - -**Moonshot** (3个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| Moonshot V1 8K | 对话 | ¥2.00 | ¥10.00 | 8192 | -| Kimi K2 0905 Preview | 对话 | ¥4.00 | ¥16.00 | 262144 | -| Kimi K2.6 | 视觉 | ¥6.50 | ¥27.00 | 262144 | - -### 💻 代码模型(19个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Pareto Code Router | OpenRouter | 免费 | 免费 | -| Qwen: Qwen3 Coder Plus | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder Flash | Qwen | 免费 | 免费 | -| OpenAI: GPT-5 Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex-Max | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.2-Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex-Mini | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.3-Codex | OpenAI | 免费 | 免费 | -| Qwen: Qwen3 Coder Next | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder 480B A35B | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder 480B A35B... | Qwen | 免费 | 免费 | -| Kwaipilot: KAT-Coder-Pro V2 | kwaipilot | 免费 | 免费 | -| xAI: Grok Code Fast 1 | xAI | 免费 | 免费 | -| Mistral: Codestral 2508 | mistralai | 免费 | 免费 | -| Qwen: Qwen3 Coder 30B A3B I... | Qwen | 免费 | 免费 | -| Qwen2.5 Coder 32B Instruct | Qwen | 免费 | 免费 | -| Arcee AI: Coder Large | arcee-ai | 免费 | 免费 | -| AlfredPros: CodeLLaMa 7B In... | alfredpros | 免费 | 免费 | - -### 🧠 推理模型(34个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Qwen: Qwen Plus 0728 (think... | Qwen | 免费 | 免费 | -| MoonshotAI: Kimi K2 Thinking | Moonshot AI | 免费 | 免费 | -| Qwen: Qwen3 Max Thinking | Qwen | 免费 | 免费 | -| Arcee AI: Trinity Large Thi... | arcee-ai | 免费 | 免费 | -| OpenAI: o3 Mini | OpenAI | 免费 | 免费 | -| OpenAI: o1-pro | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini | OpenAI | 免费 | 免费 | -| OpenAI: o3 Deep Research | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini Deep Research | OpenAI | 免费 | 免费 | -| OpenAI: o1 | OpenAI | 免费 | 免费 | -| OpenAI: o3 | OpenAI | 免费 | 免费 | -| OpenAI: o3 Pro | OpenAI | 免费 | 免费 | -| OpenAI: o3 Mini High | OpenAI | 免费 | 免费 | -| Anthropic: Claude 3.7 Sonne... | Anthropic | 免费 | 免费 | -| OpenAI: o4 Mini High | OpenAI | 免费 | 免费 | -| DeepSeek: R1 0528 | DeepSeek | 免费 | 免费 | -| Arcee AI: Maestro Reasoning | arcee-ai | 免费 | 免费 | -| Sao10K: Llama 3.3 Euryale 70B | sao10k | 免费 | 免费 | -| DeepSeek: R1 Distill Llama 70B | DeepSeek | 免费 | 免费 | -| Qwen: Qwen3 30B A3B Thinkin... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Next 80B A3B Th... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 235B A22B Th... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 235B A22B Think... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Thin... | Qwen | 免费 | 免费 | -| Baidu: ERNIE 4.5 21B A3B Th... | Baidu | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Thinking | Qwen | 免费 | 免费 | -| Sao10K: Llama 3.1 Euryale 7... | sao10k | 免费 | 免费 | -| Perplexity: Sonar Reasoning... | Perplexity | 免费 | 免费 | -| DeepSeek: R1 | DeepSeek | 免费 | 免费 | -| DeepSeek: R1 Distill Qwen 32B | DeepSeek | 免费 | 免费 | -| LiquidAI: LFM2.5-1.2B-Think... | liquid | 免费 | 免费 | -| Sao10K: Llama 3.1 70B Hanam... | sao10k | 免费 | 免费 | -| Sao10k: Llama 3 Euryale 70B... | sao10k | 免费 | 免费 | -| Sao10K: Llama 3 8B Lunaris | sao10k | 免费 | 免费 | - -### 👁️ 视觉/多模态模型(15个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| MoonshotAI: Kimi K2.6 | Moonshot AI | 免费 | 免费 | -| Qwen: Qwen3 VL 235B A22B In... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 235B A22B Th... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Inst... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Thin... | Qwen | 免费 | 免费 | -| Qwen: Qwen VL Max | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Instruct | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Thinking | Qwen | 免费 | 免费 | -| Qwen: Qwen VL Plus | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 32B Instruct | Qwen | 免费 | 免费 | -| Meta: Llama 3.2 11B Vision ... | meta-llama | 免费 | 免费 | -| NVIDIA: Nemotron Nano 12B 2... | NVIDIA | 免费 | 免费 | -| Baidu: ERNIE 4.5 VL 424B A47B | Baidu | 免费 | 免费 | -| Qwen: Qwen2.5 VL 72B Instruct | Qwen | 免费 | 免费 | -| Baidu: ERNIE 4.5 VL 28B A3B | Baidu | 免费 | 免费 | - -## 🇨🇳 国内官方平台(5 家) - -- **Zhipu**: 29 个模型,最低 ¥0.18/MTok -- **ByteDance Volcano**: 43 个模型,最低 ¥0.15/MTok -- **Moonshot**: 3 个模型,最低 ¥2.00/MTok -- **DeepSeek**: 2 个模型,最低 ¥0.14/MTok -- **Baidu Qianfan**: 44 个模型,最低 ¥0.00/MTok - -## ☁️ 国际官方平台(1 家) - -- **OpenAI**: 3 个模型,最低 $0.75/MTok - -## 🔀 中转/聚合平台(1 家) - -- **OpenRouter**: 377 个模型,最低 $0.00/MTok - ---- - -📌 **说明**: 本报告由 LLM Intelligence Hub 自动生成。 -- 国际模型价格按 1 USD = 7.25 CNY 换算显示，括号内为原生货币价格 -- 国内模型价格为厂商原生 CNY 定价 -- 数据来源: OpenRouter API + 智谱AI + 百度千帆 + Moonshot + DeepSeek + OpenAI - -_生成时间: 2026-05-12T08:00:01+08:00_ diff --git a/reports/daily/2026/05/daily_report_2026-05-13.html b/reports/daily/2026/05/daily_report_2026-05-13.html deleted file mode 100644 index 17a36d5..0000000 --- a/reports/daily/2026/05/daily_report_2026-05-13.html +++ /dev/null @@ -1,1241 +0,0 @@ - - - - - -LLM Intelligence Hub - 2026-05-13 - - - -
- -
-

🤖 LLM Intelligence Hub

-

每日情报报告 · 2026-05-13 · 503 模型覆盖

-
- - -
-
-
模型总数
-
503
-
-
-
免费模型
-
373
-
-
-
国际模型
-
5
-
-
-
国内模型
-
76
-
-
- - - - - -
-

🆓 免费模型(373 个)

-

代表性模型(前20个):

-
- -
-
xAI: Grok 4 Fast
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
Auto Router
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
Pareto Code Router
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.20
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.1 Fast
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.20 Multi-Agent
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
OpenAI: GPT-5.4
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.5
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.5 Pro
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.4 Pro
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI GPT Latest
-
~openai 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
Owl Alpha
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048756 tokens -
-
- -
-
Google: Gemini 2.5 Pro Preview 06-05
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 3 Flash Preview
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 3.1 Pro Preview
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.0 Flash
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 3.1 Pro Preview Custom Tools
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google Gemini Pro Latest
-
~google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.0 Flash Lite
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google Gemini Flash Latest
-
~google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
- -

... 共 373 个免费模型,以上为前20个

- -
- - - - -
-

🌍 国际低价模型 TOP 5

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
排名模型厂商输入价格输出价格上下文
1Qwen3-VL-8BAlibaba$0.20$0.5032000
2Qwen3-VL-32BAlibaba$0.50$1.0032000
3GPT-5.4 MiniOpenAI$0.75$4.50200000
4Doubao-ProByteDance$0.80$2.0032000
5DeepSeek-V3DeepSeek$1.00$2.0064000
-
- - - - -
-

🇨🇳 国内模型 TOP 10

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
排名模型厂商输入价格输出价格上下文
1DeepSeek V4 FlashDeepSeek$0.14$0.281000000
2doubao-seed-1.6-flashByteDance$0.15$0.3032000
3GLM-4.6V-FlashXZhipu AI$0.15$1.508000
4GLM-Realtime-FlashZhipu AI$0.18$0.188000
5doubao-seed-2.0-miniByteDance$0.20$0.4032000
6doubao-seed-1.6-liteByteDance$0.30$0.6032000
7doubao-seed-1.6-flash-128kByteDance$0.30$0.60128000
8GLM-Realtime-AirZhipu AI$0.30$0.308000
9doubao-1.5-lite-32kByteDance$0.30$0.6032000
10doubao-seed-2.0-mini-128kByteDance$0.40$0.80128000
11DeepSeek V4 ProDeepSeek$0.43$0.871000000
12GLM-4.7-FlashXZhipu AI$0.50$3.00200000
13GLM-4-AirZhipu AI$0.50$0.25128000
14doubao-seed-1.6-lite-128kByteDance$0.60$1.20128000
15doubao-seed-1.6-flash-256kByteDance$0.60$1.20256000
16doubao-seed-2.0-liteByteDance$0.60$1.2032000
17doubao-seed-characterByteDance$0.80$1.6032000
18doubao-seed-1.8ByteDance$0.80$1.6032000
19doubao-seed-1.6ByteDance$0.80$1.6032000
20GLM-4.5-AirZhipu AI$0.80$2.0032000
21doubao-pro-32kByteDance$0.80$1.6032000
22doubao-seed-1.6-visionByteDance$0.80$1.6032000
23doubao-1.5-pro-32kByteDance$0.80$1.6032000
24doubao-seed-2.0-mini-256kByteDance$0.80$1.60256000
25doubao-seed-2.0-lite-128kByteDance$0.90$1.80128000
26GLM-4-LongZhipu AI$1.00$0.501000000
27doubao-seed-1.8-128kByteDance$1.20$2.40128000
28GLM-4.5-Air (32K+)Zhipu AI$1.20$8.00128000
29doubao-seed-codeByteDance$1.20$2.4032000
30doubao-seed-1.6-vision-128kByteDance$1.20$2.40128000
31doubao-seed-1.6-lite-256kByteDance$1.20$2.40256000
32doubao-seed-1.6-128kByteDance$1.20$2.40128000
33doubao-seed-character-128kByteDance$1.20$2.40128000
34doubao-seed-code-128kByteDance$1.40$2.80128000
35doubao-seed-2.0-lite-256kByteDance$1.80$3.60256000
36deepseek-v3ByteDance$2.00$4.0032000
37GLM-4.7Zhipu AI$2.00$8.0032000
38GLM-4.5VZhipu AI$2.00$6.0032000
39GLM-4.6VZhipu AI$2.00$6.008000
40Moonshot V1 8KMoonshot AI$2.00$10.008192
41deepseek-v3.2ByteDance$2.00$4.0032000
42GLM-TTSZhipu AI$2.00$0.008000
43glm-4.7ByteDance$2.00$4.0032000
44doubao-seed-1.6-vision-256kByteDance$2.40$4.80256000
45doubao-seed-1.8-256kByteDance$2.40$4.80256000
46doubao-seed-1.6-256kByteDance$2.40$4.80256000
47doubao-seed-code-256kByteDance$2.80$5.60256000
48doubao-1.5-vision-proByteDance$3.00$6.0032000
49doubao-seed-2.0-codeByteDance$3.20$6.4032000
50doubao-seed-2.0-proByteDance$3.20$6.4032000
51deepseek-v3.1ByteDance$4.00$8.0032000
52Kimi K2 0905 PreviewMoonshot AI$4.00$16.00262144
53glm-4.7-128kByteDance$4.00$8.00128000
54GLM-5Zhipu AI$4.00$18.0032000
55deepseek-v3.2-128kByteDance$4.00$8.00128000
56GLM-4.7 (32K+)Zhipu AI$4.00$16.00200000
57deepseek-r1ByteDance$4.00$8.0032000
58GLM-4V-PlusZhipu AI$4.00$4.008000
59doubao-seed-2.0-code-128kByteDance$4.80$9.60128000
60doubao-seed-2.0-pro-128kByteDance$4.80$9.60128000
61GLM-5-TurboZhipu AI$5.00$22.0032000
62GLM-TTS-CloneZhipu AI$6.00$0.008000
63GLM-5 (32K+)Zhipu AI$6.00$22.00200000
64GLM-5.1Zhipu AI$6.00$24.0032000
65Kimi K2.6Moonshot AI$6.50$27.00262144
66GLM-5-Turbo (32K+)Zhipu AI$7.00$26.00200000
67GLM-5.1 (32K+)Zhipu AI$8.00$28.00200000
68doubao-seed-2.0-code-256kByteDance$9.60$19.20256000
69doubao-seed-2.0-pro-256kByteDance$9.60$19.20256000
70GLM-4-AirXZhipu AI$10.00$10.008000
71GLM-ASR-2512Zhipu AI$16.00$0.008000
72ERNIE 5.1Baidu$22.00$22.000
73ERNIE 5.0Baidu$40.00$40.000
74GLM-4VZhipu AI$50.00$50.002000
75GLM-4-VoiceZhipu AI$80.00$80.008000
76GLM-4-0520Zhipu AI$100.00$50.00128000
-
- - - - -
-

☁️ 云厂商/官方平台(6 家)

- - - - - - - - - - - - - - - -
平台模型数最低价格平均价格
OpenAI3$0.75$2.75
Baidu Qianfan44$0.00$1.41
Zhipu29$0.18$10.99
ByteDance Volcano43$0.15$2.11
Moonshot3$2.00$4.17
DeepSeek2$0.14$0.29
-
- - - - -
-

🔀 中转/聚合平台(1 家)

- - - - - -
平台模型数最低价格平均价格
OpenRouter379$0.00$0.03
-
- - -
-

📌 本报告由 LLM Intelligence Hub 自动生成 · 2026-05-13

-

价格单位:USD/1M tokens

-
- -
- - \ No newline at end of file diff --git a/reports/daily/2026/05/daily_report_2026-05-13.md b/reports/daily/2026/05/daily_report_2026-05-13.md deleted file mode 100644 index afc7f77..0000000 --- a/reports/daily/2026/05/daily_report_2026-05-13.md +++ /dev/null @@ -1,351 +0,0 @@ -# 🤖 LLM Intelligence Hub - 每日情报报告 - -**报告日期**: 2026-05-13 -**生成时间**: 2026-05-13T08:00:01+08:00 - -## 📊 数据质量摘要 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 503 | -| 数据新鲜 | 460 | -| CNY定价 | 126 | -| USD定价 | 377 | -| 厂商总数 | 81 | - -## 🆓 免费模型(共 373 个) - -**按国家分布**: US 144个, 国际 145个, CN 84个 - -**代表性模型(前20个)**: - -| 模型 | 厂商 | 国家 | 上下文 | -|------|------|------|--------| -| xAI: Grok 4 Fast | xAI | US | 2000000 | -| Auto Router | OpenRouter | US | 2000000 | -| Pareto Code Router | OpenRouter | US | 2000000 | -| xAI: Grok 4.20 | xAI | US | 2000000 | -| xAI: Grok 4.1 Fast | xAI | US | 2000000 | -| xAI: Grok 4.20 Multi-Agent | xAI | US | 2000000 | -| OpenAI: GPT-5.4 | OpenAI | US | 1050000 | -| OpenAI: GPT-5.5 | OpenAI | US | 1050000 | -| OpenAI: GPT-5.5 Pro | OpenAI | US | 1050000 | -| OpenAI: GPT-5.4 Pro | OpenAI | US | 1050000 | -| OpenAI GPT Latest | ~openai | 国际 | 1050000 | -| Owl Alpha | OpenRouter | US | 1048756 | -| Google: Gemini 2.5 Pro Preview 06-05 | Google | US | 1048576 | -| Google: Gemini 3 Flash Preview | Google | US | 1048576 | -| Google: Gemini 3.1 Pro Preview | Google | US | 1048576 | -| Google: Gemini 2.0 Flash | Google | US | 1048576 | -| Google: Gemini 3.1 Pro Preview Custom Tools | Google | US | 1048576 | -| Google Gemini Pro Latest | ~google | 国际 | 1048576 | -| Google: Gemini 2.0 Flash Lite | Google | US | 1048576 | -| Google Gemini Flash Latest | ~google | 国际 | 1048576 | -| ... | ... | ... | ... | - -> 共 373 个免费模型,以上为前20个代表性模型 - -## 🌍 国际推荐模型 TOP 5 - -| 排名 | 模型 | 厂商 | 场景 | 输入(原价) | 输出(原价) | 上下文 | -|------|------|------|------|-----------|-----------|--------| -| 1 | Qwen3-VL-8B | Alibaba | 视觉 | ¥0.20 | ¥0.50 | 32000 | -| 2 | Qwen3-VL-32B | Alibaba | 视觉 | ¥0.50 | ¥1.00 | 32000 | -| 3 | GPT-5.4 Mini | OpenAI | 对话 | $0.75 | $4.50 | 200000 | -| 4 | Doubao-Pro | ByteDance | 视觉 | ¥0.80 | ¥2.00 | 32000 | -| 5 | DeepSeek-V3 | DeepSeek | 对话 | ¥1.00 | ¥2.00 | 64000 | - -## 🇨🇳 国内模型 TOP 10 - -| 排名 | 模型 | 厂商 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|------|------|-----------|-----------|--------| -| 1 | DeepSeek V4 Flash | DeepSeek | 对话 | ¥1.02 | ¥2.03 | 1000000 | -| 2 | doubao-seed-1.6-flash | ByteDance | 对话 | ¥0.15 | ¥0.30 | 32000 | -| 3 | GLM-4.6V-FlashX | Zhipu AI | 视觉 | ¥0.15 | ¥1.50 | 8000 | -| 4 | GLM-Realtime-Flash | Zhipu AI | 对话 | ¥0.18 | ¥0.18 | 8000 | -| 5 | doubao-seed-2.0-mini | ByteDance | 对话 | ¥0.20 | ¥0.40 | 32000 | -| 6 | doubao-seed-1.6-lite | ByteDance | 对话 | ¥0.30 | ¥0.60 | 32000 | -| 7 | doubao-seed-1.6-flash-128k | ByteDance | 对话 | ¥0.30 | ¥0.60 | 128000 | -| 8 | GLM-Realtime-Air | Zhipu AI | 对话 | ¥0.30 | ¥0.30 | 8000 | -| 9 | doubao-1.5-lite-32k | ByteDance | 对话 | ¥0.30 | ¥0.60 | 32000 | -| 10 | doubao-seed-2.0-mini-128k | ByteDance | 对话 | ¥0.40 | ¥0.80 | 128000 | -| 11 | DeepSeek V4 Pro | DeepSeek | 对话 | ¥3.15 | ¥6.31 | 1000000 | -| 12 | GLM-4.7-FlashX | Zhipu AI | 对话 | ¥0.50 | ¥3.00 | 200000 | -| 13 | GLM-4-Air | Zhipu AI | 对话 | ¥0.50 | ¥0.25 | 128000 | -| 14 | doubao-seed-1.6-lite-128k | ByteDance | 对话 | ¥0.60 | ¥1.20 | 128000 | -| 15 | doubao-seed-1.6-flash-256k | ByteDance | 对话 | ¥0.60 | ¥1.20 | 256000 | -| 16 | doubao-seed-2.0-lite | ByteDance | 对话 | ¥0.60 | ¥1.20 | 32000 | -| 17 | doubao-seed-character | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 18 | doubao-seed-1.8 | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 19 | doubao-seed-1.6 | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 20 | GLM-4.5-Air | Zhipu AI | 对话 | ¥0.80 | ¥2.00 | 32000 | -| 21 | doubao-pro-32k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 22 | doubao-seed-1.6-vision | ByteDance | 视觉 | ¥0.80 | ¥1.60 | 32000 | -| 23 | doubao-1.5-pro-32k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 24 | doubao-seed-2.0-mini-256k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 256000 | -| 25 | doubao-seed-2.0-lite-128k | ByteDance | 对话 | ¥0.90 | ¥1.80 | 128000 | -| 26 | GLM-4-Long | Zhipu AI | 对话 | ¥1.00 | ¥0.50 | 1000000 | -| 27 | doubao-seed-1.8-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 28 | GLM-4.5-Air (32K+) | Zhipu AI | 对话 | ¥1.20 | ¥8.00 | 128000 | -| 29 | doubao-seed-code | ByteDance | 代码 | ¥1.20 | ¥2.40 | 32000 | -| 30 | doubao-seed-1.6-vision-128k | ByteDance | 视觉 | ¥1.20 | ¥2.40 | 128000 | -| 31 | doubao-seed-1.6-lite-256k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 256000 | -| 32 | doubao-seed-1.6-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 33 | doubao-seed-character-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 34 | doubao-seed-code-128k | ByteDance | 代码 | ¥1.40 | ¥2.80 | 128000 | -| 35 | doubao-seed-2.0-lite-256k | ByteDance | 对话 | ¥1.80 | ¥3.60 | 256000 | -| 36 | deepseek-v3 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 37 | GLM-4.7 | Zhipu AI | 对话 | ¥2.00 | ¥8.00 | 32000 | -| 38 | GLM-4.5V | Zhipu AI | 视觉 | ¥2.00 | ¥6.00 | 32000 | -| 39 | GLM-4.6V | Zhipu AI | 视觉 | ¥2.00 | ¥6.00 | 8000 | -| 40 | Moonshot V1 8K | Moonshot AI | 对话 | ¥2.00 | ¥10.00 | 8192 | -| 41 | deepseek-v3.2 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 42 | GLM-TTS | Zhipu AI | 对话 | ¥2.00 | 免费 | 8000 | -| 43 | glm-4.7 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 44 | doubao-seed-1.6-vision-256k | ByteDance | 视觉 | ¥2.40 | ¥4.80 | 256000 | -| 45 | doubao-seed-1.8-256k | ByteDance | 对话 | ¥2.40 | ¥4.80 | 256000 | -| 46 | doubao-seed-1.6-256k | ByteDance | 对话 | ¥2.40 | ¥4.80 | 256000 | -| 47 | doubao-seed-code-256k | ByteDance | 代码 | ¥2.80 | ¥5.60 | 256000 | -| 48 | doubao-1.5-vision-pro | ByteDance | 视觉 | ¥3.00 | ¥6.00 | 32000 | -| 49 | doubao-seed-2.0-code | ByteDance | 代码 | ¥3.20 | ¥6.40 | 32000 | -| 50 | doubao-seed-2.0-pro | ByteDance | 对话 | ¥3.20 | ¥6.40 | 32000 | -| 51 | deepseek-v3.1 | ByteDance | 对话 | ¥4.00 | ¥8.00 | 32000 | -| 52 | Kimi K2 0905 Preview | Moonshot AI | 对话 | ¥4.00 | ¥16.00 | 262144 | -| 53 | glm-4.7-128k | ByteDance | 对话 | ¥4.00 | ¥8.00 | 128000 | -| 54 | GLM-5 | Zhipu AI | 对话 | ¥4.00 | ¥18.00 | 32000 | -| 55 | deepseek-v3.2-128k | ByteDance | 对话 | ¥4.00 | ¥8.00 | 128000 | -| 56 | GLM-4.7 (32K+) | Zhipu AI | 对话 | ¥4.00 | ¥16.00 | 200000 | -| 57 | deepseek-r1 | ByteDance | 推理 | ¥4.00 | ¥8.00 | 32000 | -| 58 | GLM-4V-Plus | Zhipu AI | 视觉 | ¥4.00 | ¥4.00 | 8000 | -| 59 | doubao-seed-2.0-code-128k | ByteDance | 代码 | ¥4.80 | ¥9.60 | 128000 | -| 60 | doubao-seed-2.0-pro-128k | ByteDance | 对话 | ¥4.80 | ¥9.60 | 128000 | -| 61 | GLM-5-Turbo | Zhipu AI | 对话 | ¥5.00 | ¥22.00 | 32000 | -| 62 | GLM-TTS-Clone | Zhipu AI | 对话 | ¥6.00 | 免费 | 8000 | -| 63 | GLM-5 (32K+) | Zhipu AI | 对话 | ¥6.00 | ¥22.00 | 200000 | -| 64 | GLM-5.1 | Zhipu AI | 对话 | ¥6.00 | ¥24.00 | 32000 | -| 65 | Kimi K2.6 | Moonshot AI | 视觉 | ¥6.50 | ¥27.00 | 262144 | -| 66 | GLM-5-Turbo (32K+) | Zhipu AI | 对话 | ¥7.00 | ¥26.00 | 200000 | -| 67 | GLM-5.1 (32K+) | Zhipu AI | 对话 | ¥8.00 | ¥28.00 | 200000 | -| 68 | doubao-seed-2.0-code-256k | ByteDance | 代码 | ¥9.60 | ¥19.20 | 256000 | -| 69 | doubao-seed-2.0-pro-256k | ByteDance | 对话 | ¥9.60 | ¥19.20 | 256000 | -| 70 | GLM-4-AirX | Zhipu AI | 对话 | ¥10.00 | ¥10.00 | 8000 | -| 71 | GLM-ASR-2512 | Zhipu AI | 对话 | ¥16.00 | 免费 | 8000 | -| 72 | ERNIE 5.1 | Baidu | 对话 | ¥22.00 | ¥22.00 | 0 | -| 73 | ERNIE 5.0 | Baidu | 对话 | ¥40.00 | ¥40.00 | 0 | -| 74 | GLM-4V | Zhipu AI | 视觉 | ¥50.00 | ¥50.00 | 2000 | -| 75 | GLM-4-Voice | Zhipu AI | 对话 | ¥80.00 | ¥80.00 | 8000 | -| 76 | GLM-4-0520 | Zhipu AI | 对话 | ¥100.00 | ¥50.00 | 128000 | - -## 📊 模型分类概览 - -### 🇨🇳 国内官方平台模型 - -**ByteDance Volcano** (43个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| doubao-seed-1.6-flash | 对话 | ¥0.15 | ¥0.30 | 32000 | -| doubao-seed-2.0-mini | 对话 | ¥0.20 | ¥0.40 | 32000 | -| doubao-seed-1.6-lite | 对话 | ¥0.30 | ¥0.60 | 32000 | -| doubao-seed-1.6-flash-128k | 对话 | ¥0.30 | ¥0.60 | 128000 | -| doubao-1.5-lite-32k | 对话 | ¥0.30 | ¥0.60 | 32000 | -| doubao-seed-2.0-mini-128k | 对话 | ¥0.40 | ¥0.80 | 128000 | -| doubao-seed-1.6-lite-128k | 对话 | ¥0.60 | ¥1.20 | 128000 | -| doubao-seed-1.6-flash-256k | 对话 | ¥0.60 | ¥1.20 | 256000 | -| doubao-seed-2.0-lite | 对话 | ¥0.60 | ¥1.20 | 32000 | -| doubao-seed-character | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.8 | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.6 | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-pro-32k | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.6-vision | 视觉 | ¥0.80 | ¥1.60 | 32000 | -| doubao-1.5-pro-32k | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-2.0-mini-256k | 对话 | ¥0.80 | ¥1.60 | 256000 | -| doubao-seed-2.0-lite-128k | 对话 | ¥0.90 | ¥1.80 | 128000 | -| doubao-seed-1.8-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-code | 代码 | ¥1.20 | ¥2.40 | 32000 | -| doubao-seed-1.6-vision-128k | 视觉 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-1.6-lite-256k | 对话 | ¥1.20 | ¥2.40 | 256000 | -| doubao-seed-1.6-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-character-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-code-128k | 代码 | ¥1.40 | ¥2.80 | 128000 | -| doubao-seed-2.0-lite-256k | 对话 | ¥1.80 | ¥3.60 | 256000 | -| deepseek-v3 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| deepseek-v3.2 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| glm-4.7 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| doubao-seed-1.6-vision-256k | 视觉 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-1.8-256k | 对话 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-1.6-256k | 对话 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-code-256k | 代码 | ¥2.80 | ¥5.60 | 256000 | -| doubao-1.5-vision-pro | 视觉 | ¥3.00 | ¥6.00 | 32000 | -| doubao-seed-2.0-code | 代码 | ¥3.20 | ¥6.40 | 32000 | -| doubao-seed-2.0-pro | 对话 | ¥3.20 | ¥6.40 | 32000 | -| deepseek-v3.1 | 对话 | ¥4.00 | ¥8.00 | 32000 | -| glm-4.7-128k | 对话 | ¥4.00 | ¥8.00 | 128000 | -| deepseek-v3.2-128k | 对话 | ¥4.00 | ¥8.00 | 128000 | -| deepseek-r1 | 推理 | ¥4.00 | ¥8.00 | 32000 | -| doubao-seed-2.0-code-128k | 代码 | ¥4.80 | ¥9.60 | 128000 | -| doubao-seed-2.0-pro-128k | 对话 | ¥4.80 | ¥9.60 | 128000 | -| doubao-seed-2.0-code-256k | 代码 | ¥9.60 | ¥19.20 | 256000 | -| doubao-seed-2.0-pro-256k | 对话 | ¥9.60 | ¥19.20 | 256000 | - -**Zhipu** (26个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| GLM-4.6V-FlashX | 视觉 | ¥0.15 | ¥1.50 | 8000 | -| GLM-Realtime-Flash | 对话 | ¥0.18 | ¥0.18 | 8000 | -| GLM-Realtime-Air | 对话 | ¥0.30 | ¥0.30 | 8000 | -| GLM-4.7-FlashX | 对话 | ¥0.50 | ¥3.00 | 200000 | -| GLM-4-Air | 对话 | ¥0.50 | ¥0.25 | 128000 | -| GLM-4.5-Air | 对话 | ¥0.80 | ¥2.00 | 32000 | -| GLM-4-Long | 对话 | ¥1.00 | ¥0.50 | 1000000 | -| GLM-4.5-Air (32K+) | 对话 | ¥1.20 | ¥8.00 | 128000 | -| GLM-4.7 | 对话 | ¥2.00 | ¥8.00 | 32000 | -| GLM-4.5V | 视觉 | ¥2.00 | ¥6.00 | 32000 | -| GLM-4.6V | 视觉 | ¥2.00 | ¥6.00 | 8000 | -| GLM-TTS | 对话 | ¥2.00 | 免费 | 8000 | -| GLM-5 | 对话 | ¥4.00 | ¥18.00 | 32000 | -| GLM-4.7 (32K+) | 对话 | ¥4.00 | ¥16.00 | 200000 | -| GLM-4V-Plus | 视觉 | ¥4.00 | ¥4.00 | 8000 | -| GLM-5-Turbo | 对话 | ¥5.00 | ¥22.00 | 32000 | -| GLM-TTS-Clone | 对话 | ¥6.00 | 免费 | 8000 | -| GLM-5 (32K+) | 对话 | ¥6.00 | ¥22.00 | 200000 | -| GLM-5.1 | 对话 | ¥6.00 | ¥24.00 | 32000 | -| GLM-5-Turbo (32K+) | 对话 | ¥7.00 | ¥26.00 | 200000 | -| GLM-5.1 (32K+) | 对话 | ¥8.00 | ¥28.00 | 200000 | -| GLM-4-AirX | 对话 | ¥10.00 | ¥10.00 | 8000 | -| GLM-ASR-2512 | 对话 | ¥16.00 | 免费 | 8000 | -| GLM-4V | 视觉 | ¥50.00 | ¥50.00 | 2000 | -| GLM-4-Voice | 对话 | ¥80.00 | ¥80.00 | 8000 | -| GLM-4-0520 | 对话 | ¥100.00 | ¥50.00 | 128000 | - -**Moonshot** (3个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| Moonshot V1 8K | 对话 | ¥2.00 | ¥10.00 | 8192 | -| Kimi K2 0905 Preview | 对话 | ¥4.00 | ¥16.00 | 262144 | -| Kimi K2.6 | 视觉 | ¥6.50 | ¥27.00 | 262144 | - -**Baidu Qianfan** (2个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| ERNIE 5.1 | 对话 | ¥22.00 | ¥22.00 | 0 | -| ERNIE 5.0 | 对话 | ¥40.00 | ¥40.00 | 0 | - -**DeepSeek** (2个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| DeepSeek V4 Flash | 对话 | ¥1.02 | ¥2.03 | 1000000 | -| DeepSeek V4 Pro | 对话 | ¥3.15 | ¥6.31 | 1000000 | - -### 💻 代码模型(19个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Pareto Code Router | OpenRouter | 免费 | 免费 | -| Qwen: Qwen3 Coder Flash | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder Plus | Qwen | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex-Mini | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex-Max | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.2-Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5 Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.3-Codex | OpenAI | 免费 | 免费 | -| Qwen: Qwen3 Coder Next | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder 480B A35B | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder 480B A35B... | Qwen | 免费 | 免费 | -| Kwaipilot: KAT-Coder-Pro V2 | kwaipilot | 免费 | 免费 | -| xAI: Grok Code Fast 1 | xAI | 免费 | 免费 | -| Mistral: Codestral 2508 | mistralai | 免费 | 免费 | -| Qwen: Qwen3 Coder 30B A3B I... | Qwen | 免费 | 免费 | -| Qwen2.5 Coder 32B Instruct | Qwen | 免费 | 免费 | -| Arcee AI: Coder Large | arcee-ai | 免费 | 免费 | -| AlfredPros: CodeLLaMa 7B In... | alfredpros | 免费 | 免费 | - -### 🧠 推理模型(35个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Qwen: Qwen Plus 0728 (think... | Qwen | 免费 | 免费 | -| Arcee AI: Trinity Large Thi... | arcee-ai | 免费 | 免费 | -| Qwen: Qwen3 Max Thinking | Qwen | 免费 | 免费 | -| MoonshotAI: Kimi K2 Thinking | Moonshot AI | 免费 | 免费 | -| Arcee AI: Trinity Large Thi... | arcee-ai | 免费 | 免费 | -| OpenAI: o3 Mini High | OpenAI | 免费 | 免费 | -| OpenAI: o3 Deep Research | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini Deep Research | OpenAI | 免费 | 免费 | -| OpenAI: o1 | OpenAI | 免费 | 免费 | -| OpenAI: o3 Mini | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini High | OpenAI | 免费 | 免费 | -| Anthropic: Claude 3.7 Sonne... | Anthropic | 免费 | 免费 | -| OpenAI: o3 Pro | OpenAI | 免费 | 免费 | -| OpenAI: o1-pro | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini | OpenAI | 免费 | 免费 | -| OpenAI: o3 | OpenAI | 免费 | 免费 | -| DeepSeek: R1 0528 | DeepSeek | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Thinking | Qwen | 免费 | 免费 | -| Sao10K: Llama 3.1 Euryale 7... | sao10k | 免费 | 免费 | -| Qwen: Qwen3 30B A3B Thinkin... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 235B A22B Think... | Qwen | 免费 | 免费 | -| Sao10K: Llama 3.3 Euryale 70B | sao10k | 免费 | 免费 | -| Baidu: ERNIE 4.5 21B A3B Th... | Baidu | 免费 | 免费 | -| DeepSeek: R1 Distill Llama 70B | DeepSeek | 免费 | 免费 | -| Qwen: Qwen3 Next 80B A3B Th... | Qwen | 免费 | 免费 | -| Arcee AI: Maestro Reasoning | arcee-ai | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Thin... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 235B A22B Th... | Qwen | 免费 | 免费 | -| Perplexity: Sonar Reasoning... | Perplexity | 免费 | 免费 | -| DeepSeek: R1 | DeepSeek | 免费 | 免费 | -| LiquidAI: LFM2.5-1.2B-Think... | liquid | 免费 | 免费 | -| DeepSeek: R1 Distill Qwen 32B | DeepSeek | 免费 | 免费 | -| Sao10K: Llama 3.1 70B Hanam... | sao10k | 免费 | 免费 | -| Sao10k: Llama 3 Euryale 70B... | sao10k | 免费 | 免费 | -| Sao10K: Llama 3 8B Lunaris | sao10k | 免费 | 免费 | - -### 👁️ 视觉/多模态模型(15个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Qwen: Qwen3 VL 235B A22B In... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Thinking | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Instruct | Qwen | 免费 | 免费 | -| Meta: Llama 3.2 11B Vision ... | meta-llama | 免费 | 免费 | -| Qwen: Qwen VL Max | Qwen | 免费 | 免费 | -| Qwen: Qwen VL Plus | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Thin... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Inst... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 32B Instruct | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 235B A22B Th... | Qwen | 免费 | 免费 | -| NVIDIA: Nemotron Nano 12B 2... | NVIDIA | 免费 | 免费 | -| Baidu: ERNIE 4.5 VL 424B A47B | Baidu | 免费 | 免费 | -| MoonshotAI: Kimi K2.6 | Moonshot AI | 免费 | 免费 | -| Qwen: Qwen2.5 VL 72B Instruct | Qwen | 免费 | 免费 | -| Baidu: ERNIE 4.5 VL 28B A3B | Baidu | 免费 | 免费 | - -## 🇨🇳 国内官方平台(5 家) - -- **Baidu Qianfan**: 44 个模型,最低 ¥0.00/MTok -- **Zhipu**: 29 个模型,最低 ¥0.18/MTok -- **ByteDance Volcano**: 43 个模型,最低 ¥0.15/MTok -- **Moonshot**: 3 个模型,最低 ¥2.00/MTok -- **DeepSeek**: 2 个模型,最低 ¥0.14/MTok - -## ☁️ 国际官方平台(1 家) - -- **OpenAI**: 3 个模型,最低 $0.75/MTok - -## 🔀 中转/聚合平台(1 家) - -- **OpenRouter**: 379 个模型,最低 $0.00/MTok - ---- - -📌 **说明**: 本报告由 LLM Intelligence Hub 自动生成。 -- 国际模型价格按 1 USD = 7.25 CNY 换算显示，括号内为原生货币价格 -- 国内模型价格为厂商原生 CNY 定价 -- 数据来源: OpenRouter API + 智谱AI + 百度千帆 + Moonshot + DeepSeek + OpenAI - -_生成时间: 2026-05-13T08:00:01+08:00_ diff --git a/reports/daily/daily_report_2026-05-05.md b/reports/daily/daily_report_2026-05-05.md deleted file mode 100644 index 1738ce1..0000000 --- a/reports/daily/daily_report_2026-05-05.md +++ /dev/null @@ -1,27 +0,0 @@ -# LLM Intelligence Hub - 每日报告 -**报告日期**: 2026-05-05 -**原始采集时间**: 2026-05-05T08:00:00Z - -## 概览 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 2 | -| 免费模型 | 1 | -| 付费模型 | 1 | - -## 免费模型 TOP 10（按上下文长度排序） - -| 模型 | 上下文长度 | 特性 | -|------|------------|------| -| anthropic/claude-3.5-sonnet:free | 200000 | 无 | - -## 低价模型 TOP 10（按输入价格升序，$/M Token） - -| 模型 | 输入价格 | 输出价格 | 上下文长度 | -|------|---------|---------|------------| -| openai/gpt-4o | 2.5000 | 10.0000 | 128000 | - - ---- -_由 LLM Intelligence Hub 自动生成 2026-05-05_ diff --git a/reports/daily/daily_report_2026-05-06.md b/reports/daily/daily_report_2026-05-06.md deleted file mode 100644 index f27911c..0000000 --- a/reports/daily/daily_report_2026-05-06.md +++ /dev/null @@ -1,27 +0,0 @@ -# LLM Intelligence Hub - 每日报告 -**报告日期**: 2026-05-06 -**生成时间**: 2026-05-06T20:34:56+08:00 - -## 概览 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 2 | -| 免费模型 | 1 | -| 付费模型 | 1 | - -## 免费模型 TOP 5（按上下文长度排序） - -| 模型 | 上下文长度 | 特性 | -|------|------------|------| -| anthropic/claude-3.5-sonnet:free | 200000 | 无 | - -## 低价模型 TOP 5（按输入价格升序，$/M Token） - -| 模型 | 输入价格 | 输出价格 | 上下文长度 | -|------|---------|---------|------------| -| openai/gpt-4o | 2.5000 | 10.0000 | 128000 | - - ---- -_由 LLM Intelligence Hub 自动生成 2026-05-06_ diff --git a/reports/daily/daily_report_2026-05-07.md b/reports/daily/daily_report_2026-05-07.md deleted file mode 100644 index e71be86..0000000 --- a/reports/daily/daily_report_2026-05-07.md +++ /dev/null @@ -1,27 +0,0 @@ -# LLM Intelligence Hub - 每日报告 -**报告日期**: 2026-05-07 -**原始采集时间**: 2026-05-07T11:18:12+08:00 - -## 概览 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 2 | -| 免费模型 | 1 | -| 付费模型 | 1 | - -## 免费模型 TOP 10（按上下文长度排序） - -| 模型 | 上下文长度 | 特性 | -|------|------------|------| -| anthropic/claude-3.5-sonnet:free | 200000 | 无 | - -## 低价模型 TOP 10（按输入价格升序，$/M Token） - -| 模型 | 输入价格 | 输出价格 | 上下文长度 | -|------|---------|---------|------------| -| openai/gpt-4o | 2.5000 | 10.0000 | 128000 | - - ---- -_由 LLM Intelligence Hub 自动生成 2026-05-07_ diff --git a/reports/daily/daily_report_2026-05-08.md b/reports/daily/daily_report_2026-05-08.md deleted file mode 100644 index 610e9d2..0000000 --- a/reports/daily/daily_report_2026-05-08.md +++ /dev/null @@ -1,27 +0,0 @@ -# LLM Intelligence Hub - 每日报告 -**报告日期**: 2026-05-08 -**原始采集时间**: 2026-05-08T13:47:39+08:00 - -## 概览 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 2 | -| 免费模型 | 1 | -| 付费模型 | 1 | - -## 免费模型 TOP 10（按上下文长度排序） - -| 模型 | 上下文长度 | 特性 | -|------|------------|------| -| anthropic/claude-3.5-sonnet:free | 200000 | 无 | - -## 低价模型 TOP 10（按输入价格升序，$/M Token） - -| 模型 | 输入价格 | 输出价格 | 上下文长度 | -|------|---------|---------|------------| -| openai/gpt-4o | 2.5000 | 10.0000 | 128000 | - - ---- -_由 LLM Intelligence Hub 自动生成 2026-05-08_ diff --git a/reports/daily/daily_report_2026-05-09.md b/reports/daily/daily_report_2026-05-09.md deleted file mode 100644 index 5743ef1..0000000 --- a/reports/daily/daily_report_2026-05-09.md +++ /dev/null @@ -1,27 +0,0 @@ -# LLM Intelligence Hub - 每日报告 -**报告日期**: 2026-05-09 -**原始采集时间**: 2026-05-09T21:30:54+08:00 - -## 概览 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 2 | -| 免费模型 | 1 | -| 付费模型 | 1 | - -## 免费模型 TOP 10（按上下文长度排序） - -| 模型 | 上下文长度 | 特性 | -|------|------------|------| -| anthropic/claude-3.5-sonnet:free | 200000 | 无 | - -## 低价模型 TOP 10（按输入价格升序，$/M Token） - -| 模型 | 输入价格 | 输出价格 | 上下文长度 | -|------|---------|---------|------------| -| openai/gpt-4o | 2.5000 | 10.0000 | 128000 | - - ---- -_由 LLM Intelligence Hub 自动生成 2026-05-09_ diff --git a/reports/daily/daily_report_2026-05-10.md b/reports/daily/daily_report_2026-05-10.md deleted file mode 100644 index a753629..0000000 --- a/reports/daily/daily_report_2026-05-10.md +++ /dev/null @@ -1,409 +0,0 @@ -# 🤖 LLM Intelligence Hub - 每日情报报告 - -**报告日期**: 2026-05-10 -**生成时间**: 2026-05-10T23:02:31+08:00 - -## 📊 数据质量摘要 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 377 | -| 数据新鲜 | 368 | -| 数据待补 | 9 | -| CNY定价 | 0 | -| USD定价 | 377 | -| 厂商总数 | 60 | - -## 🆓 免费模型 TOP 10 - -| 模型 | 厂商 | 上下文 | -|------|------|--------| -| openai/gpt-4o | Openai | 128000 | -| anthropic/claude-3.5-sonnet:free | Anthropic | 200000 | -| deepseek/deepseek-r1 | Deepseek | 64000 | -| moonshotai/kimi-k2.6 | Moonshotai | 262144 | -| moonshotai/kimi-k2.5 | Moonshotai | 262144 | -| inclusionai/ring-2.6-1t:free | Inclusionai | 262144 | -| google/gemini-3.1-flash-lite | Google | 1048576 | -| baidu/cobuddy:free | Baidu | 131072 | -| openai/gpt-chat-latest | Openai | 400000 | -| x-ai/grok-4.3 | X Ai | 1000000 | -| ibm-granite/granite-4.1-8b | Ibm Granite | 131072 | -| mistralai/mistral-medium-3-5 | Mistralai | 262144 | -| openrouter/owl-alpha | Openrouter | 1048756 | -| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | Nvidia | 256000 | -| poolside/laguna-xs.2:free | Poolside | 131072 | -| poolside/laguna-m.1:free | Poolside | 131072 | -| ~anthropic/claude-haiku-latest | ~anthropic | 200000 | -| ~openai/gpt-mini-latest | ~openai | 400000 | -| ~google/gemini-pro-latest | ~google | 1048576 | -| ~moonshotai/kimi-latest | ~moonshotai | 262144 | -| ~google/gemini-flash-latest | ~google | 1048576 | -| ~anthropic/claude-sonnet-latest | ~anthropic | 1000000 | -| ~openai/gpt-latest | ~openai | 1050000 | -| qwen/qwen3.5-plus-20260420 | Qwen | 1000000 | -| qwen/qwen3.6-flash | Qwen | 1000000 | -| qwen/qwen3.6-35b-a3b | Qwen | 262144 | -| qwen/qwen3.6-max-preview | Qwen | 262144 | -| qwen/qwen3.6-27b | Qwen | 262144 | -| openai/gpt-5.5-pro | Openai | 1050000 | -| openai/gpt-5.5 | Openai | 1050000 | -| deepseek/deepseek-v4-pro | Deepseek | 1048576 | -| deepseek/deepseek-v4-flash | Deepseek | 1048576 | -| inclusionai/ling-2.6-1t | Inclusionai | 262144 | -| tencent/hy3-preview | Tencent | 262144 | -| xiaomi/mimo-v2.5-pro | Xiaomi | 1048576 | -| xiaomi/mimo-v2.5 | Xiaomi | 1048576 | -| openai/gpt-5.4-image-2 | Openai | 272000 | -| inclusionai/ling-2.6-flash | Inclusionai | 262144 | -| ~anthropic/claude-opus-latest | ~anthropic | 1000000 | -| openrouter/pareto-code | Openrouter | 2000000 | -| baidu/qianfan-ocr-fast:free | Baidu | 65536 | -| anthropic/claude-opus-4.7 | Anthropic | 1000000 | -| anthropic/claude-opus-4.6-fast | Anthropic | 1000000 | -| z-ai/glm-5.1 | Z Ai | 202752 | -| google/gemma-4-26b-a4b-it:free | Google | 262144 | -| google/gemma-4-26b-a4b-it | Google | 262144 | -| google/gemma-4-31b-it:free | Google | 262144 | -| google/gemma-4-31b-it | Google | 262144 | -| qwen/qwen3.6-plus | Qwen | 1000000 | -| z-ai/glm-5v-turbo | Z Ai | 202752 | -| arcee-ai/trinity-large-thinking | Arcee Ai | 262144 | -| x-ai/grok-4.20-multi-agent | X Ai | 2000000 | -| x-ai/grok-4.20 | X Ai | 2000000 | -| google/lyria-3-pro-preview | Google | 1048576 | -| google/lyria-3-clip-preview | Google | 1048576 | -| kwaipilot/kat-coder-pro-v2 | Kwaipilot | 256000 | -| rekaai/reka-edge | Rekaai | 16384 | -| xiaomi/mimo-v2-omni | Xiaomi | 262144 | -| xiaomi/mimo-v2-pro | Xiaomi | 1048576 | -| minimax/minimax-m2.7 | Minimax | 196608 | -| openai/gpt-5.4-nano | Openai | 400000 | -| openai/gpt-5.4-mini | Openai | 400000 | -| mistralai/mistral-small-2603 | Mistralai | 262144 | -| z-ai/glm-5-turbo | Z Ai | 202752 | -| nvidia/nemotron-3-super-120b-a12b:free | Nvidia | 262144 | -| nvidia/nemotron-3-super-120b-a12b | Nvidia | 262144 | -| bytedance-seed/seed-2.0-lite | Bytedance Seed | 262144 | -| qwen/qwen3.5-9b | Qwen | 262144 | -| openai/gpt-5.4-pro | Openai | 1050000 | -| openai/gpt-5.4 | Openai | 1050000 | -| inception/mercury-2 | Inception | 128000 | -| openai/gpt-5.3-chat | Openai | 128000 | -| google/gemini-3.1-flash-lite-preview | Google | 1048576 | -| bytedance-seed/seed-2.0-mini | Bytedance Seed | 262144 | -| google/gemini-3.1-flash-image-preview | Google | 65536 | -| qwen/qwen3.5-35b-a3b | Qwen | 262144 | -| qwen/qwen3.5-27b | Qwen | 262144 | -| qwen/qwen3.5-122b-a10b | Qwen | 262144 | -| qwen/qwen3.5-flash-02-23 | Qwen | 1000000 | -| liquid/lfm-2-24b-a2b | Liquid | 32768 | -| google/gemini-3.1-pro-preview-customtools | Google | 1048576 | -| openai/gpt-5.3-codex | Openai | 400000 | -| aion-labs/aion-2.0 | Aion Labs | 131072 | -| google/gemini-3.1-pro-preview | Google | 1048576 | -| anthropic/claude-sonnet-4.6 | Anthropic | 1000000 | -| qwen/qwen3.5-plus-02-15 | Qwen | 1000000 | -| qwen/qwen3.5-397b-a17b | Qwen | 262144 | -| minimax/minimax-m2.5:free | Minimax | 196608 | -| minimax/minimax-m2.5 | Minimax | 196608 | -| z-ai/glm-5 | Z Ai | 202752 | -| qwen/qwen3-max-thinking | Qwen | 262144 | -| anthropic/claude-opus-4.6 | Anthropic | 1000000 | -| qwen/qwen3-coder-next | Qwen | 262144 | -| openrouter/free | Openrouter | 200000 | -| stepfun/step-3.5-flash | Stepfun | 262144 | -| arcee-ai/trinity-large-preview | Arcee Ai | 131000 | -| upstage/solar-pro-3 | Upstage | 128000 | -| minimax/minimax-m2-her | Minimax | 65536 | -| writer/palmyra-x5 | Writer | 1040000 | -| liquid/lfm-2.5-1.2b-thinking:free | Liquid | 32768 | -| liquid/lfm-2.5-1.2b-instruct:free | Liquid | 32768 | -| openai/gpt-audio | Openai | 128000 | -| openai/gpt-audio-mini | Openai | 128000 | -| z-ai/glm-4.7-flash | Z Ai | 202752 | -| openai/gpt-5.2-codex | Openai | 400000 | -| bytedance-seed/seed-1.6-flash | Bytedance Seed | 262144 | -| bytedance-seed/seed-1.6 | Bytedance Seed | 262144 | -| minimax/minimax-m2.1 | Minimax | 196608 | -| z-ai/glm-4.7 | Z Ai | 202752 | -| google/gemini-3-flash-preview | Google | 1048576 | -| xiaomi/mimo-v2-flash | Xiaomi | 262144 | -| nvidia/nemotron-3-nano-30b-a3b:free | Nvidia | 256000 | -| nvidia/nemotron-3-nano-30b-a3b | Nvidia | 262144 | -| openai/gpt-5.2-chat | Openai | 128000 | -| openai/gpt-5.2-pro | Openai | 400000 | -| openai/gpt-5.2 | Openai | 400000 | -| mistralai/devstral-2512 | Mistralai | 262144 | -| relace/relace-search | Relace | 256000 | -| z-ai/glm-4.6v | Z Ai | 131072 | -| nex-agi/deepseek-v3.1-nex-n1 | Nex Agi | 131072 | -| essentialai/rnj-1-instruct | Essentialai | 32768 | -| openrouter/bodybuilder | Openrouter | 128000 | -| openai/gpt-5.1-codex-max | Openai | 400000 | -| amazon/nova-2-lite-v1 | Amazon | 1000000 | -| mistralai/ministral-14b-2512 | Mistralai | 262144 | -| mistralai/ministral-8b-2512 | Mistralai | 262144 | -| mistralai/ministral-3b-2512 | Mistralai | 131072 | -| mistralai/mistral-large-2512 | Mistralai | 262144 | -| arcee-ai/trinity-mini | Arcee Ai | 131072 | -| deepseek/deepseek-v3.2-speciale | Deepseek | 163840 | -| deepseek/deepseek-v3.2 | Deepseek | 131072 | -| prime-intellect/intellect-3 | Prime Intellect | 131072 | -| anthropic/claude-opus-4.5 | Anthropic | 200000 | -| allenai/olmo-3-32b-think | Allenai | 65536 | -| google/gemini-3-pro-image-preview | Google | 65536 | -| x-ai/grok-4.1-fast | X Ai | 2000000 | -| deepcogito/cogito-v2.1-671b | Deepcogito | 128000 | -| openai/gpt-5.1 | Openai | 400000 | -| openai/gpt-5.1-chat | Openai | 128000 | -| openai/gpt-5.1-codex | Openai | 400000 | -| openai/gpt-5.1-codex-mini | Openai | 400000 | -| moonshotai/kimi-k2-thinking | Moonshotai | 262144 | -| amazon/nova-premier-v1 | Amazon | 1000000 | -| perplexity/sonar-pro-search | Perplexity | 200000 | -| mistralai/voxtral-small-24b-2507 | Mistralai | 32000 | -| openai/gpt-oss-safeguard-20b | Openai | 131072 | -| nvidia/nemotron-nano-12b-v2-vl:free | Nvidia | 128000 | -| minimax/minimax-m2 | Minimax | 196608 | -| qwen/qwen3-vl-32b-instruct | Qwen | 131072 | -| ibm-granite/granite-4.0-h-micro | Ibm Granite | 131000 | -| microsoft/phi-4-mini-instruct | Microsoft | 128000 | -| openai/gpt-5-image-mini | Openai | 400000 | -| anthropic/claude-haiku-4.5 | Anthropic | 200000 | -| qwen/qwen3-vl-8b-thinking | Qwen | 131072 | -| qwen/qwen3-vl-8b-instruct | Qwen | 131072 | -| openai/gpt-5-image | Openai | 400000 | -| openai/o3-deep-research | Openai | 200000 | -| openai/o4-mini-deep-research | Openai | 200000 | -| nvidia/llama-3.3-nemotron-super-49b-v1.5 | Nvidia | 131072 | -| baidu/ernie-4.5-21b-a3b-thinking | Baidu | 131072 | -| google/gemini-2.5-flash-image | Google | 32768 | -| qwen/qwen3-vl-30b-a3b-thinking | Qwen | 131072 | -| qwen/qwen3-vl-30b-a3b-instruct | Qwen | 131072 | -| openai/gpt-5-pro | Openai | 400000 | -| z-ai/glm-4.6 | Z Ai | 204800 | -| anthropic/claude-sonnet-4.5 | Anthropic | 1000000 | -| deepseek/deepseek-v3.2-exp | Deepseek | 163840 | -| thedrummer/cydonia-24b-v4.1 | Thedrummer | 131072 | -| relace/relace-apply-3 | Relace | 256000 | -| google/gemini-2.5-flash-lite-preview-09-2025 | Google | 1048576 | -| qwen/qwen3-vl-235b-a22b-thinking | Qwen | 131072 | -| qwen/qwen3-vl-235b-a22b-instruct | Qwen | 262144 | -| qwen/qwen3-max | Qwen | 262144 | -| qwen/qwen3-coder-plus | Qwen | 1000000 | -| openai/gpt-5-codex | Openai | 400000 | -| deepseek/deepseek-v3.1-terminus | Deepseek | 163840 | -| x-ai/grok-4-fast | X Ai | 2000000 | -| alibaba/tongyi-deepresearch-30b-a3b | Alibaba | 131072 | -| qwen/qwen3-coder-flash | Qwen | 1000000 | -| qwen/qwen3-next-80b-a3b-thinking | Qwen | 131072 | -| qwen/qwen3-next-80b-a3b-instruct:free | Qwen | 262144 | -| qwen/qwen3-next-80b-a3b-instruct | Qwen | 262144 | -| qwen/qwen-plus-2025-07-28:thinking | Qwen | 1000000 | -| qwen/qwen-plus-2025-07-28 | Qwen | 1000000 | -| nvidia/nemotron-nano-9b-v2:free | Nvidia | 128000 | -| nvidia/nemotron-nano-9b-v2 | Nvidia | 131072 | -| moonshotai/kimi-k2-0905 | Moonshotai | 262144 | -| qwen/qwen3-30b-a3b-thinking-2507 | Qwen | 131072 | -| x-ai/grok-code-fast-1 | X Ai | 256000 | -| nousresearch/hermes-4-70b | Nousresearch | 131072 | -| nousresearch/hermes-4-405b | Nousresearch | 131072 | -| deepseek/deepseek-chat-v3.1 | Deepseek | 32768 | -| openai/gpt-4o-audio-preview | Openai | 128000 | -| mistralai/mistral-medium-3.1 | Mistralai | 131072 | -| baidu/ernie-4.5-21b-a3b | Baidu | 120000 | -| baidu/ernie-4.5-vl-28b-a3b | Baidu | 30000 | -| z-ai/glm-4.5v | Z Ai | 65536 | -| ai21/jamba-large-1.7 | Ai21 | 256000 | -| openai/gpt-5-chat | Openai | 128000 | -| openai/gpt-5 | Openai | 400000 | -| openai/gpt-5-mini | Openai | 400000 | -| openai/gpt-5-nano | Openai | 400000 | -| openai/gpt-oss-120b:free | Openai | 131072 | -| openai/gpt-oss-120b | Openai | 131072 | -| openai/gpt-oss-20b:free | Openai | 131072 | -| openai/gpt-oss-20b | Openai | 131072 | -| anthropic/claude-opus-4.1 | Anthropic | 200000 | -| mistralai/codestral-2508 | Mistralai | 256000 | -| qwen/qwen3-coder-30b-a3b-instruct | Qwen | 160000 | -| qwen/qwen3-30b-a3b-instruct-2507 | Qwen | 262144 | -| z-ai/glm-4.5 | Z Ai | 131072 | -| z-ai/glm-4.5-air:free | Z Ai | 131072 | -| z-ai/glm-4.5-air | Z Ai | 131072 | -| qwen/qwen3-235b-a22b-thinking-2507 | Qwen | 131072 | -| z-ai/glm-4-32b | Z Ai | 128000 | -| qwen/qwen3-coder:free | Qwen | 262000 | -| qwen/qwen3-coder | Qwen | 262144 | -| bytedance/ui-tars-1.5-7b | Bytedance | 128000 | -| google/gemini-2.5-flash-lite | Google | 1048576 | -| qwen/qwen3-235b-a22b-2507 | Qwen | 262144 | -| switchpoint/router | Switchpoint | 131072 | -| moonshotai/kimi-k2 | Moonshotai | 131072 | -| mistralai/devstral-medium | Mistralai | 131072 | -| mistralai/devstral-small | Mistralai | 131072 | -| cognitivecomputations/dolphin-mistral-24b-venice-edition:free | Cognitivecomputations | 32768 | -| x-ai/grok-4 | X Ai | 256000 | -| tencent/hunyuan-a13b-instruct | Tencent | 131072 | -| morph/morph-v3-large | Morph | 262144 | -| morph/morph-v3-fast | Morph | 81920 | -| baidu/ernie-4.5-vl-424b-a47b | Baidu | 123000 | -| baidu/ernie-4.5-300b-a47b | Baidu | 123000 | -| mistralai/mistral-small-3.2-24b-instruct | Mistralai | 128000 | -| minimax/minimax-m1 | Minimax | 1000000 | -| google/gemini-2.5-flash | Google | 1048576 | -| google/gemini-2.5-pro | Google | 1048576 | -| openai/o3-pro | Openai | 200000 | -| x-ai/grok-3-mini | X Ai | 131072 | -| x-ai/grok-3 | X Ai | 131072 | -| google/gemini-2.5-pro-preview | Google | 1048576 | -| deepseek/deepseek-r1-0528 | Deepseek | 163840 | -| anthropic/claude-opus-4 | Anthropic | 200000 | -| anthropic/claude-sonnet-4 | Anthropic | 1000000 | -| google/gemma-3n-e4b-it | Google | 32768 | -| mistralai/mistral-medium-3 | Mistralai | 131072 | -| google/gemini-2.5-pro-preview-05-06 | Google | 1048576 | -| arcee-ai/spotlight | Arcee Ai | 131072 | -| arcee-ai/maestro-reasoning | Arcee Ai | 131072 | -| arcee-ai/virtuoso-large | Arcee Ai | 131072 | -| arcee-ai/coder-large | Arcee Ai | 32768 | -| meta-llama/llama-guard-4-12b | Meta Llama | 163840 | -| qwen/qwen3-30b-a3b | Qwen | 40960 | -| qwen/qwen3-8b | Qwen | 40960 | -| qwen/qwen3-14b | Qwen | 40960 | -| qwen/qwen3-32b | Qwen | 40960 | -| qwen/qwen3-235b-a22b | Qwen | 131072 | -| openai/o4-mini-high | Openai | 200000 | -| openai/o3 | Openai | 200000 | -| openai/o4-mini | Openai | 200000 | -| openai/gpt-4.1 | Openai | 1047576 | -| openai/gpt-4.1-mini | Openai | 1047576 | -| openai/gpt-4.1-nano | Openai | 1047576 | -| alfredpros/codellama-7b-instruct-solidity | Alfredpros | 4096 | -| x-ai/grok-3-mini-beta | X Ai | 131072 | -| x-ai/grok-3-beta | X Ai | 131072 | -| meta-llama/llama-4-maverick | Meta Llama | 1048576 | -| meta-llama/llama-4-scout | Meta Llama | 327680 | -| deepseek/deepseek-chat-v3-0324 | Deepseek | 163840 | -| openai/o1-pro | Openai | 200000 | -| mistralai/mistral-small-3.1-24b-instruct | Mistralai | 128000 | -| google/gemma-3-4b-it | Google | 131072 | -| google/gemma-3-12b-it | Google | 131072 | -| cohere/command-a | Cohere | 256000 | -| openai/gpt-4o-mini-search-preview | Openai | 128000 | -| openai/gpt-4o-search-preview | Openai | 128000 | -| rekaai/reka-flash-3 | Rekaai | 65536 | -| google/gemma-3-27b-it | Google | 131072 | -| thedrummer/skyfall-36b-v2 | Thedrummer | 32768 | -| perplexity/sonar-reasoning-pro | Perplexity | 128000 | -| perplexity/sonar-pro | Perplexity | 200000 | -| perplexity/sonar-deep-research | Perplexity | 128000 | -| google/gemini-2.0-flash-lite-001 | Google | 1048576 | -| anthropic/claude-3.7-sonnet | Anthropic | 200000 | -| anthropic/claude-3.7-sonnet:thinking | Anthropic | 200000 | -| mistralai/mistral-saba | Mistralai | 32768 | -| meta-llama/llama-guard-3-8b | Meta Llama | 131072 | -| openai/o3-mini-high | Openai | 200000 | -| google/gemini-2.0-flash-001 | Google | 1000000 | -| qwen/qwen-vl-plus | Qwen | 131072 | -| aion-labs/aion-1.0 | Aion Labs | 131072 | -| aion-labs/aion-1.0-mini | Aion Labs | 131072 | -| aion-labs/aion-rp-llama-3.1-8b | Aion Labs | 32768 | -| qwen/qwen-vl-max | Qwen | 131072 | -| qwen/qwen-turbo | Qwen | 131072 | -| qwen/qwen2.5-vl-72b-instruct | Qwen | 32000 | -| qwen/qwen-plus | Qwen | 1000000 | -| qwen/qwen-max | Qwen | 32768 | -| openai/o3-mini | Openai | 200000 | -| mistralai/mistral-small-24b-instruct-2501 | Mistralai | 32768 | -| deepseek/deepseek-r1-distill-qwen-32b | Deepseek | 32768 | -| perplexity/sonar | Perplexity | 127072 | -| deepseek/deepseek-r1-distill-llama-70b | Deepseek | 131072 | -| minimax/minimax-01 | Minimax | 1000192 | -| microsoft/phi-4 | Microsoft | 16384 | -| sao10k/l3.1-70b-hanami-x1 | Sao10k | 16000 | -| deepseek/deepseek-chat | Deepseek | 163840 | -| sao10k/l3.3-euryale-70b | Sao10k | 131072 | -| openai/o1 | Openai | 200000 | -| cohere/command-r7b-12-2024 | Cohere | 128000 | -| meta-llama/llama-3.3-70b-instruct:free | Meta Llama | 65536 | -| meta-llama/llama-3.3-70b-instruct | Meta Llama | 131072 | -| amazon/nova-lite-v1 | Amazon | 300000 | -| amazon/nova-micro-v1 | Amazon | 128000 | -| amazon/nova-pro-v1 | Amazon | 300000 | -| openai/gpt-4o-2024-11-20 | Openai | 128000 | -| mistralai/mistral-large-2411 | Mistralai | 131072 | -| mistralai/mistral-large-2407 | Mistralai | 131072 | -| mistralai/pixtral-large-2411 | Mistralai | 131072 | -| qwen/qwen-2.5-coder-32b-instruct | Qwen | 32768 | -| thedrummer/unslopnemo-12b | Thedrummer | 32768 | -| anthropic/claude-3.5-haiku | Anthropic | 200000 | -| anthracite-org/magnum-v4-72b | Anthracite Org | 16384 | -| qwen/qwen-2.5-7b-instruct | Qwen | 32768 | -| inflection/inflection-3-productivity | Inflection | 8000 | -| inflection/inflection-3-pi | Inflection | 8000 | -| thedrummer/rocinante-12b | Thedrummer | 32768 | -| meta-llama/llama-3.2-3b-instruct:free | Meta Llama | 131072 | -| meta-llama/llama-3.2-3b-instruct | Meta Llama | 80000 | -| meta-llama/llama-3.2-1b-instruct | Meta Llama | 60000 | -| meta-llama/llama-3.2-11b-vision-instruct | Meta Llama | 131072 | -| qwen/qwen-2.5-72b-instruct | Qwen | 32768 | -| cohere/command-r-plus-08-2024 | Cohere | 128000 | -| cohere/command-r-08-2024 | Cohere | 128000 | -| sao10k/l3.1-euryale-70b | Sao10k | 131072 | -| nousresearch/hermes-3-llama-3.1-70b | Nousresearch | 131072 | -| nousresearch/hermes-3-llama-3.1-405b:free | Nousresearch | 131072 | -| nousresearch/hermes-3-llama-3.1-405b | Nousresearch | 131072 | -| sao10k/l3-lunaris-8b | Sao10k | 8192 | -| openai/gpt-4o-2024-08-06 | Openai | 128000 | -| meta-llama/llama-3.1-8b-instruct | Meta Llama | 16384 | -| meta-llama/llama-3.1-70b-instruct | Meta Llama | 131072 | -| mistralai/mistral-nemo | Mistralai | 131072 | -| openai/gpt-4o-mini-2024-07-18 | Openai | 128000 | -| openai/gpt-4o-mini | Openai | 128000 | -| google/gemma-2-27b-it | Google | 8192 | -| sao10k/l3-euryale-70b | Sao10k | 8192 | -| nousresearch/hermes-2-pro-llama-3-8b | Nousresearch | 8192 | -| openai/gpt-4o-2024-05-13 | Openai | 128000 | -| meta-llama/llama-3-8b-instruct | Meta Llama | 8192 | -| meta-llama/llama-3-70b-instruct | Meta Llama | 8192 | -| mistralai/mixtral-8x22b-instruct | Mistralai | 65536 | -| microsoft/wizardlm-2-8x22b | Microsoft | 65535 | -| openai/gpt-4-turbo | Openai | 128000 | -| anthropic/claude-3-haiku | Anthropic | 200000 | -| mistralai/mistral-large | Mistralai | 128000 | -| openai/gpt-4-turbo-preview | Openai | 128000 | -| openai/gpt-3.5-turbo-0613 | Openai | 4095 | -| alpindale/goliath-120b | Alpindale | 6144 | -| openrouter/auto | Openrouter | 2000000 | -| openai/gpt-4-1106-preview | Openai | 128000 | -| openai/gpt-3.5-turbo-instruct | Openai | 4095 | -| mistralai/mistral-7b-instruct-v0.1 | Mistralai | 2824 | -| openai/gpt-3.5-turbo-16k | Openai | 16385 | -| mancer/weaver | Mancer | 8000 | -| undi95/remm-slerp-l2-13b | Undi95 | 6144 | -| gryphe/mythomax-l2-13b | Gryphe | 4096 | -| openai/gpt-4-0314 | Openai | 8191 | -| openai/gpt-4 | Openai | 8191 | -| openai/gpt-3.5-turbo | Openai | 16385 | - -## 📏 大上下文模型 TOP 10 - -| 排名 | 模型 | 厂商 | 上下文长度 | -|------|------|------|------------| -| 1 | openrouter/auto | Openrouter | 2000000 | -| 2 | x-ai/grok-4.1-fast | X Ai | 2000000 | -| 3 | x-ai/grok-4.20 | X Ai | 2000000 | -| 4 | x-ai/grok-4.20-multi-agent | X Ai | 2000000 | -| 5 | openrouter/pareto-code | Openrouter | 2000000 | -| 6 | x-ai/grok-4-fast | X Ai | 2000000 | -| 7 | openai/gpt-5.4 | Openai | 1050000 | -| 8 | openai/gpt-5.4-pro | Openai | 1050000 | -| 9 | openai/gpt-5.5 | Openai | 1050000 | -| 10 | openai/gpt-5.5-pro | Openai | 1050000 | - ---- - -📌 **说明**: 本报告由 LLM Intelligence Hub 自动生成。价格单位：USD/1M tokens。 - -_生成时间: 2026-05-10T23:02:31+08:00_ diff --git a/reports/daily/daily_report_2026-05-11.md b/reports/daily/daily_report_2026-05-11.md deleted file mode 100644 index 8eea893..0000000 --- a/reports/daily/daily_report_2026-05-11.md +++ /dev/null @@ -1,350 +0,0 @@ -# 🤖 LLM Intelligence Hub - 每日情报报告 - -**报告日期**: 2026-05-11 -**生成时间**: 2026-05-11T23:19:30+08:00 - -## 📊 数据质量摘要 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 501 | -| 数据新鲜 | 458 | -| CNY定价 | 126 | -| USD定价 | 375 | -| 厂商总数 | 81 | - -## 🆓 免费模型(共 372 个) - -**按国家分布**: US 145个, 国际 143个, CN 84个 - -**代表性模型(前20个)**: - -| 模型 | 厂商 | 国家 | 上下文 | -|------|------|------|--------| -| Auto Router | OpenRouter | US | 2000000 | -| xAI: Grok 4.20 | xAI | US | 2000000 | -| xAI: Grok 4.20 Multi-Agent | xAI | US | 2000000 | -| Pareto Code Router | OpenRouter | US | 2000000 | -| xAI: Grok 4 Fast | xAI | US | 2000000 | -| xAI: Grok 4.1 Fast | xAI | US | 2000000 | -| OpenAI: GPT-5.4 | OpenAI | US | 1050000 | -| OpenAI: GPT-5.4 Pro | OpenAI | US | 1050000 | -| OpenAI: GPT-5.5 | OpenAI | US | 1050000 | -| OpenAI: GPT-5.5 Pro | OpenAI | US | 1050000 | -| OpenAI GPT Latest | ~openai | 国际 | 1050000 | -| Owl Alpha | OpenRouter | US | 1048756 | -| Google: Gemini 2.5 Flash Lite | Google | US | 1048576 | -| DeepSeek: DeepSeek V4 Flash | DeepSeek | CN | 1048576 | -| Google: Gemini 3.1 Pro Preview | Google | US | 1048576 | -| Google: Gemini 3.1 Pro Preview Custom Tools | Google | US | 1048576 | -| Google: Gemini 2.0 Flash Lite | Google | US | 1048576 | -| Google: Gemini 2.5 Pro Preview 05-06 | Google | US | 1048576 | -| Google Gemini Pro Latest | ~google | 国际 | 1048576 | -| Google: Gemini 2.5 Pro Preview 06-05 | Google | US | 1048576 | -| ... | ... | ... | ... | - -> 共 372 个免费模型,以上为前20个代表性模型 - -## 🌍 国际推荐模型 TOP 5 - -| 排名 | 模型 | 厂商 | 场景 | 输入(原价) | 输出(原价) | 上下文 | -|------|------|------|------|-----------|-----------|--------| -| 1 | Qwen3-VL-8B | Alibaba | 视觉 | ¥0.20 | ¥0.50 | 32000 | -| 2 | Qwen3-VL-32B | Alibaba | 视觉 | ¥0.50 | ¥1.00 | 32000 | -| 3 | GPT-5.4 Mini | OpenAI | 对话 | $0.75 | $4.50 | 200000 | -| 4 | Doubao-Pro | ByteDance | 视觉 | ¥0.80 | ¥2.00 | 32000 | -| 5 | DeepSeek-V3 | DeepSeek | 对话 | ¥1.00 | ¥2.00 | 64000 | - -## 🇨🇳 国内模型 TOP 10 - -| 排名 | 模型 | 厂商 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|------|------|-----------|-----------|--------| -| 1 | DeepSeek V4 Flash | DeepSeek | 对话 | ¥1.02 | ¥2.03 | 1000000 | -| 2 | doubao-seed-1.6-flash | ByteDance | 对话 | ¥0.15 | ¥0.30 | 32000 | -| 3 | GLM-4.6V-FlashX | Zhipu AI | 视觉 | ¥0.15 | ¥1.50 | 8000 | -| 4 | GLM-Realtime-Flash | Zhipu AI | 对话 | ¥0.18 | ¥0.18 | 8000 | -| 5 | doubao-seed-2.0-mini | ByteDance | 对话 | ¥0.20 | ¥0.40 | 32000 | -| 6 | doubao-seed-1.6-lite | ByteDance | 对话 | ¥0.30 | ¥0.60 | 32000 | -| 7 | doubao-seed-1.6-flash-128k | ByteDance | 对话 | ¥0.30 | ¥0.60 | 128000 | -| 8 | GLM-Realtime-Air | Zhipu AI | 对话 | ¥0.30 | ¥0.30 | 8000 | -| 9 | doubao-1.5-lite-32k | ByteDance | 对话 | ¥0.30 | ¥0.60 | 32000 | -| 10 | doubao-seed-2.0-mini-128k | ByteDance | 对话 | ¥0.40 | ¥0.80 | 128000 | -| 11 | DeepSeek V4 Pro | DeepSeek | 对话 | ¥3.15 | ¥6.31 | 1000000 | -| 12 | GLM-4.7-FlashX | Zhipu AI | 对话 | ¥0.50 | ¥3.00 | 200000 | -| 13 | GLM-4-Air | Zhipu AI | 对话 | ¥0.50 | ¥0.25 | 128000 | -| 14 | doubao-seed-1.6-lite-128k | ByteDance | 对话 | ¥0.60 | ¥1.20 | 128000 | -| 15 | doubao-seed-1.6-flash-256k | ByteDance | 对话 | ¥0.60 | ¥1.20 | 256000 | -| 16 | doubao-seed-2.0-lite | ByteDance | 对话 | ¥0.60 | ¥1.20 | 32000 | -| 17 | doubao-seed-character | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 18 | doubao-seed-1.8 | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 19 | doubao-seed-1.6 | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 20 | GLM-4.5-Air | Zhipu AI | 对话 | ¥0.80 | ¥2.00 | 32000 | -| 21 | doubao-pro-32k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 22 | doubao-seed-1.6-vision | ByteDance | 视觉 | ¥0.80 | ¥1.60 | 32000 | -| 23 | doubao-1.5-pro-32k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 24 | doubao-seed-2.0-mini-256k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 256000 | -| 25 | doubao-seed-2.0-lite-128k | ByteDance | 对话 | ¥0.90 | ¥1.80 | 128000 | -| 26 | GLM-4-Long | Zhipu AI | 对话 | ¥1.00 | ¥0.50 | 1000000 | -| 27 | doubao-seed-1.8-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 28 | GLM-4.5-Air (32K+) | Zhipu AI | 对话 | ¥1.20 | ¥8.00 | 128000 | -| 29 | doubao-seed-code | ByteDance | 代码 | ¥1.20 | ¥2.40 | 32000 | -| 30 | doubao-seed-1.6-vision-128k | ByteDance | 视觉 | ¥1.20 | ¥2.40 | 128000 | -| 31 | doubao-seed-1.6-lite-256k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 256000 | -| 32 | doubao-seed-1.6-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 33 | doubao-seed-character-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 34 | doubao-seed-code-128k | ByteDance | 代码 | ¥1.40 | ¥2.80 | 128000 | -| 35 | doubao-seed-2.0-lite-256k | ByteDance | 对话 | ¥1.80 | ¥3.60 | 256000 | -| 36 | deepseek-v3 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 37 | GLM-4.7 | Zhipu AI | 对话 | ¥2.00 | ¥8.00 | 32000 | -| 38 | GLM-4.5V | Zhipu AI | 视觉 | ¥2.00 | ¥6.00 | 32000 | -| 39 | GLM-4.6V | Zhipu AI | 视觉 | ¥2.00 | ¥6.00 | 8000 | -| 40 | Moonshot V1 8K | Moonshot AI | 对话 | ¥2.00 | ¥10.00 | 8192 | -| 41 | deepseek-v3.2 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 42 | GLM-TTS | Zhipu AI | 对话 | ¥2.00 | 免费 | 8000 | -| 43 | glm-4.7 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 44 | doubao-seed-1.6-vision-256k | ByteDance | 视觉 | ¥2.40 | ¥4.80 | 256000 | -| 45 | doubao-seed-1.8-256k | ByteDance | 对话 | ¥2.40 | ¥4.80 | 256000 | -| 46 | doubao-seed-1.6-256k | ByteDance | 对话 | ¥2.40 | ¥4.80 | 256000 | -| 47 | doubao-seed-code-256k | ByteDance | 代码 | ¥2.80 | ¥5.60 | 256000 | -| 48 | doubao-1.5-vision-pro | ByteDance | 视觉 | ¥3.00 | ¥6.00 | 32000 | -| 49 | doubao-seed-2.0-code | ByteDance | 代码 | ¥3.20 | ¥6.40 | 32000 | -| 50 | doubao-seed-2.0-pro | ByteDance | 对话 | ¥3.20 | ¥6.40 | 32000 | -| 51 | deepseek-v3.1 | ByteDance | 对话 | ¥4.00 | ¥8.00 | 32000 | -| 52 | Kimi K2 0905 Preview | Moonshot AI | 对话 | ¥4.00 | ¥16.00 | 262144 | -| 53 | glm-4.7-128k | ByteDance | 对话 | ¥4.00 | ¥8.00 | 128000 | -| 54 | GLM-5 | Zhipu AI | 对话 | ¥4.00 | ¥18.00 | 32000 | -| 55 | deepseek-v3.2-128k | ByteDance | 对话 | ¥4.00 | ¥8.00 | 128000 | -| 56 | GLM-4.7 (32K+) | Zhipu AI | 对话 | ¥4.00 | ¥16.00 | 200000 | -| 57 | deepseek-r1 | ByteDance | 推理 | ¥4.00 | ¥8.00 | 32000 | -| 58 | GLM-4V-Plus | Zhipu AI | 视觉 | ¥4.00 | ¥4.00 | 8000 | -| 59 | doubao-seed-2.0-code-128k | ByteDance | 代码 | ¥4.80 | ¥9.60 | 128000 | -| 60 | doubao-seed-2.0-pro-128k | ByteDance | 对话 | ¥4.80 | ¥9.60 | 128000 | -| 61 | GLM-5-Turbo | Zhipu AI | 对话 | ¥5.00 | ¥22.00 | 32000 | -| 62 | GLM-TTS-Clone | Zhipu AI | 对话 | ¥6.00 | 免费 | 8000 | -| 63 | GLM-5 (32K+) | Zhipu AI | 对话 | ¥6.00 | ¥22.00 | 200000 | -| 64 | GLM-5.1 | Zhipu AI | 对话 | ¥6.00 | ¥24.00 | 32000 | -| 65 | Kimi K2.6 | Moonshot AI | 视觉 | ¥6.50 | ¥27.00 | 262144 | -| 66 | GLM-5-Turbo (32K+) | Zhipu AI | 对话 | ¥7.00 | ¥26.00 | 200000 | -| 67 | GLM-5.1 (32K+) | Zhipu AI | 对话 | ¥8.00 | ¥28.00 | 200000 | -| 68 | doubao-seed-2.0-code-256k | ByteDance | 代码 | ¥9.60 | ¥19.20 | 256000 | -| 69 | doubao-seed-2.0-pro-256k | ByteDance | 对话 | ¥9.60 | ¥19.20 | 256000 | -| 70 | GLM-4-AirX | Zhipu AI | 对话 | ¥10.00 | ¥10.00 | 8000 | -| 71 | GLM-ASR-2512 | Zhipu AI | 对话 | ¥16.00 | 免费 | 8000 | -| 72 | ERNIE 5.1 | Baidu | 对话 | ¥22.00 | ¥22.00 | 0 | -| 73 | ERNIE 5.0 | Baidu | 对话 | ¥40.00 | ¥40.00 | 0 | -| 74 | GLM-4V | Zhipu AI | 视觉 | ¥50.00 | ¥50.00 | 2000 | -| 75 | GLM-4-Voice | Zhipu AI | 对话 | ¥80.00 | ¥80.00 | 8000 | -| 76 | GLM-4-0520 | Zhipu AI | 对话 | ¥100.00 | ¥50.00 | 128000 | - -## 📊 模型分类概览 - -### 🇨🇳 国内官方平台模型 - -**DeepSeek** (2个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| DeepSeek V4 Flash | 对话 | ¥1.02 | ¥2.03 | 1000000 | -| DeepSeek V4 Pro | 对话 | ¥3.15 | ¥6.31 | 1000000 | - -**ByteDance Volcano** (43个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| doubao-seed-1.6-flash | 对话 | ¥0.15 | ¥0.30 | 32000 | -| doubao-seed-2.0-mini | 对话 | ¥0.20 | ¥0.40 | 32000 | -| doubao-seed-1.6-lite | 对话 | ¥0.30 | ¥0.60 | 32000 | -| doubao-seed-1.6-flash-128k | 对话 | ¥0.30 | ¥0.60 | 128000 | -| doubao-1.5-lite-32k | 对话 | ¥0.30 | ¥0.60 | 32000 | -| doubao-seed-2.0-mini-128k | 对话 | ¥0.40 | ¥0.80 | 128000 | -| doubao-seed-1.6-lite-128k | 对话 | ¥0.60 | ¥1.20 | 128000 | -| doubao-seed-1.6-flash-256k | 对话 | ¥0.60 | ¥1.20 | 256000 | -| doubao-seed-2.0-lite | 对话 | ¥0.60 | ¥1.20 | 32000 | -| doubao-seed-character | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.8 | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.6 | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-pro-32k | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.6-vision | 视觉 | ¥0.80 | ¥1.60 | 32000 | -| doubao-1.5-pro-32k | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-2.0-mini-256k | 对话 | ¥0.80 | ¥1.60 | 256000 | -| doubao-seed-2.0-lite-128k | 对话 | ¥0.90 | ¥1.80 | 128000 | -| doubao-seed-1.8-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-code | 代码 | ¥1.20 | ¥2.40 | 32000 | -| doubao-seed-1.6-vision-128k | 视觉 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-1.6-lite-256k | 对话 | ¥1.20 | ¥2.40 | 256000 | -| doubao-seed-1.6-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-character-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-code-128k | 代码 | ¥1.40 | ¥2.80 | 128000 | -| doubao-seed-2.0-lite-256k | 对话 | ¥1.80 | ¥3.60 | 256000 | -| deepseek-v3 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| deepseek-v3.2 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| glm-4.7 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| doubao-seed-1.6-vision-256k | 视觉 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-1.8-256k | 对话 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-1.6-256k | 对话 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-code-256k | 代码 | ¥2.80 | ¥5.60 | 256000 | -| doubao-1.5-vision-pro | 视觉 | ¥3.00 | ¥6.00 | 32000 | -| doubao-seed-2.0-code | 代码 | ¥3.20 | ¥6.40 | 32000 | -| doubao-seed-2.0-pro | 对话 | ¥3.20 | ¥6.40 | 32000 | -| deepseek-v3.1 | 对话 | ¥4.00 | ¥8.00 | 32000 | -| glm-4.7-128k | 对话 | ¥4.00 | ¥8.00 | 128000 | -| deepseek-v3.2-128k | 对话 | ¥4.00 | ¥8.00 | 128000 | -| deepseek-r1 | 推理 | ¥4.00 | ¥8.00 | 32000 | -| doubao-seed-2.0-code-128k | 代码 | ¥4.80 | ¥9.60 | 128000 | -| doubao-seed-2.0-pro-128k | 对话 | ¥4.80 | ¥9.60 | 128000 | -| doubao-seed-2.0-code-256k | 代码 | ¥9.60 | ¥19.20 | 256000 | -| doubao-seed-2.0-pro-256k | 对话 | ¥9.60 | ¥19.20 | 256000 | - -**Zhipu** (26个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| GLM-4.6V-FlashX | 视觉 | ¥0.15 | ¥1.50 | 8000 | -| GLM-Realtime-Flash | 对话 | ¥0.18 | ¥0.18 | 8000 | -| GLM-Realtime-Air | 对话 | ¥0.30 | ¥0.30 | 8000 | -| GLM-4.7-FlashX | 对话 | ¥0.50 | ¥3.00 | 200000 | -| GLM-4-Air | 对话 | ¥0.50 | ¥0.25 | 128000 | -| GLM-4.5-Air | 对话 | ¥0.80 | ¥2.00 | 32000 | -| GLM-4-Long | 对话 | ¥1.00 | ¥0.50 | 1000000 | -| GLM-4.5-Air (32K+) | 对话 | ¥1.20 | ¥8.00 | 128000 | -| GLM-4.7 | 对话 | ¥2.00 | ¥8.00 | 32000 | -| GLM-4.5V | 视觉 | ¥2.00 | ¥6.00 | 32000 | -| GLM-4.6V | 视觉 | ¥2.00 | ¥6.00 | 8000 | -| GLM-TTS | 对话 | ¥2.00 | 免费 | 8000 | -| GLM-5 | 对话 | ¥4.00 | ¥18.00 | 32000 | -| GLM-4.7 (32K+) | 对话 | ¥4.00 | ¥16.00 | 200000 | -| GLM-4V-Plus | 视觉 | ¥4.00 | ¥4.00 | 8000 | -| GLM-5-Turbo | 对话 | ¥5.00 | ¥22.00 | 32000 | -| GLM-TTS-Clone | 对话 | ¥6.00 | 免费 | 8000 | -| GLM-5 (32K+) | 对话 | ¥6.00 | ¥22.00 | 200000 | -| GLM-5.1 | 对话 | ¥6.00 | ¥24.00 | 32000 | -| GLM-5-Turbo (32K+) | 对话 | ¥7.00 | ¥26.00 | 200000 | -| GLM-5.1 (32K+) | 对话 | ¥8.00 | ¥28.00 | 200000 | -| GLM-4-AirX | 对话 | ¥10.00 | ¥10.00 | 8000 | -| GLM-ASR-2512 | 对话 | ¥16.00 | 免费 | 8000 | -| GLM-4V | 视觉 | ¥50.00 | ¥50.00 | 2000 | -| GLM-4-Voice | 对话 | ¥80.00 | ¥80.00 | 8000 | -| GLM-4-0520 | 对话 | ¥100.00 | ¥50.00 | 128000 | - -**Moonshot** (3个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| Moonshot V1 8K | 对话 | ¥2.00 | ¥10.00 | 8192 | -| Kimi K2 0905 Preview | 对话 | ¥4.00 | ¥16.00 | 262144 | -| Kimi K2.6 | 视觉 | ¥6.50 | ¥27.00 | 262144 | - -**Baidu Qianfan** (2个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| ERNIE 5.1 | 对话 | ¥22.00 | ¥22.00 | 0 | -| ERNIE 5.0 | 对话 | ¥40.00 | ¥40.00 | 0 | - -### 💻 代码模型(19个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Pareto Code Router | OpenRouter | 免费 | 免费 | -| Qwen: Qwen3 Coder Flash | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder Plus | Qwen | 免费 | 免费 | -| OpenAI: GPT-5 Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex-Max | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.2-Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.3-Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex-Mini | OpenAI | 免费 | 免费 | -| Qwen: Qwen3 Coder Next | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder 480B A35B | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder 480B A35B... | Qwen | 免费 | 免费 | -| Kwaipilot: KAT-Coder-Pro V2 | kwaipilot | 免费 | 免费 | -| xAI: Grok Code Fast 1 | xAI | 免费 | 免费 | -| Mistral: Codestral 2508 | mistralai | 免费 | 免费 | -| Qwen: Qwen3 Coder 30B A3B I... | Qwen | 免费 | 免费 | -| Qwen2.5 Coder 32B Instruct | Qwen | 免费 | 免费 | -| Arcee AI: Coder Large | arcee-ai | 免费 | 免费 | -| AlfredPros: CodeLLaMa 7B In... | alfredpros | 免费 | 免费 | - -### 🧠 推理模型(34个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Qwen: Qwen Plus 0728 (think... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Max Thinking | Qwen | 免费 | 免费 | -| MoonshotAI: Kimi K2 Thinking | Moonshot AI | 免费 | 免费 | -| Arcee AI: Trinity Large Thi... | arcee-ai | 免费 | 免费 | -| OpenAI: o3 Mini High | OpenAI | 免费 | 免费 | -| OpenAI: o3 Deep Research | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini Deep Research | OpenAI | 免费 | 免费 | -| OpenAI: o1 | OpenAI | 免费 | 免费 | -| OpenAI: o3 Mini | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini High | OpenAI | 免费 | 免费 | -| Anthropic: Claude 3.7 Sonne... | Anthropic | 免费 | 免费 | -| OpenAI: o3 Pro | OpenAI | 免费 | 免费 | -| OpenAI: o1-pro | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini | OpenAI | 免费 | 免费 | -| OpenAI: o3 | OpenAI | 免费 | 免费 | -| DeepSeek: R1 0528 | DeepSeek | 免费 | 免费 | -| Qwen: Qwen3 VL 235B A22B Th... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Thinking | Qwen | 免费 | 免费 | -| Sao10K: Llama 3.1 Euryale 7... | sao10k | 免费 | 免费 | -| Qwen: Qwen3 30B A3B Thinkin... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 235B A22B Think... | Qwen | 免费 | 免费 | -| Baidu: ERNIE 4.5 21B A3B Th... | Baidu | 免费 | 免费 | -| Sao10K: Llama 3.3 Euryale 70B | sao10k | 免费 | 免费 | -| DeepSeek: R1 Distill Llama 70B | DeepSeek | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Thin... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Next 80B A3B Th... | Qwen | 免费 | 免费 | -| Arcee AI: Maestro Reasoning | arcee-ai | 免费 | 免费 | -| Perplexity: Sonar Reasoning... | Perplexity | 免费 | 免费 | -| DeepSeek: R1 | DeepSeek | 免费 | 免费 | -| LiquidAI: LFM2.5-1.2B-Think... | liquid | 免费 | 免费 | -| DeepSeek: R1 Distill Qwen 32B | DeepSeek | 免费 | 免费 | -| Sao10K: Llama 3.1 70B Hanam... | sao10k | 免费 | 免费 | -| Sao10K: Llama 3 8B Lunaris | sao10k | 免费 | 免费 | -| Sao10k: Llama 3 Euryale 70B... | sao10k | 免费 | 免费 | - -### 👁️ 视觉/多模态模型(15个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Qwen: Qwen3 VL 235B A22B In... | Qwen | 免费 | 免费 | -| MoonshotAI: Kimi K2.6 | Moonshot AI | 免费 | 免费 | -| Qwen: Qwen3 VL 235B A22B Th... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Thinking | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Instruct | Qwen | 免费 | 免费 | -| Meta: Llama 3.2 11B Vision ... | meta-llama | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Thin... | Qwen | 免费 | 免费 | -| Qwen: Qwen VL Max | Qwen | 免费 | 免费 | -| Qwen: Qwen VL Plus | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Inst... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 32B Instruct | Qwen | 免费 | 免费 | -| NVIDIA: Nemotron Nano 12B 2... | NVIDIA | 免费 | 免费 | -| Baidu: ERNIE 4.5 VL 424B A47B | Baidu | 免费 | 免费 | -| Qwen: Qwen2.5 VL 72B Instruct | Qwen | 免费 | 免费 | -| Baidu: ERNIE 4.5 VL 28B A3B | Baidu | 免费 | 免费 | - -## 🇨🇳 国内官方平台(5 家) - -- **Moonshot**: 3 个模型,最低 ¥2.00/MTok -- **DeepSeek**: 2 个模型,最低 ¥0.14/MTok -- **Baidu Qianfan**: 44 个模型,最低 ¥0.00/MTok -- **Zhipu**: 29 个模型,最低 ¥0.18/MTok -- **ByteDance Volcano**: 43 个模型,最低 ¥0.15/MTok - -## ☁️ 国际官方平台(1 家) - -- **OpenAI**: 3 个模型,最低 $0.75/MTok - -## 🔀 中转/聚合平台(1 家) - -- **OpenRouter**: 377 个模型,最低 $0.00/MTok - ---- - -📌 **说明**: 本报告由 LLM Intelligence Hub 自动生成。 -- 国际模型价格按 1 USD = 7.25 CNY 换算显示，括号内为原生货币价格 -- 国内模型价格为厂商原生 CNY 定价 -- 数据来源: OpenRouter API + 智谱AI + 百度千帆 + Moonshot + DeepSeek + OpenAI - -_生成时间: 2026-05-11T23:19:30+08:00_ diff --git a/reports/daily/daily_report_2026-05-12.md b/reports/daily/daily_report_2026-05-12.md deleted file mode 100644 index 7ca466e..0000000 --- a/reports/daily/daily_report_2026-05-12.md +++ /dev/null @@ -1,351 +0,0 @@ -# 🤖 LLM Intelligence Hub - 每日情报报告 - -**报告日期**: 2026-05-12 -**生成时间**: 2026-05-12T22:48:17+08:00 - -## 📊 数据质量摘要 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 502 | -| 数据新鲜 | 459 | -| CNY定价 | 126 | -| USD定价 | 376 | -| 厂商总数 | 81 | - -## 🆓 免费模型(共 373 个) - -**按国家分布**: US 145个, 国际 144个, CN 84个 - -**代表性模型(前20个)**: - -| 模型 | 厂商 | 国家 | 上下文 | -|------|------|------|--------| -| Pareto Code Router | OpenRouter | US | 2000000 | -| Auto Router | OpenRouter | US | 2000000 | -| xAI: Grok 4.20 | xAI | US | 2000000 | -| xAI: Grok 4 Fast | xAI | US | 2000000 | -| xAI: Grok 4.1 Fast | xAI | US | 2000000 | -| xAI: Grok 4.20 Multi-Agent | xAI | US | 2000000 | -| OpenAI: GPT-5.5 | OpenAI | US | 1050000 | -| OpenAI: GPT-5.5 Pro | OpenAI | US | 1050000 | -| OpenAI GPT Latest | ~openai | 国际 | 1050000 | -| OpenAI: GPT-5.4 Pro | OpenAI | US | 1050000 | -| OpenAI: GPT-5.4 | OpenAI | US | 1050000 | -| Owl Alpha | OpenRouter | US | 1048756 | -| DeepSeek: DeepSeek V4 Pro | DeepSeek | CN | 1048576 | -| Google: Gemini 2.5 Flash Lite | Google | US | 1048576 | -| Google: Gemini 3.1 Pro Preview | Google | US | 1048576 | -| Google: Gemini 2.0 Flash | Google | US | 1048576 | -| Google: Gemini 2.0 Flash Lite | Google | US | 1048576 | -| Google: Gemini 2.5 Flash Lite Preview 09-2025 | Google | US | 1048576 | -| Google Gemini Pro Latest | ~google | 国际 | 1048576 | -| Google: Gemini 2.5 Pro Preview 06-05 | Google | US | 1048576 | -| ... | ... | ... | ... | - -> 共 373 个免费模型,以上为前20个代表性模型 - -## 🌍 国际推荐模型 TOP 5 - -| 排名 | 模型 | 厂商 | 场景 | 输入(原价) | 输出(原价) | 上下文 | -|------|------|------|------|-----------|-----------|--------| -| 1 | Qwen3-VL-8B | Alibaba | 视觉 | ¥0.20 | ¥0.50 | 32000 | -| 2 | Qwen3-VL-32B | Alibaba | 视觉 | ¥0.50 | ¥1.00 | 32000 | -| 3 | GPT-5.4 Mini | OpenAI | 对话 | $0.75 | $4.50 | 200000 | -| 4 | Doubao-Pro | ByteDance | 视觉 | ¥0.80 | ¥2.00 | 32000 | -| 5 | DeepSeek-V3 | DeepSeek | 对话 | ¥1.00 | ¥2.00 | 64000 | - -## 🇨🇳 国内模型 TOP 10 - -| 排名 | 模型 | 厂商 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|------|------|-----------|-----------|--------| -| 1 | DeepSeek V4 Flash | DeepSeek | 对话 | ¥1.02 | ¥2.03 | 1000000 | -| 2 | doubao-seed-1.6-flash | ByteDance | 对话 | ¥0.15 | ¥0.30 | 32000 | -| 3 | GLM-4.6V-FlashX | Zhipu AI | 视觉 | ¥0.15 | ¥1.50 | 8000 | -| 4 | GLM-Realtime-Flash | Zhipu AI | 对话 | ¥0.18 | ¥0.18 | 8000 | -| 5 | doubao-seed-2.0-mini | ByteDance | 对话 | ¥0.20 | ¥0.40 | 32000 | -| 6 | doubao-seed-1.6-lite | ByteDance | 对话 | ¥0.30 | ¥0.60 | 32000 | -| 7 | doubao-seed-1.6-flash-128k | ByteDance | 对话 | ¥0.30 | ¥0.60 | 128000 | -| 8 | GLM-Realtime-Air | Zhipu AI | 对话 | ¥0.30 | ¥0.30 | 8000 | -| 9 | doubao-1.5-lite-32k | ByteDance | 对话 | ¥0.30 | ¥0.60 | 32000 | -| 10 | doubao-seed-2.0-mini-128k | ByteDance | 对话 | ¥0.40 | ¥0.80 | 128000 | -| 11 | DeepSeek V4 Pro | DeepSeek | 对话 | ¥3.15 | ¥6.31 | 1000000 | -| 12 | GLM-4.7-FlashX | Zhipu AI | 对话 | ¥0.50 | ¥3.00 | 200000 | -| 13 | GLM-4-Air | Zhipu AI | 对话 | ¥0.50 | ¥0.25 | 128000 | -| 14 | doubao-seed-1.6-lite-128k | ByteDance | 对话 | ¥0.60 | ¥1.20 | 128000 | -| 15 | doubao-seed-1.6-flash-256k | ByteDance | 对话 | ¥0.60 | ¥1.20 | 256000 | -| 16 | doubao-seed-2.0-lite | ByteDance | 对话 | ¥0.60 | ¥1.20 | 32000 | -| 17 | doubao-seed-character | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 18 | doubao-seed-1.8 | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 19 | doubao-seed-1.6 | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 20 | GLM-4.5-Air | Zhipu AI | 对话 | ¥0.80 | ¥2.00 | 32000 | -| 21 | doubao-pro-32k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 22 | doubao-seed-1.6-vision | ByteDance | 视觉 | ¥0.80 | ¥1.60 | 32000 | -| 23 | doubao-1.5-pro-32k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 24 | doubao-seed-2.0-mini-256k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 256000 | -| 25 | doubao-seed-2.0-lite-128k | ByteDance | 对话 | ¥0.90 | ¥1.80 | 128000 | -| 26 | GLM-4-Long | Zhipu AI | 对话 | ¥1.00 | ¥0.50 | 1000000 | -| 27 | doubao-seed-1.8-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 28 | GLM-4.5-Air (32K+) | Zhipu AI | 对话 | ¥1.20 | ¥8.00 | 128000 | -| 29 | doubao-seed-code | ByteDance | 代码 | ¥1.20 | ¥2.40 | 32000 | -| 30 | doubao-seed-1.6-vision-128k | ByteDance | 视觉 | ¥1.20 | ¥2.40 | 128000 | -| 31 | doubao-seed-1.6-lite-256k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 256000 | -| 32 | doubao-seed-1.6-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 33 | doubao-seed-character-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 34 | doubao-seed-code-128k | ByteDance | 代码 | ¥1.40 | ¥2.80 | 128000 | -| 35 | doubao-seed-2.0-lite-256k | ByteDance | 对话 | ¥1.80 | ¥3.60 | 256000 | -| 36 | deepseek-v3 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 37 | GLM-4.7 | Zhipu AI | 对话 | ¥2.00 | ¥8.00 | 32000 | -| 38 | GLM-4.5V | Zhipu AI | 视觉 | ¥2.00 | ¥6.00 | 32000 | -| 39 | GLM-4.6V | Zhipu AI | 视觉 | ¥2.00 | ¥6.00 | 8000 | -| 40 | Moonshot V1 8K | Moonshot AI | 对话 | ¥2.00 | ¥10.00 | 8192 | -| 41 | deepseek-v3.2 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 42 | GLM-TTS | Zhipu AI | 对话 | ¥2.00 | 免费 | 8000 | -| 43 | glm-4.7 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 44 | doubao-seed-1.6-vision-256k | ByteDance | 视觉 | ¥2.40 | ¥4.80 | 256000 | -| 45 | doubao-seed-1.8-256k | ByteDance | 对话 | ¥2.40 | ¥4.80 | 256000 | -| 46 | doubao-seed-1.6-256k | ByteDance | 对话 | ¥2.40 | ¥4.80 | 256000 | -| 47 | doubao-seed-code-256k | ByteDance | 代码 | ¥2.80 | ¥5.60 | 256000 | -| 48 | doubao-1.5-vision-pro | ByteDance | 视觉 | ¥3.00 | ¥6.00 | 32000 | -| 49 | doubao-seed-2.0-code | ByteDance | 代码 | ¥3.20 | ¥6.40 | 32000 | -| 50 | doubao-seed-2.0-pro | ByteDance | 对话 | ¥3.20 | ¥6.40 | 32000 | -| 51 | deepseek-v3.1 | ByteDance | 对话 | ¥4.00 | ¥8.00 | 32000 | -| 52 | Kimi K2 0905 Preview | Moonshot AI | 对话 | ¥4.00 | ¥16.00 | 262144 | -| 53 | glm-4.7-128k | ByteDance | 对话 | ¥4.00 | ¥8.00 | 128000 | -| 54 | GLM-5 | Zhipu AI | 对话 | ¥4.00 | ¥18.00 | 32000 | -| 55 | deepseek-v3.2-128k | ByteDance | 对话 | ¥4.00 | ¥8.00 | 128000 | -| 56 | GLM-4.7 (32K+) | Zhipu AI | 对话 | ¥4.00 | ¥16.00 | 200000 | -| 57 | deepseek-r1 | ByteDance | 推理 | ¥4.00 | ¥8.00 | 32000 | -| 58 | GLM-4V-Plus | Zhipu AI | 视觉 | ¥4.00 | ¥4.00 | 8000 | -| 59 | doubao-seed-2.0-code-128k | ByteDance | 代码 | ¥4.80 | ¥9.60 | 128000 | -| 60 | doubao-seed-2.0-pro-128k | ByteDance | 对话 | ¥4.80 | ¥9.60 | 128000 | -| 61 | GLM-5-Turbo | Zhipu AI | 对话 | ¥5.00 | ¥22.00 | 32000 | -| 62 | GLM-TTS-Clone | Zhipu AI | 对话 | ¥6.00 | 免费 | 8000 | -| 63 | GLM-5 (32K+) | Zhipu AI | 对话 | ¥6.00 | ¥22.00 | 200000 | -| 64 | GLM-5.1 | Zhipu AI | 对话 | ¥6.00 | ¥24.00 | 32000 | -| 65 | Kimi K2.6 | Moonshot AI | 视觉 | ¥6.50 | ¥27.00 | 262144 | -| 66 | GLM-5-Turbo (32K+) | Zhipu AI | 对话 | ¥7.00 | ¥26.00 | 200000 | -| 67 | GLM-5.1 (32K+) | Zhipu AI | 对话 | ¥8.00 | ¥28.00 | 200000 | -| 68 | doubao-seed-2.0-code-256k | ByteDance | 代码 | ¥9.60 | ¥19.20 | 256000 | -| 69 | doubao-seed-2.0-pro-256k | ByteDance | 对话 | ¥9.60 | ¥19.20 | 256000 | -| 70 | GLM-4-AirX | Zhipu AI | 对话 | ¥10.00 | ¥10.00 | 8000 | -| 71 | GLM-ASR-2512 | Zhipu AI | 对话 | ¥16.00 | 免费 | 8000 | -| 72 | ERNIE 5.1 | Baidu | 对话 | ¥22.00 | ¥22.00 | 0 | -| 73 | ERNIE 5.0 | Baidu | 对话 | ¥40.00 | ¥40.00 | 0 | -| 74 | GLM-4V | Zhipu AI | 视觉 | ¥50.00 | ¥50.00 | 2000 | -| 75 | GLM-4-Voice | Zhipu AI | 对话 | ¥80.00 | ¥80.00 | 8000 | -| 76 | GLM-4-0520 | Zhipu AI | 对话 | ¥100.00 | ¥50.00 | 128000 | - -## 📊 模型分类概览 - -### 🇨🇳 国内官方平台模型 - -**ByteDance Volcano** (43个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| doubao-seed-1.6-flash | 对话 | ¥0.15 | ¥0.30 | 32000 | -| doubao-seed-2.0-mini | 对话 | ¥0.20 | ¥0.40 | 32000 | -| doubao-seed-1.6-lite | 对话 | ¥0.30 | ¥0.60 | 32000 | -| doubao-seed-1.6-flash-128k | 对话 | ¥0.30 | ¥0.60 | 128000 | -| doubao-1.5-lite-32k | 对话 | ¥0.30 | ¥0.60 | 32000 | -| doubao-seed-2.0-mini-128k | 对话 | ¥0.40 | ¥0.80 | 128000 | -| doubao-seed-1.6-lite-128k | 对话 | ¥0.60 | ¥1.20 | 128000 | -| doubao-seed-1.6-flash-256k | 对话 | ¥0.60 | ¥1.20 | 256000 | -| doubao-seed-2.0-lite | 对话 | ¥0.60 | ¥1.20 | 32000 | -| doubao-seed-character | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.8 | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.6 | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-pro-32k | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.6-vision | 视觉 | ¥0.80 | ¥1.60 | 32000 | -| doubao-1.5-pro-32k | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-2.0-mini-256k | 对话 | ¥0.80 | ¥1.60 | 256000 | -| doubao-seed-2.0-lite-128k | 对话 | ¥0.90 | ¥1.80 | 128000 | -| doubao-seed-1.8-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-code | 代码 | ¥1.20 | ¥2.40 | 32000 | -| doubao-seed-1.6-vision-128k | 视觉 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-1.6-lite-256k | 对话 | ¥1.20 | ¥2.40 | 256000 | -| doubao-seed-1.6-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-character-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-code-128k | 代码 | ¥1.40 | ¥2.80 | 128000 | -| doubao-seed-2.0-lite-256k | 对话 | ¥1.80 | ¥3.60 | 256000 | -| deepseek-v3 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| deepseek-v3.2 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| glm-4.7 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| doubao-seed-1.6-vision-256k | 视觉 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-1.8-256k | 对话 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-1.6-256k | 对话 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-code-256k | 代码 | ¥2.80 | ¥5.60 | 256000 | -| doubao-1.5-vision-pro | 视觉 | ¥3.00 | ¥6.00 | 32000 | -| doubao-seed-2.0-code | 代码 | ¥3.20 | ¥6.40 | 32000 | -| doubao-seed-2.0-pro | 对话 | ¥3.20 | ¥6.40 | 32000 | -| deepseek-v3.1 | 对话 | ¥4.00 | ¥8.00 | 32000 | -| glm-4.7-128k | 对话 | ¥4.00 | ¥8.00 | 128000 | -| deepseek-v3.2-128k | 对话 | ¥4.00 | ¥8.00 | 128000 | -| deepseek-r1 | 推理 | ¥4.00 | ¥8.00 | 32000 | -| doubao-seed-2.0-code-128k | 代码 | ¥4.80 | ¥9.60 | 128000 | -| doubao-seed-2.0-pro-128k | 对话 | ¥4.80 | ¥9.60 | 128000 | -| doubao-seed-2.0-code-256k | 代码 | ¥9.60 | ¥19.20 | 256000 | -| doubao-seed-2.0-pro-256k | 对话 | ¥9.60 | ¥19.20 | 256000 | - -**Zhipu** (26个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| GLM-4.6V-FlashX | 视觉 | ¥0.15 | ¥1.50 | 8000 | -| GLM-Realtime-Flash | 对话 | ¥0.18 | ¥0.18 | 8000 | -| GLM-Realtime-Air | 对话 | ¥0.30 | ¥0.30 | 8000 | -| GLM-4.7-FlashX | 对话 | ¥0.50 | ¥3.00 | 200000 | -| GLM-4-Air | 对话 | ¥0.50 | ¥0.25 | 128000 | -| GLM-4.5-Air | 对话 | ¥0.80 | ¥2.00 | 32000 | -| GLM-4-Long | 对话 | ¥1.00 | ¥0.50 | 1000000 | -| GLM-4.5-Air (32K+) | 对话 | ¥1.20 | ¥8.00 | 128000 | -| GLM-4.7 | 对话 | ¥2.00 | ¥8.00 | 32000 | -| GLM-4.5V | 视觉 | ¥2.00 | ¥6.00 | 32000 | -| GLM-4.6V | 视觉 | ¥2.00 | ¥6.00 | 8000 | -| GLM-TTS | 对话 | ¥2.00 | 免费 | 8000 | -| GLM-5 | 对话 | ¥4.00 | ¥18.00 | 32000 | -| GLM-4.7 (32K+) | 对话 | ¥4.00 | ¥16.00 | 200000 | -| GLM-4V-Plus | 视觉 | ¥4.00 | ¥4.00 | 8000 | -| GLM-5-Turbo | 对话 | ¥5.00 | ¥22.00 | 32000 | -| GLM-TTS-Clone | 对话 | ¥6.00 | 免费 | 8000 | -| GLM-5 (32K+) | 对话 | ¥6.00 | ¥22.00 | 200000 | -| GLM-5.1 | 对话 | ¥6.00 | ¥24.00 | 32000 | -| GLM-5-Turbo (32K+) | 对话 | ¥7.00 | ¥26.00 | 200000 | -| GLM-5.1 (32K+) | 对话 | ¥8.00 | ¥28.00 | 200000 | -| GLM-4-AirX | 对话 | ¥10.00 | ¥10.00 | 8000 | -| GLM-ASR-2512 | 对话 | ¥16.00 | 免费 | 8000 | -| GLM-4V | 视觉 | ¥50.00 | ¥50.00 | 2000 | -| GLM-4-Voice | 对话 | ¥80.00 | ¥80.00 | 8000 | -| GLM-4-0520 | 对话 | ¥100.00 | ¥50.00 | 128000 | - -**Moonshot** (3个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| Moonshot V1 8K | 对话 | ¥2.00 | ¥10.00 | 8192 | -| Kimi K2 0905 Preview | 对话 | ¥4.00 | ¥16.00 | 262144 | -| Kimi K2.6 | 视觉 | ¥6.50 | ¥27.00 | 262144 | - -**Baidu Qianfan** (2个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| ERNIE 5.1 | 对话 | ¥22.00 | ¥22.00 | 0 | -| ERNIE 5.0 | 对话 | ¥40.00 | ¥40.00 | 0 | - -**DeepSeek** (2个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| DeepSeek V4 Flash | 对话 | ¥1.02 | ¥2.03 | 1000000 | -| DeepSeek V4 Pro | 对话 | ¥3.15 | ¥6.31 | 1000000 | - -### 💻 代码模型(19个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Pareto Code Router | OpenRouter | 免费 | 免费 | -| Qwen: Qwen3 Coder Flash | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder Plus | Qwen | 免费 | 免费 | -| OpenAI: GPT-5 Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex-Max | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex-Mini | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.2-Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.3-Codex | OpenAI | 免费 | 免费 | -| Qwen: Qwen3 Coder Next | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder 480B A35B | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder 480B A35B... | Qwen | 免费 | 免费 | -| Mistral: Codestral 2508 | mistralai | 免费 | 免费 | -| Kwaipilot: KAT-Coder-Pro V2 | kwaipilot | 免费 | 免费 | -| xAI: Grok Code Fast 1 | xAI | 免费 | 免费 | -| Qwen: Qwen3 Coder 30B A3B I... | Qwen | 免费 | 免费 | -| Qwen2.5 Coder 32B Instruct | Qwen | 免费 | 免费 | -| Arcee AI: Coder Large | arcee-ai | 免费 | 免费 | -| AlfredPros: CodeLLaMa 7B In... | alfredpros | 免费 | 免费 | - -### 🧠 推理模型(35个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Qwen: Qwen Plus 0728 (think... | Qwen | 免费 | 免费 | -| Arcee AI: Trinity Large Thi... | arcee-ai | 免费 | 免费 | -| Qwen: Qwen3 Max Thinking | Qwen | 免费 | 免费 | -| MoonshotAI: Kimi K2 Thinking | Moonshot AI | 免费 | 免费 | -| Arcee AI: Trinity Large Thi... | arcee-ai | 免费 | 免费 | -| OpenAI: o3 Deep Research | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini Deep Research | OpenAI | 免费 | 免费 | -| OpenAI: o1 | OpenAI | 免费 | 免费 | -| OpenAI: o3 Mini | OpenAI | 免费 | 免费 | -| OpenAI: o3 Mini High | OpenAI | 免费 | 免费 | -| Anthropic: Claude 3.7 Sonne... | Anthropic | 免费 | 免费 | -| OpenAI: o3 Pro | OpenAI | 免费 | 免费 | -| OpenAI: o1-pro | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini High | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini | OpenAI | 免费 | 免费 | -| OpenAI: o3 | OpenAI | 免费 | 免费 | -| DeepSeek: R1 0528 | DeepSeek | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Thinking | Qwen | 免费 | 免费 | -| Sao10K: Llama 3.1 Euryale 7... | sao10k | 免费 | 免费 | -| Qwen: Qwen3 30B A3B Thinkin... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 235B A22B Think... | Qwen | 免费 | 免费 | -| Baidu: ERNIE 4.5 21B A3B Th... | Baidu | 免费 | 免费 | -| Sao10K: Llama 3.3 Euryale 70B | sao10k | 免费 | 免费 | -| DeepSeek: R1 Distill Llama 70B | DeepSeek | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Thin... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Next 80B A3B Th... | Qwen | 免费 | 免费 | -| Arcee AI: Maestro Reasoning | arcee-ai | 免费 | 免费 | -| Qwen: Qwen3 VL 235B A22B Th... | Qwen | 免费 | 免费 | -| Perplexity: Sonar Reasoning... | Perplexity | 免费 | 免费 | -| DeepSeek: R1 | DeepSeek | 免费 | 免费 | -| LiquidAI: LFM2.5-1.2B-Think... | liquid | 免费 | 免费 | -| DeepSeek: R1 Distill Qwen 32B | DeepSeek | 免费 | 免费 | -| Sao10K: Llama 3.1 70B Hanam... | sao10k | 免费 | 免费 | -| Sao10K: Llama 3 8B Lunaris | sao10k | 免费 | 免费 | -| Sao10k: Llama 3 Euryale 70B... | sao10k | 免费 | 免费 | - -### 👁️ 视觉/多模态模型(15个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Qwen: Qwen3 VL 235B A22B In... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 32B Instruct | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Thinking | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Instruct | Qwen | 免费 | 免费 | -| Meta: Llama 3.2 11B Vision ... | meta-llama | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Thin... | Qwen | 免费 | 免费 | -| Qwen: Qwen VL Max | Qwen | 免费 | 免费 | -| Qwen: Qwen VL Plus | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Inst... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 235B A22B Th... | Qwen | 免费 | 免费 | -| NVIDIA: Nemotron Nano 12B 2... | NVIDIA | 免费 | 免费 | -| Baidu: ERNIE 4.5 VL 424B A47B | Baidu | 免费 | 免费 | -| MoonshotAI: Kimi K2.6 | Moonshot AI | 免费 | 免费 | -| Qwen: Qwen2.5 VL 72B Instruct | Qwen | 免费 | 免费 | -| Baidu: ERNIE 4.5 VL 28B A3B | Baidu | 免费 | 免费 | - -## 🇨🇳 国内官方平台(5 家) - -- **Moonshot**: 3 个模型,最低 ¥2.00/MTok -- **DeepSeek**: 2 个模型,最低 ¥0.14/MTok -- **Baidu Qianfan**: 44 个模型,最低 ¥0.00/MTok -- **Zhipu**: 29 个模型,最低 ¥0.18/MTok -- **ByteDance Volcano**: 43 个模型,最低 ¥0.15/MTok - -## ☁️ 国际官方平台(1 家) - -- **OpenAI**: 3 个模型,最低 $0.75/MTok - -## 🔀 中转/聚合平台(1 家) - -- **OpenRouter**: 378 个模型,最低 $0.00/MTok - ---- - -📌 **说明**: 本报告由 LLM Intelligence Hub 自动生成。 -- 国际模型价格按 1 USD = 7.25 CNY 换算显示，括号内为原生货币价格 -- 国内模型价格为厂商原生 CNY 定价 -- 数据来源: OpenRouter API + 智谱AI + 百度千帆 + Moonshot + DeepSeek + OpenAI - -_生成时间: 2026-05-12T22:48:17+08:00_ diff --git a/reports/daily/daily_report_2026-05-13.md b/reports/daily/daily_report_2026-05-13.md deleted file mode 100644 index a7002bc..0000000 --- a/reports/daily/daily_report_2026-05-13.md +++ /dev/null @@ -1,366 +0,0 @@ -# 🤖 LLM Intelligence Hub - 每日情报报告 - -**报告日期**: 2026-05-13 -**生成时间**: 2026-05-13T09:42:02+08:00 - -## 📊 数据质量摘要 - -| 指标 | 数值 | -|------|------| -| 模型总数 | 504 | -| 数据新鲜 | 461 | -| CNY定价 | 126 | -| USD定价 | 378 | -| 厂商总数 | 81 | - -## 🆓 免费模型(共 375 个) - -**按国家分布**: US 146个, 国际 145个, CN 84个 - -**代表性模型(前20个)**: - -| 模型 | 厂商 | 国家 | 上下文 | -|------|------|------|--------| -| Pareto Code Router | OpenRouter | US | 2000000 | -| xAI: Grok 4.20 Multi-Agent | xAI | US | 2000000 | -| Auto Router | OpenRouter | US | 2000000 | -| xAI: Grok 4 Fast | xAI | US | 2000000 | -| xAI: Grok 4.20 | xAI | US | 2000000 | -| xAI: Grok 4.1 Fast | xAI | US | 2000000 | -| OpenAI: GPT-5.4 | OpenAI | US | 1050000 | -| OpenAI: GPT-5.5 | OpenAI | US | 1050000 | -| OpenAI: GPT-5.5 Pro | OpenAI | US | 1050000 | -| OpenAI GPT Latest | ~openai | 国际 | 1050000 | -| OpenAI: GPT-5.4 Pro | OpenAI | US | 1050000 | -| Owl Alpha | OpenRouter | US | 1048756 | -| Google Gemini Flash Latest | ~google | 国际 | 1048576 | -| Google: Gemini 2.5 Flash Lite | Google | US | 1048576 | -| Google: Gemini 2.0 Flash Lite | Google | US | 1048576 | -| Meta: Llama 4 Maverick | meta-llama | 国际 | 1048576 | -| Google: Lyria 3 Clip Preview | Google | US | 1048576 | -| Google: Lyria 3 Pro Preview | Google | US | 1048576 | -| Google Gemini Pro Latest | ~google | 国际 | 1048576 | -| Google: Gemini 3 Flash Preview | Google | US | 1048576 | -| ... | ... | ... | ... | - -> 共 375 个免费模型,以上为前20个代表性模型 - -## 🌍 国际推荐模型 TOP 5 - -| 排名 | 模型 | 厂商 | 场景 | 输入(原价) | 输出(原价) | 上下文 | -|------|------|------|------|-----------|-----------|--------| -| 1 | Qwen3-VL-8B | Alibaba | 视觉 | ¥0.20 | ¥0.50 | 32000 | -| 2 | Qwen3-VL-32B | Alibaba | 视觉 | ¥0.50 | ¥1.00 | 32000 | -| 3 | GPT-5.4 Mini | OpenAI | 对话 | $0.75 | $4.50 | 200000 | -| 4 | Doubao-Pro | ByteDance | 视觉 | ¥0.80 | ¥2.00 | 32000 | -| 5 | DeepSeek-V3 | DeepSeek | 对话 | ¥1.00 | ¥2.00 | 64000 | - -## 🇨🇳 国内模型 TOP 10 - -| 排名 | 模型 | 厂商 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|------|------|-----------|-----------|--------| -| 1 | DeepSeek V4 Flash | DeepSeek | 对话 | ¥1.02 | ¥2.03 | 1000000 | -| 2 | doubao-seed-1.6-flash | ByteDance | 对话 | ¥0.15 | ¥0.30 | 32000 | -| 3 | GLM-4.6V-FlashX | Zhipu AI | 视觉 | ¥0.15 | ¥1.50 | 8000 | -| 4 | GLM-Realtime-Flash | Zhipu AI | 对话 | ¥0.18 | ¥0.18 | 8000 | -| 5 | doubao-seed-2.0-mini | ByteDance | 对话 | ¥0.20 | ¥0.40 | 32000 | -| 6 | doubao-seed-1.6-lite | ByteDance | 对话 | ¥0.30 | ¥0.60 | 32000 | -| 7 | doubao-seed-1.6-flash-128k | ByteDance | 对话 | ¥0.30 | ¥0.60 | 128000 | -| 8 | GLM-Realtime-Air | Zhipu AI | 对话 | ¥0.30 | ¥0.30 | 8000 | -| 9 | doubao-1.5-lite-32k | ByteDance | 对话 | ¥0.30 | ¥0.60 | 32000 | -| 10 | doubao-seed-2.0-mini-128k | ByteDance | 对话 | ¥0.40 | ¥0.80 | 128000 | -| 11 | DeepSeek V4 Pro | DeepSeek | 对话 | ¥3.15 | ¥6.31 | 1000000 | -| 12 | GLM-4.7-FlashX | Zhipu AI | 对话 | ¥0.50 | ¥3.00 | 200000 | -| 13 | GLM-4-Air | Zhipu AI | 对话 | ¥0.50 | ¥0.25 | 128000 | -| 14 | doubao-seed-1.6-lite-128k | ByteDance | 对话 | ¥0.60 | ¥1.20 | 128000 | -| 15 | doubao-seed-1.6-flash-256k | ByteDance | 对话 | ¥0.60 | ¥1.20 | 256000 | -| 16 | doubao-seed-2.0-lite | ByteDance | 对话 | ¥0.60 | ¥1.20 | 32000 | -| 17 | doubao-seed-character | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 18 | doubao-seed-1.8 | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 19 | doubao-seed-1.6 | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 20 | GLM-4.5-Air | Zhipu AI | 对话 | ¥0.80 | ¥2.00 | 32000 | -| 21 | doubao-pro-32k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 22 | doubao-seed-1.6-vision | ByteDance | 视觉 | ¥0.80 | ¥1.60 | 32000 | -| 23 | doubao-1.5-pro-32k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 32000 | -| 24 | doubao-seed-2.0-mini-256k | ByteDance | 对话 | ¥0.80 | ¥1.60 | 256000 | -| 25 | doubao-seed-2.0-lite-128k | ByteDance | 对话 | ¥0.90 | ¥1.80 | 128000 | -| 26 | GLM-4-Long | Zhipu AI | 对话 | ¥1.00 | ¥0.50 | 1000000 | -| 27 | doubao-seed-1.8-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 28 | GLM-4.5-Air (32K+) | Zhipu AI | 对话 | ¥1.20 | ¥8.00 | 128000 | -| 29 | doubao-seed-code | ByteDance | 代码 | ¥1.20 | ¥2.40 | 32000 | -| 30 | doubao-seed-1.6-vision-128k | ByteDance | 视觉 | ¥1.20 | ¥2.40 | 128000 | -| 31 | doubao-seed-1.6-lite-256k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 256000 | -| 32 | doubao-seed-1.6-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 33 | doubao-seed-character-128k | ByteDance | 对话 | ¥1.20 | ¥2.40 | 128000 | -| 34 | doubao-seed-code-128k | ByteDance | 代码 | ¥1.40 | ¥2.80 | 128000 | -| 35 | doubao-seed-2.0-lite-256k | ByteDance | 对话 | ¥1.80 | ¥3.60 | 256000 | -| 36 | deepseek-v3 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 37 | GLM-4.7 | Zhipu AI | 对话 | ¥2.00 | ¥8.00 | 32000 | -| 38 | GLM-4.5V | Zhipu AI | 视觉 | ¥2.00 | ¥6.00 | 32000 | -| 39 | GLM-4.6V | Zhipu AI | 视觉 | ¥2.00 | ¥6.00 | 8000 | -| 40 | Moonshot V1 8K | Moonshot AI | 对话 | ¥2.00 | ¥10.00 | 8192 | -| 41 | deepseek-v3.2 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 42 | GLM-TTS | Zhipu AI | 对话 | ¥2.00 | 免费 | 8000 | -| 43 | glm-4.7 | ByteDance | 对话 | ¥2.00 | ¥4.00 | 32000 | -| 44 | doubao-seed-1.6-vision-256k | ByteDance | 视觉 | ¥2.40 | ¥4.80 | 256000 | -| 45 | doubao-seed-1.8-256k | ByteDance | 对话 | ¥2.40 | ¥4.80 | 256000 | -| 46 | doubao-seed-1.6-256k | ByteDance | 对话 | ¥2.40 | ¥4.80 | 256000 | -| 47 | doubao-seed-code-256k | ByteDance | 代码 | ¥2.80 | ¥5.60 | 256000 | -| 48 | doubao-1.5-vision-pro | ByteDance | 视觉 | ¥3.00 | ¥6.00 | 32000 | -| 49 | doubao-seed-2.0-code | ByteDance | 代码 | ¥3.20 | ¥6.40 | 32000 | -| 50 | doubao-seed-2.0-pro | ByteDance | 对话 | ¥3.20 | ¥6.40 | 32000 | -| 51 | deepseek-v3.1 | ByteDance | 对话 | ¥4.00 | ¥8.00 | 32000 | -| 52 | Kimi K2 0905 Preview | Moonshot AI | 对话 | ¥4.00 | ¥16.00 | 262144 | -| 53 | glm-4.7-128k | ByteDance | 对话 | ¥4.00 | ¥8.00 | 128000 | -| 54 | GLM-5 | Zhipu AI | 对话 | ¥4.00 | ¥18.00 | 32000 | -| 55 | deepseek-v3.2-128k | ByteDance | 对话 | ¥4.00 | ¥8.00 | 128000 | -| 56 | GLM-4.7 (32K+) | Zhipu AI | 对话 | ¥4.00 | ¥16.00 | 200000 | -| 57 | deepseek-r1 | ByteDance | 推理 | ¥4.00 | ¥8.00 | 32000 | -| 58 | GLM-4V-Plus | Zhipu AI | 视觉 | ¥4.00 | ¥4.00 | 8000 | -| 59 | doubao-seed-2.0-code-128k | ByteDance | 代码 | ¥4.80 | ¥9.60 | 128000 | -| 60 | doubao-seed-2.0-pro-128k | ByteDance | 对话 | ¥4.80 | ¥9.60 | 128000 | -| 61 | GLM-5-Turbo | Zhipu AI | 对话 | ¥5.00 | ¥22.00 | 32000 | -| 62 | GLM-TTS-Clone | Zhipu AI | 对话 | ¥6.00 | 免费 | 8000 | -| 63 | GLM-5 (32K+) | Zhipu AI | 对话 | ¥6.00 | ¥22.00 | 200000 | -| 64 | GLM-5.1 | Zhipu AI | 对话 | ¥6.00 | ¥24.00 | 32000 | -| 65 | Kimi K2.6 | Moonshot AI | 视觉 | ¥6.50 | ¥27.00 | 262144 | -| 66 | GLM-5-Turbo (32K+) | Zhipu AI | 对话 | ¥7.00 | ¥26.00 | 200000 | -| 67 | GLM-5.1 (32K+) | Zhipu AI | 对话 | ¥8.00 | ¥28.00 | 200000 | -| 68 | doubao-seed-2.0-code-256k | ByteDance | 代码 | ¥9.60 | ¥19.20 | 256000 | -| 69 | doubao-seed-2.0-pro-256k | ByteDance | 对话 | ¥9.60 | ¥19.20 | 256000 | -| 70 | GLM-4-AirX | Zhipu AI | 对话 | ¥10.00 | ¥10.00 | 8000 | -| 71 | GLM-ASR-2512 | Zhipu AI | 对话 | ¥16.00 | 免费 | 8000 | -| 72 | ERNIE 5.1 | Baidu | 对话 | ¥22.00 | ¥22.00 | 0 | -| 73 | ERNIE 5.0 | Baidu | 对话 | ¥40.00 | ¥40.00 | 0 | -| 74 | GLM-4V | Zhipu AI | 视觉 | ¥50.00 | ¥50.00 | 2000 | -| 75 | GLM-4-Voice | Zhipu AI | 对话 | ¥80.00 | ¥80.00 | 8000 | -| 76 | GLM-4-0520 | Zhipu AI | 对话 | ¥100.00 | ¥50.00 | 128000 | - -## 💳 腾讯云套餐订阅价 - -> 以下为套餐订阅价，不参与按模型输入/输出单价排行。 - -| 套餐 | 月费 | 月额度 | 上下文上限 | 覆盖模型 | -|------|------|--------|------------|----------| -| Hy Token Plan Lite | ¥28.00/月 | 3500万 Tokens/月 | 256K | 1 个（hy3-preview） | -| 通用 Token Plan Lite | ¥39.00/月 | 3500万 Tokens/月 | - | 10 个（tc-code-latest, minimax-m2.5, minimax-m2.7） | -| Hy Token Plan Standard | ¥78.00/月 | 1亿 Tokens/月 | 256K | 1 个（hy3-preview） | -| 通用 Token Plan Standard | ¥99.00/月 | 1亿 Tokens/月 | - | 10 个（tc-code-latest, minimax-m2.5, minimax-m2.7） | -| Hy Token Plan Pro | ¥238.00/月 | 3.2亿 Tokens/月 | 256K | 1 个（hy3-preview） | -| 通用 Token Plan Pro | ¥299.00/月 | 3.2亿 Tokens/月 | - | 10 个（tc-code-latest, minimax-m2.5, minimax-m2.7） | -| Hy Token Plan Max | ¥468.00/月 | 6.5亿 Tokens/月 | 256K | 1 个（hy3-preview） | -| 通用 Token Plan Max | ¥599.00/月 | 6.5亿 Tokens/月 | - | 10 个（tc-code-latest, minimax-m2.5, minimax-m2.7） | - -## 📊 模型分类概览 - -### 🇨🇳 国内官方平台模型 - -**Zhipu** (26个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| GLM-4.6V-FlashX | 视觉 | ¥0.15 | ¥1.50 | 8000 | -| GLM-Realtime-Flash | 对话 | ¥0.18 | ¥0.18 | 8000 | -| GLM-Realtime-Air | 对话 | ¥0.30 | ¥0.30 | 8000 | -| GLM-4.7-FlashX | 对话 | ¥0.50 | ¥3.00 | 200000 | -| GLM-4-Air | 对话 | ¥0.50 | ¥0.25 | 128000 | -| GLM-4.5-Air | 对话 | ¥0.80 | ¥2.00 | 32000 | -| GLM-4-Long | 对话 | ¥1.00 | ¥0.50 | 1000000 | -| GLM-4.5-Air (32K+) | 对话 | ¥1.20 | ¥8.00 | 128000 | -| GLM-4.7 | 对话 | ¥2.00 | ¥8.00 | 32000 | -| GLM-4.5V | 视觉 | ¥2.00 | ¥6.00 | 32000 | -| GLM-4.6V | 视觉 | ¥2.00 | ¥6.00 | 8000 | -| GLM-TTS | 对话 | ¥2.00 | 免费 | 8000 | -| GLM-5 | 对话 | ¥4.00 | ¥18.00 | 32000 | -| GLM-4.7 (32K+) | 对话 | ¥4.00 | ¥16.00 | 200000 | -| GLM-4V-Plus | 视觉 | ¥4.00 | ¥4.00 | 8000 | -| GLM-5-Turbo | 对话 | ¥5.00 | ¥22.00 | 32000 | -| GLM-TTS-Clone | 对话 | ¥6.00 | 免费 | 8000 | -| GLM-5 (32K+) | 对话 | ¥6.00 | ¥22.00 | 200000 | -| GLM-5.1 | 对话 | ¥6.00 | ¥24.00 | 32000 | -| GLM-5-Turbo (32K+) | 对话 | ¥7.00 | ¥26.00 | 200000 | -| GLM-5.1 (32K+) | 对话 | ¥8.00 | ¥28.00 | 200000 | -| GLM-4-AirX | 对话 | ¥10.00 | ¥10.00 | 8000 | -| GLM-ASR-2512 | 对话 | ¥16.00 | 免费 | 8000 | -| GLM-4V | 视觉 | ¥50.00 | ¥50.00 | 2000 | -| GLM-4-Voice | 对话 | ¥80.00 | ¥80.00 | 8000 | -| GLM-4-0520 | 对话 | ¥100.00 | ¥50.00 | 128000 | - -**Moonshot** (3个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| Moonshot V1 8K | 对话 | ¥2.00 | ¥10.00 | 8192 | -| Kimi K2 0905 Preview | 对话 | ¥4.00 | ¥16.00 | 262144 | -| Kimi K2.6 | 视觉 | ¥6.50 | ¥27.00 | 262144 | - -**Baidu Qianfan** (2个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| ERNIE 5.1 | 对话 | ¥22.00 | ¥22.00 | 0 | -| ERNIE 5.0 | 对话 | ¥40.00 | ¥40.00 | 0 | - -**DeepSeek** (2个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| DeepSeek V4 Flash | 对话 | ¥1.02 | ¥2.03 | 1000000 | -| DeepSeek V4 Pro | 对话 | ¥3.15 | ¥6.31 | 1000000 | - -**ByteDance Volcano** (43个) - -| 模型 | 场景 | 输入(CNY) | 输出(CNY) | 上下文 | -|------|------|-----------|-----------|--------| -| doubao-seed-1.6-flash | 对话 | ¥0.15 | ¥0.30 | 32000 | -| doubao-seed-2.0-mini | 对话 | ¥0.20 | ¥0.40 | 32000 | -| doubao-seed-1.6-lite | 对话 | ¥0.30 | ¥0.60 | 32000 | -| doubao-seed-1.6-flash-128k | 对话 | ¥0.30 | ¥0.60 | 128000 | -| doubao-1.5-lite-32k | 对话 | ¥0.30 | ¥0.60 | 32000 | -| doubao-seed-2.0-mini-128k | 对话 | ¥0.40 | ¥0.80 | 128000 | -| doubao-seed-1.6-lite-128k | 对话 | ¥0.60 | ¥1.20 | 128000 | -| doubao-seed-1.6-flash-256k | 对话 | ¥0.60 | ¥1.20 | 256000 | -| doubao-seed-2.0-lite | 对话 | ¥0.60 | ¥1.20 | 32000 | -| doubao-seed-character | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.8 | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.6 | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-pro-32k | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-1.6-vision | 视觉 | ¥0.80 | ¥1.60 | 32000 | -| doubao-1.5-pro-32k | 对话 | ¥0.80 | ¥1.60 | 32000 | -| doubao-seed-2.0-mini-256k | 对话 | ¥0.80 | ¥1.60 | 256000 | -| doubao-seed-2.0-lite-128k | 对话 | ¥0.90 | ¥1.80 | 128000 | -| doubao-seed-1.8-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-code | 代码 | ¥1.20 | ¥2.40 | 32000 | -| doubao-seed-1.6-vision-128k | 视觉 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-1.6-lite-256k | 对话 | ¥1.20 | ¥2.40 | 256000 | -| doubao-seed-1.6-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-character-128k | 对话 | ¥1.20 | ¥2.40 | 128000 | -| doubao-seed-code-128k | 代码 | ¥1.40 | ¥2.80 | 128000 | -| doubao-seed-2.0-lite-256k | 对话 | ¥1.80 | ¥3.60 | 256000 | -| deepseek-v3 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| deepseek-v3.2 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| glm-4.7 | 对话 | ¥2.00 | ¥4.00 | 32000 | -| doubao-seed-1.6-vision-256k | 视觉 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-1.8-256k | 对话 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-1.6-256k | 对话 | ¥2.40 | ¥4.80 | 256000 | -| doubao-seed-code-256k | 代码 | ¥2.80 | ¥5.60 | 256000 | -| doubao-1.5-vision-pro | 视觉 | ¥3.00 | ¥6.00 | 32000 | -| doubao-seed-2.0-code | 代码 | ¥3.20 | ¥6.40 | 32000 | -| doubao-seed-2.0-pro | 对话 | ¥3.20 | ¥6.40 | 32000 | -| deepseek-v3.1 | 对话 | ¥4.00 | ¥8.00 | 32000 | -| glm-4.7-128k | 对话 | ¥4.00 | ¥8.00 | 128000 | -| deepseek-v3.2-128k | 对话 | ¥4.00 | ¥8.00 | 128000 | -| deepseek-r1 | 推理 | ¥4.00 | ¥8.00 | 32000 | -| doubao-seed-2.0-code-128k | 代码 | ¥4.80 | ¥9.60 | 128000 | -| doubao-seed-2.0-pro-128k | 对话 | ¥4.80 | ¥9.60 | 128000 | -| doubao-seed-2.0-code-256k | 代码 | ¥9.60 | ¥19.20 | 256000 | -| doubao-seed-2.0-pro-256k | 对话 | ¥9.60 | ¥19.20 | 256000 | - -### 💻 代码模型(19个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Pareto Code Router | OpenRouter | 免费 | 免费 | -| Qwen: Qwen3 Coder Flash | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder Plus | Qwen | 免费 | 免费 | -| OpenAI: GPT-5 Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex-Mini | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.2-Codex | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.1-Codex-Max | OpenAI | 免费 | 免费 | -| OpenAI: GPT-5.3-Codex | OpenAI | 免费 | 免费 | -| Qwen: Qwen3 Coder Next | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder 480B A35B | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Coder 480B A35B... | Qwen | 免费 | 免费 | -| Mistral: Codestral 2508 | mistralai | 免费 | 免费 | -| Kwaipilot: KAT-Coder-Pro V2 | kwaipilot | 免费 | 免费 | -| xAI: Grok Code Fast 1 | xAI | 免费 | 免费 | -| Qwen: Qwen3 Coder 30B A3B I... | Qwen | 免费 | 免费 | -| Arcee AI: Coder Large | arcee-ai | 免费 | 免费 | -| Qwen2.5 Coder 32B Instruct | Qwen | 免费 | 免费 | -| AlfredPros: CodeLLaMa 7B In... | alfredpros | 免费 | 免费 | - -### 🧠 推理模型(35个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Qwen: Qwen Plus 0728 (think... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Max Thinking | Qwen | 免费 | 免费 | -| Arcee AI: Trinity Large Thi... | arcee-ai | 免费 | 免费 | -| MoonshotAI: Kimi K2 Thinking | Moonshot AI | 免费 | 免费 | -| Arcee AI: Trinity Large Thi... | arcee-ai | 免费 | 免费 | -| OpenAI: o1-pro | OpenAI | 免费 | 免费 | -| OpenAI: o3 Deep Research | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini Deep Research | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini | OpenAI | 免费 | 免费 | -| OpenAI: o3 | OpenAI | 免费 | 免费 | -| OpenAI: o4 Mini High | OpenAI | 免费 | 免费 | -| Anthropic: Claude 3.7 Sonne... | Anthropic | 免费 | 免费 | -| OpenAI: o1 | OpenAI | 免费 | 免费 | -| OpenAI: o3 Mini | OpenAI | 免费 | 免费 | -| OpenAI: o3 Mini High | OpenAI | 免费 | 免费 | -| OpenAI: o3 Pro | OpenAI | 免费 | 免费 | -| DeepSeek: R1 0528 | DeepSeek | 免费 | 免费 | -| Qwen: Qwen3 30B A3B Thinkin... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 235B A22B Think... | Qwen | 免费 | 免费 | -| Sao10K: Llama 3.3 Euryale 70B | sao10k | 免费 | 免费 | -| DeepSeek: R1 Distill Llama 70B | DeepSeek | 免费 | 免费 | -| Sao10K: Llama 3.1 Euryale 7... | sao10k | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Thinking | Qwen | 免费 | 免费 | -| Qwen: Qwen3 Next 80B A3B Th... | Qwen | 免费 | 免费 | -| Arcee AI: Maestro Reasoning | arcee-ai | 免费 | 免费 | -| Qwen: Qwen3 VL 235B A22B Th... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Thin... | Qwen | 免费 | 免费 | -| Baidu: ERNIE 4.5 21B A3B Th... | Baidu | 免费 | 免费 | -| Perplexity: Sonar Reasoning... | Perplexity | 免费 | 免费 | -| DeepSeek: R1 | DeepSeek | 免费 | 免费 | -| DeepSeek: R1 Distill Qwen 32B | DeepSeek | 免费 | 免费 | -| LiquidAI: LFM2.5-1.2B-Think... | liquid | 免费 | 免费 | -| Sao10K: Llama 3.1 70B Hanam... | sao10k | 免费 | 免费 | -| Sao10K: Llama 3 8B Lunaris | sao10k | 免费 | 免费 | -| Sao10k: Llama 3 Euryale 70B... | sao10k | 免费 | 免费 | - -### 👁️ 视觉/多模态模型(15个) - -| 模型 | 厂商 | 输入(原价) | 输出(原价) | -|------|------|-----------|-----------| -| Qwen: Qwen3 VL 235B A22B In... | Qwen | 免费 | 免费 | -| MoonshotAI: Kimi K2.6 | Moonshot AI | 免费 | 免费 | -| Meta: Llama 3.2 11B Vision ... | meta-llama | 免费 | 免费 | -| Qwen: Qwen VL Max | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Thinking | Qwen | 免费 | 免费 | -| Qwen: Qwen VL Plus | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 235B A22B Th... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 32B Instruct | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 8B Instruct | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Inst... | Qwen | 免费 | 免费 | -| Qwen: Qwen3 VL 30B A3B Thin... | Qwen | 免费 | 免费 | -| NVIDIA: Nemotron Nano 12B 2... | NVIDIA | 免费 | 免费 | -| Baidu: ERNIE 4.5 VL 424B A47B | Baidu | 免费 | 免费 | -| Qwen: Qwen2.5 VL 72B Instruct | Qwen | 免费 | 免费 | -| Baidu: ERNIE 4.5 VL 28B A3B | Baidu | 免费 | 免费 | - -## 🇨🇳 国内官方平台(5 家) - -- **Moonshot**: 3 个模型,最低 ¥2.00/MTok -- **DeepSeek**: 2 个模型,最低 ¥0.14/MTok -- **Baidu Qianfan**: 44 个模型,最低 ¥0.00/MTok -- **Zhipu**: 29 个模型,最低 ¥0.18/MTok -- **ByteDance Volcano**: 43 个模型,最低 ¥0.15/MTok - -## ☁️ 国际官方平台(1 家) - -- **OpenAI**: 3 个模型,最低 $0.75/MTok - -## 🔀 中转/聚合平台(1 家) - -- **OpenRouter**: 380 个模型,最低 $0.00/MTok - ---- - -📌 **说明**: 本报告由 LLM Intelligence Hub 自动生成。 -- 国际模型价格按 1 USD = 7.25 CNY 换算显示，括号内为原生货币价格 -- 国内模型价格为厂商原生 CNY 定价 -- 数据来源: OpenRouter API + 智谱AI + 百度千帆 + Moonshot + DeepSeek + OpenAI - -_生成时间: 2026-05-13T09:42:02+08:00_ diff --git a/reports/daily/html/daily_report_2026-05-10.html b/reports/daily/html/daily_report_2026-05-10.html deleted file mode 100644 index 199da06..0000000 --- a/reports/daily/html/daily_report_2026-05-10.html +++ /dev/null @@ -1,28 +0,0 @@ - -LLM Hub - 2026-05-10 - -

🤖 LLM Intelligence Hub

每日情报报告 - 2026-05-10

- -
-

📊 数据质量摘要

- - - - - - -
指标数值
模型总数377
数据新鲜368
CNY定价0
USD定价377
厂商总数60
- - - -

📌 本报告由 LLM Intelligence Hub 自动生成

- \ No newline at end of file diff --git a/reports/daily/html/daily_report_2026-05-11.html b/reports/daily/html/daily_report_2026-05-11.html deleted file mode 100644 index d06a888..0000000 --- a/reports/daily/html/daily_report_2026-05-11.html +++ /dev/null @@ -1,1241 +0,0 @@ - - - - - -LLM Intelligence Hub - 2026-05-11 - - - -
- -
-

🤖 LLM Intelligence Hub

-

每日情报报告 · 2026-05-11 · 501 模型覆盖

-
- - -
-
-
模型总数
-
501
-
-
-
免费模型
-
372
-
-
-
国际模型
-
5
-
-
-
国内模型
-
76
-
-
- - - - - -
-

🆓 免费模型(372 个)

-

代表性模型(前20个):

-
- -
-
Auto Router
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.20
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.20 Multi-Agent
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
Pareto Code Router
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4 Fast
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.1 Fast
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
OpenAI: GPT-5.4
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.4 Pro
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.5
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.5 Pro
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI GPT Latest
-
~openai 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
Owl Alpha
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048756 tokens -
-
- -
-
Google: Gemini 2.5 Flash Lite
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
DeepSeek: DeepSeek V4 Flash
-
DeepSeek 国内
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 3.1 Pro Preview
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 3.1 Pro Preview Custom Tools
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.0 Flash Lite
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.5 Pro Preview 05-06
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google Gemini Pro Latest
-
~google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.5 Pro Preview 06-05
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
- -

... 共 372 个免费模型,以上为前20个

- -
- - - - -
-

🌍 国际低价模型 TOP 5

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
排名模型厂商输入价格输出价格上下文
1Qwen3-VL-8BAlibaba$0.20$0.5032000
2Qwen3-VL-32BAlibaba$0.50$1.0032000
3GPT-5.4 MiniOpenAI$0.75$4.50200000
4Doubao-ProByteDance$0.80$2.0032000
5DeepSeek-V3DeepSeek$1.00$2.0064000
-
- - - - -
-

🇨🇳 国内模型 TOP 10

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
排名模型厂商输入价格输出价格上下文
1DeepSeek V4 FlashDeepSeek$0.14$0.281000000
2doubao-seed-1.6-flashByteDance$0.15$0.3032000
3GLM-4.6V-FlashXZhipu AI$0.15$1.508000
4GLM-Realtime-FlashZhipu AI$0.18$0.188000
5doubao-seed-2.0-miniByteDance$0.20$0.4032000
6doubao-seed-1.6-liteByteDance$0.30$0.6032000
7doubao-seed-1.6-flash-128kByteDance$0.30$0.60128000
8GLM-Realtime-AirZhipu AI$0.30$0.308000
9doubao-1.5-lite-32kByteDance$0.30$0.6032000
10doubao-seed-2.0-mini-128kByteDance$0.40$0.80128000
11DeepSeek V4 ProDeepSeek$0.43$0.871000000
12GLM-4.7-FlashXZhipu AI$0.50$3.00200000
13GLM-4-AirZhipu AI$0.50$0.25128000
14doubao-seed-1.6-lite-128kByteDance$0.60$1.20128000
15doubao-seed-1.6-flash-256kByteDance$0.60$1.20256000
16doubao-seed-2.0-liteByteDance$0.60$1.2032000
17doubao-seed-characterByteDance$0.80$1.6032000
18doubao-seed-1.8ByteDance$0.80$1.6032000
19doubao-seed-1.6ByteDance$0.80$1.6032000
20GLM-4.5-AirZhipu AI$0.80$2.0032000
21doubao-pro-32kByteDance$0.80$1.6032000
22doubao-seed-1.6-visionByteDance$0.80$1.6032000
23doubao-1.5-pro-32kByteDance$0.80$1.6032000
24doubao-seed-2.0-mini-256kByteDance$0.80$1.60256000
25doubao-seed-2.0-lite-128kByteDance$0.90$1.80128000
26GLM-4-LongZhipu AI$1.00$0.501000000
27doubao-seed-1.8-128kByteDance$1.20$2.40128000
28GLM-4.5-Air (32K+)Zhipu AI$1.20$8.00128000
29doubao-seed-codeByteDance$1.20$2.4032000
30doubao-seed-1.6-vision-128kByteDance$1.20$2.40128000
31doubao-seed-1.6-lite-256kByteDance$1.20$2.40256000
32doubao-seed-1.6-128kByteDance$1.20$2.40128000
33doubao-seed-character-128kByteDance$1.20$2.40128000
34doubao-seed-code-128kByteDance$1.40$2.80128000
35doubao-seed-2.0-lite-256kByteDance$1.80$3.60256000
36deepseek-v3ByteDance$2.00$4.0032000
37GLM-4.7Zhipu AI$2.00$8.0032000
38GLM-4.5VZhipu AI$2.00$6.0032000
39GLM-4.6VZhipu AI$2.00$6.008000
40Moonshot V1 8KMoonshot AI$2.00$10.008192
41deepseek-v3.2ByteDance$2.00$4.0032000
42GLM-TTSZhipu AI$2.00$0.008000
43glm-4.7ByteDance$2.00$4.0032000
44doubao-seed-1.6-vision-256kByteDance$2.40$4.80256000
45doubao-seed-1.8-256kByteDance$2.40$4.80256000
46doubao-seed-1.6-256kByteDance$2.40$4.80256000
47doubao-seed-code-256kByteDance$2.80$5.60256000
48doubao-1.5-vision-proByteDance$3.00$6.0032000
49doubao-seed-2.0-codeByteDance$3.20$6.4032000
50doubao-seed-2.0-proByteDance$3.20$6.4032000
51deepseek-v3.1ByteDance$4.00$8.0032000
52Kimi K2 0905 PreviewMoonshot AI$4.00$16.00262144
53glm-4.7-128kByteDance$4.00$8.00128000
54GLM-5Zhipu AI$4.00$18.0032000
55deepseek-v3.2-128kByteDance$4.00$8.00128000
56GLM-4.7 (32K+)Zhipu AI$4.00$16.00200000
57deepseek-r1ByteDance$4.00$8.0032000
58GLM-4V-PlusZhipu AI$4.00$4.008000
59doubao-seed-2.0-code-128kByteDance$4.80$9.60128000
60doubao-seed-2.0-pro-128kByteDance$4.80$9.60128000
61GLM-5-TurboZhipu AI$5.00$22.0032000
62GLM-TTS-CloneZhipu AI$6.00$0.008000
63GLM-5 (32K+)Zhipu AI$6.00$22.00200000
64GLM-5.1Zhipu AI$6.00$24.0032000
65Kimi K2.6Moonshot AI$6.50$27.00262144
66GLM-5-Turbo (32K+)Zhipu AI$7.00$26.00200000
67GLM-5.1 (32K+)Zhipu AI$8.00$28.00200000
68doubao-seed-2.0-code-256kByteDance$9.60$19.20256000
69doubao-seed-2.0-pro-256kByteDance$9.60$19.20256000
70GLM-4-AirXZhipu AI$10.00$10.008000
71GLM-ASR-2512Zhipu AI$16.00$0.008000
72ERNIE 5.1Baidu$22.00$22.000
73ERNIE 5.0Baidu$40.00$40.000
74GLM-4VZhipu AI$50.00$50.002000
75GLM-4-VoiceZhipu AI$80.00$80.008000
76GLM-4-0520Zhipu AI$100.00$50.00128000
-
- - - - -
-

☁️ 云厂商/官方平台(6 家)

- - - - - - - - - - - - - - - -
平台模型数最低价格平均价格
Moonshot3$2.00$4.17
DeepSeek2$0.14$0.29
OpenAI3$0.75$2.75
Baidu Qianfan44$0.00$1.41
Zhipu29$0.18$10.99
ByteDance Volcano43$0.15$2.11
-
- - - - -
-

🔀 中转/聚合平台(1 家)

- - - - - -
平台模型数最低价格平均价格
OpenRouter377$0.00$0.02
-
- - -
-

📌 本报告由 LLM Intelligence Hub 自动生成 · 2026-05-11

-

价格单位:USD/1M tokens

-
- -
- - \ No newline at end of file diff --git a/reports/daily/html/daily_report_2026-05-12.html b/reports/daily/html/daily_report_2026-05-12.html deleted file mode 100644 index 614fc2f..0000000 --- a/reports/daily/html/daily_report_2026-05-12.html +++ /dev/null @@ -1,1241 +0,0 @@ - - - - - -LLM Intelligence Hub - 2026-05-12 - - - -
- -
-

🤖 LLM Intelligence Hub

-

每日情报报告 · 2026-05-12 · 502 模型覆盖

-
- - -
-
-
模型总数
-
502
-
-
-
免费模型
-
373
-
-
-
国际模型
-
5
-
-
-
国内模型
-
76
-
-
- - - - - -
-

🆓 免费模型(373 个)

-

代表性模型(前20个):

-
- -
-
Pareto Code Router
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
Auto Router
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.20
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4 Fast
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.1 Fast
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.20 Multi-Agent
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
OpenAI: GPT-5.5
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.5 Pro
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI GPT Latest
-
~openai 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.4 Pro
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.4
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
Owl Alpha
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048756 tokens -
-
- -
-
DeepSeek: DeepSeek V4 Pro
-
DeepSeek 国内
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.5 Flash Lite
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 3.1 Pro Preview
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.0 Flash
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.0 Flash Lite
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.5 Flash Lite Preview 09-2025
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google Gemini Pro Latest
-
~google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.5 Pro Preview 06-05
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
- -

... 共 373 个免费模型,以上为前20个

- -
- - - - -
-

🌍 国际低价模型 TOP 5

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
排名模型厂商输入价格输出价格上下文
1Qwen3-VL-8BAlibaba$0.20$0.5032000
2Qwen3-VL-32BAlibaba$0.50$1.0032000
3GPT-5.4 MiniOpenAI$0.75$4.50200000
4Doubao-ProByteDance$0.80$2.0032000
5DeepSeek-V3DeepSeek$1.00$2.0064000
-
- - - - -
-

🇨🇳 国内模型 TOP 10

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
排名模型厂商输入价格输出价格上下文
1DeepSeek V4 FlashDeepSeek$0.14$0.281000000
2doubao-seed-1.6-flashByteDance$0.15$0.3032000
3GLM-4.6V-FlashXZhipu AI$0.15$1.508000
4GLM-Realtime-FlashZhipu AI$0.18$0.188000
5doubao-seed-2.0-miniByteDance$0.20$0.4032000
6doubao-seed-1.6-liteByteDance$0.30$0.6032000
7doubao-seed-1.6-flash-128kByteDance$0.30$0.60128000
8GLM-Realtime-AirZhipu AI$0.30$0.308000
9doubao-1.5-lite-32kByteDance$0.30$0.6032000
10doubao-seed-2.0-mini-128kByteDance$0.40$0.80128000
11DeepSeek V4 ProDeepSeek$0.43$0.871000000
12GLM-4.7-FlashXZhipu AI$0.50$3.00200000
13GLM-4-AirZhipu AI$0.50$0.25128000
14doubao-seed-1.6-lite-128kByteDance$0.60$1.20128000
15doubao-seed-1.6-flash-256kByteDance$0.60$1.20256000
16doubao-seed-2.0-liteByteDance$0.60$1.2032000
17doubao-seed-characterByteDance$0.80$1.6032000
18doubao-seed-1.8ByteDance$0.80$1.6032000
19doubao-seed-1.6ByteDance$0.80$1.6032000
20GLM-4.5-AirZhipu AI$0.80$2.0032000
21doubao-pro-32kByteDance$0.80$1.6032000
22doubao-seed-1.6-visionByteDance$0.80$1.6032000
23doubao-1.5-pro-32kByteDance$0.80$1.6032000
24doubao-seed-2.0-mini-256kByteDance$0.80$1.60256000
25doubao-seed-2.0-lite-128kByteDance$0.90$1.80128000
26GLM-4-LongZhipu AI$1.00$0.501000000
27doubao-seed-1.8-128kByteDance$1.20$2.40128000
28GLM-4.5-Air (32K+)Zhipu AI$1.20$8.00128000
29doubao-seed-codeByteDance$1.20$2.4032000
30doubao-seed-1.6-vision-128kByteDance$1.20$2.40128000
31doubao-seed-1.6-lite-256kByteDance$1.20$2.40256000
32doubao-seed-1.6-128kByteDance$1.20$2.40128000
33doubao-seed-character-128kByteDance$1.20$2.40128000
34doubao-seed-code-128kByteDance$1.40$2.80128000
35doubao-seed-2.0-lite-256kByteDance$1.80$3.60256000
36deepseek-v3ByteDance$2.00$4.0032000
37GLM-4.7Zhipu AI$2.00$8.0032000
38GLM-4.5VZhipu AI$2.00$6.0032000
39GLM-4.6VZhipu AI$2.00$6.008000
40Moonshot V1 8KMoonshot AI$2.00$10.008192
41deepseek-v3.2ByteDance$2.00$4.0032000
42GLM-TTSZhipu AI$2.00$0.008000
43glm-4.7ByteDance$2.00$4.0032000
44doubao-seed-1.6-vision-256kByteDance$2.40$4.80256000
45doubao-seed-1.8-256kByteDance$2.40$4.80256000
46doubao-seed-1.6-256kByteDance$2.40$4.80256000
47doubao-seed-code-256kByteDance$2.80$5.60256000
48doubao-1.5-vision-proByteDance$3.00$6.0032000
49doubao-seed-2.0-codeByteDance$3.20$6.4032000
50doubao-seed-2.0-proByteDance$3.20$6.4032000
51deepseek-v3.1ByteDance$4.00$8.0032000
52Kimi K2 0905 PreviewMoonshot AI$4.00$16.00262144
53glm-4.7-128kByteDance$4.00$8.00128000
54GLM-5Zhipu AI$4.00$18.0032000
55deepseek-v3.2-128kByteDance$4.00$8.00128000
56GLM-4.7 (32K+)Zhipu AI$4.00$16.00200000
57deepseek-r1ByteDance$4.00$8.0032000
58GLM-4V-PlusZhipu AI$4.00$4.008000
59doubao-seed-2.0-code-128kByteDance$4.80$9.60128000
60doubao-seed-2.0-pro-128kByteDance$4.80$9.60128000
61GLM-5-TurboZhipu AI$5.00$22.0032000
62GLM-TTS-CloneZhipu AI$6.00$0.008000
63GLM-5 (32K+)Zhipu AI$6.00$22.00200000
64GLM-5.1Zhipu AI$6.00$24.0032000
65Kimi K2.6Moonshot AI$6.50$27.00262144
66GLM-5-Turbo (32K+)Zhipu AI$7.00$26.00200000
67GLM-5.1 (32K+)Zhipu AI$8.00$28.00200000
68doubao-seed-2.0-code-256kByteDance$9.60$19.20256000
69doubao-seed-2.0-pro-256kByteDance$9.60$19.20256000
70GLM-4-AirXZhipu AI$10.00$10.008000
71GLM-ASR-2512Zhipu AI$16.00$0.008000
72ERNIE 5.1Baidu$22.00$22.000
73ERNIE 5.0Baidu$40.00$40.000
74GLM-4VZhipu AI$50.00$50.002000
75GLM-4-VoiceZhipu AI$80.00$80.008000
76GLM-4-0520Zhipu AI$100.00$50.00128000
-
- - - - -
-

☁️ 云厂商/官方平台(6 家)

- - - - - - - - - - - - - - - -
平台模型数最低价格平均价格
Moonshot3$2.00$4.17
DeepSeek2$0.14$0.29
OpenAI3$0.75$2.75
Baidu Qianfan44$0.00$1.41
Zhipu29$0.18$10.99
ByteDance Volcano43$0.15$2.11
-
- - - - -
-

🔀 中转/聚合平台(1 家)

- - - - - -
平台模型数最低价格平均价格
OpenRouter378$0.00$0.02
-
- - -
-

📌 本报告由 LLM Intelligence Hub 自动生成 · 2026-05-12

-

价格单位:USD/1M tokens

-
- -
- - \ No newline at end of file diff --git a/reports/daily/html/daily_report_2026-05-13.html b/reports/daily/html/daily_report_2026-05-13.html deleted file mode 100644 index 918b7f9..0000000 --- a/reports/daily/html/daily_report_2026-05-13.html +++ /dev/null @@ -1,1316 +0,0 @@ - - - - - -LLM Intelligence Hub - 2026-05-13 - - - -
- -
-

🤖 LLM Intelligence Hub

-

每日情报报告 · 2026-05-13 · 504 模型覆盖

-
- - -
-
-
模型总数
-
504
-
-
-
免费模型
-
375
-
-
-
国际模型
-
5
-
-
-
国内模型
-
76
-
-
- - - - - -
-

🆓 免费模型(375 个)

-

代表性模型(前20个):

-
- -
-
Pareto Code Router
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.20 Multi-Agent
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
Auto Router
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4 Fast
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.20
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
xAI: Grok 4.1 Fast
-
xAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 2000000 tokens -
-
- -
-
OpenAI: GPT-5.4
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.5
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.5 Pro
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI GPT Latest
-
~openai 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
OpenAI: GPT-5.4 Pro
-
OpenAI 国际
-
- 输入 - 免费 -
-
- 上下文 - 1050000 tokens -
-
- -
-
Owl Alpha
-
OpenRouter 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048756 tokens -
-
- -
-
Google Gemini Flash Latest
-
~google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.5 Flash Lite
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 2.0 Flash Lite
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Meta: Llama 4 Maverick
-
meta-llama 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Lyria 3 Clip Preview
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Lyria 3 Pro Preview
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google Gemini Pro Latest
-
~google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
-
Google: Gemini 3 Flash Preview
-
Google 国际
-
- 输入 - 免费 -
-
- 上下文 - 1048576 tokens -
-
- -
- -

... 共 375 个免费模型,以上为前20个

- -
- - - - -
-

🌍 国际低价模型 TOP 5

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
排名模型厂商输入价格输出价格上下文
1Qwen3-VL-8BAlibaba$0.20$0.5032000
2Qwen3-VL-32BAlibaba$0.50$1.0032000
3GPT-5.4 MiniOpenAI$0.75$4.50200000
4Doubao-ProByteDance$0.80$2.0032000
5DeepSeek-V3DeepSeek$1.00$2.0064000
-
- - - - -
-

🇨🇳 国内模型 TOP 10

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
排名模型厂商输入价格输出价格上下文
1DeepSeek V4 FlashDeepSeek$0.14$0.281000000
2doubao-seed-1.6-flashByteDance$0.15$0.3032000
3GLM-4.6V-FlashXZhipu AI$0.15$1.508000
4GLM-Realtime-FlashZhipu AI$0.18$0.188000
5doubao-seed-2.0-miniByteDance$0.20$0.4032000
6doubao-seed-1.6-liteByteDance$0.30$0.6032000
7doubao-seed-1.6-flash-128kByteDance$0.30$0.60128000
8GLM-Realtime-AirZhipu AI$0.30$0.308000
9doubao-1.5-lite-32kByteDance$0.30$0.6032000
10doubao-seed-2.0-mini-128kByteDance$0.40$0.80128000
11DeepSeek V4 ProDeepSeek$0.43$0.871000000
12GLM-4.7-FlashXZhipu AI$0.50$3.00200000
13GLM-4-AirZhipu AI$0.50$0.25128000
14doubao-seed-1.6-lite-128kByteDance$0.60$1.20128000
15doubao-seed-1.6-flash-256kByteDance$0.60$1.20256000
16doubao-seed-2.0-liteByteDance$0.60$1.2032000
17doubao-seed-characterByteDance$0.80$1.6032000
18doubao-seed-1.8ByteDance$0.80$1.6032000
19doubao-seed-1.6ByteDance$0.80$1.6032000
20GLM-4.5-AirZhipu AI$0.80$2.0032000
21doubao-pro-32kByteDance$0.80$1.6032000
22doubao-seed-1.6-visionByteDance$0.80$1.6032000
23doubao-1.5-pro-32kByteDance$0.80$1.6032000
24doubao-seed-2.0-mini-256kByteDance$0.80$1.60256000
25doubao-seed-2.0-lite-128kByteDance$0.90$1.80128000
26GLM-4-LongZhipu AI$1.00$0.501000000
27doubao-seed-1.8-128kByteDance$1.20$2.40128000
28GLM-4.5-Air (32K+)Zhipu AI$1.20$8.00128000
29doubao-seed-codeByteDance$1.20$2.4032000
30doubao-seed-1.6-vision-128kByteDance$1.20$2.40128000
31doubao-seed-1.6-lite-256kByteDance$1.20$2.40256000
32doubao-seed-1.6-128kByteDance$1.20$2.40128000
33doubao-seed-character-128kByteDance$1.20$2.40128000
34doubao-seed-code-128kByteDance$1.40$2.80128000
35doubao-seed-2.0-lite-256kByteDance$1.80$3.60256000
36deepseek-v3ByteDance$2.00$4.0032000
37GLM-4.7Zhipu AI$2.00$8.0032000
38GLM-4.5VZhipu AI$2.00$6.0032000
39GLM-4.6VZhipu AI$2.00$6.008000
40Moonshot V1 8KMoonshot AI$2.00$10.008192
41deepseek-v3.2ByteDance$2.00$4.0032000
42GLM-TTSZhipu AI$2.00$0.008000
43glm-4.7ByteDance$2.00$4.0032000
44doubao-seed-1.6-vision-256kByteDance$2.40$4.80256000
45doubao-seed-1.8-256kByteDance$2.40$4.80256000
46doubao-seed-1.6-256kByteDance$2.40$4.80256000
47doubao-seed-code-256kByteDance$2.80$5.60256000
48doubao-1.5-vision-proByteDance$3.00$6.0032000
49doubao-seed-2.0-codeByteDance$3.20$6.4032000
50doubao-seed-2.0-proByteDance$3.20$6.4032000
51deepseek-v3.1ByteDance$4.00$8.0032000
52Kimi K2 0905 PreviewMoonshot AI$4.00$16.00262144
53glm-4.7-128kByteDance$4.00$8.00128000
54GLM-5Zhipu AI$4.00$18.0032000
55deepseek-v3.2-128kByteDance$4.00$8.00128000
56GLM-4.7 (32K+)Zhipu AI$4.00$16.00200000
57deepseek-r1ByteDance$4.00$8.0032000
58GLM-4V-PlusZhipu AI$4.00$4.008000
59doubao-seed-2.0-code-128kByteDance$4.80$9.60128000
60doubao-seed-2.0-pro-128kByteDance$4.80$9.60128000
61GLM-5-TurboZhipu AI$5.00$22.0032000
62GLM-TTS-CloneZhipu AI$6.00$0.008000
63GLM-5 (32K+)Zhipu AI$6.00$22.00200000
64GLM-5.1Zhipu AI$6.00$24.0032000
65Kimi K2.6Moonshot AI$6.50$27.00262144
66GLM-5-Turbo (32K+)Zhipu AI$7.00$26.00200000
67GLM-5.1 (32K+)Zhipu AI$8.00$28.00200000
68doubao-seed-2.0-code-256kByteDance$9.60$19.20256000
69doubao-seed-2.0-pro-256kByteDance$9.60$19.20256000
70GLM-4-AirXZhipu AI$10.00$10.008000
71GLM-ASR-2512Zhipu AI$16.00$0.008000
72ERNIE 5.1Baidu$22.00$22.000
73ERNIE 5.0Baidu$40.00$40.000
74GLM-4VZhipu AI$50.00$50.002000
75GLM-4-VoiceZhipu AI$80.00$80.008000
76GLM-4-0520Zhipu AI$100.00$50.00128000
-
- - - -
-

💳 腾讯云套餐订阅价

-

以下为套餐订阅价，不参与按模型输入/输出单价排行。

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
套餐月费月额度上下文上限覆盖模型
Hy Token Plan Lite¥28.00/月3500万 Tokens/月256K1 个（hy3-preview）
通用 Token Plan Lite¥39.00/月3500万 Tokens/月-10 个（tc-code-latest, minimax-m2.5, minimax-m2.7）
Hy Token Plan Standard¥78.00/月1亿 Tokens/月256K1 个（hy3-preview）
通用 Token Plan Standard¥99.00/月1亿 Tokens/月-10 个（tc-code-latest, minimax-m2.5, minimax-m2.7）
Hy Token Plan Pro¥238.00/月3.2亿 Tokens/月256K1 个（hy3-preview）
通用 Token Plan Pro¥299.00/月3.2亿 Tokens/月-10 个（tc-code-latest, minimax-m2.5, minimax-m2.7）
Hy Token Plan Max¥468.00/月6.5亿 Tokens/月256K1 个（hy3-preview）
通用 Token Plan Max¥599.00/月6.5亿 Tokens/月-10 个（tc-code-latest, minimax-m2.5, minimax-m2.7）
-
- - - - -
-

☁️ 云厂商/官方平台(6 家)

- - - - - - - - - - - - - - - -
平台模型数最低价格平均价格
Moonshot3$2.00$4.17
DeepSeek2$0.14$0.29
OpenAI3$0.75$2.75
Baidu Qianfan44$0.00$1.41
Zhipu29$0.18$10.99
ByteDance Volcano43$0.15$2.11
-
- - - - -
-

🔀 中转/聚合平台(1 家)

- - - - - -
平台模型数最低价格平均价格
OpenRouter380$0.00$0.02
-
- - -
-

📌 本报告由 LLM Intelligence Hub 自动生成 · 2026-05-13

-

价格单位:USD/1M tokens

-
- -
- - \ No newline at end of file diff --git a/reports/daily/models.json b/reports/daily/models.json deleted file mode 100644 index 0c20176..0000000 --- a/reports/daily/models.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "free": 1, - "generated_at": "2026-05-08T13:47:39+08:00", - "models": [ - { - "id": "openai/gpt-4o", - "context_length": 128000, - "pricing": { - "input": 2.5, - "output": 10 - } - }, - { - "id": "anthropic/claude-3.5-sonnet:free", - "context_length": 200000, - "pricing": {} - } - ], - "paid": 1, - "total": 2 -} diff --git a/reports/openclaw/2026-05-07-2250-review.md b/reports/openclaw/2026-05-07-2250-review.md deleted file mode 100644 index f2515a2..0000000 --- a/reports/openclaw/2026-05-07-2250-review.md +++ /dev/null @@ -1,119 +0,0 @@ -# OpenClaw Multi Review — 2026-05-07 22:50 - -## Executive Summary - -项目完成度：**Phase 1 架构就绪，数据链路跑通，但资产极度单薄**。 - -- 核心代码（采集器、数据库 schema、日报生成器、Explorer 脚手架）全部存在且可编译运行 ✅ -- 验证执行器已项目本地化，8/10 任务通过 ✅ -- 实际数据规模：2 个模型（gpt-4o + claude-3.5-sonnet:free）—— **严重偏离目标 500+** -- 最后提交：3 天前（2026-05-04），`PRD.md` 未提交，处于 unstaged 状态 -- T-1.1 和 T-3.2 失败根因：验证命令用了 `rg`（ripgrep）但系统未安装 —— 非业务问题，属工具链配置问题 - -**结论**：从文档阶段进入实现阶段，但实现深度接近为零。Phase 1 的"数据采集、存储、报告"三条主链路框架已搭，但数据资产空白。 - ---- - -## 当前真实阶段 - -``` -[文档] ████████████████████ 100% PRD / 市场分析 / 技术设计 -[代码] ████████░░░░░░░░░░░░ 40% 脚手架存在，核心逻辑空 -[数据] ███░░░░░░░░░░░░░░░░░ 5% 2 模型 vs 目标 500+ -[验证] ████████████████░░░░ 80% 8/10 通过（工具问题导致 2 fail） -``` - ---- - -## 验证命令执行结果 - -| 命令 | 结果 | 说明 | -|------|------|------| -| `go build ./scripts/fetch_openrouter.go` | ✅ PASS | 编译通过，无错误 | -| `test -d reports/daily && echo exists` | ✅ PASS | 日报目录存在 | -| `test -f scripts/fetch_openrouter.go` | ✅ PASS | 采集器存在 | -| `test -f frontend/src/pages/Explorer.tsx` | ✅ PASS | Explorer 脚手架存在 | -| `go run verification_executor.go` | ⚠️ 8/10 | 2 个 task 失败因 `rg` 未安装 | -| `bash scripts/verify_t35.sh` | ✅ PASS | T-3.5 所有子检查通过 | -| `bash scripts/verify_t32.sh` | ✅ PASS | T-3.2 所有子检查通过 | - ---- - -## 已完成项 - -1. **OpenRouter 采集器** — `scripts/fetch_openrouter.go` 存在、可编译、含测试 -2. **PostgreSQL Migration** — `db/migrations/001_phase1_core_tables.sql` 存在（含 models/model_prices/report_runs 表） -3. **日报生成器** — `scripts/generate_daily_report.go` 存在，可产出 `reports/daily/daily_report_*.md` -4. **Explorer 脚手架** — `frontend/src/pages/Explorer.tsx` 存在，含筛选/卡片/表格视图框架，含 `latest_models.json` 优先 + `models.json` fallback -5. **latest_models.json 定价归一化** — 免费模型 `pricing.input/output` 均显式为 0 -6. **项目本地 TASKS.md + GOALS.md + OPENCLAW_EXECUTION.md** — 角色拆分明确 -7. **验证执行器项目本地化** — `scripts/verification_executor.go` 可独立运行 -8. **T-3.2 Dashboard 最小组件** — 表格视图、免费 badge、价格渲染、图表占位均存在（`verify_t32.sh` 通过） - ---- - -## 未完成项 - -1. **数据资产空白** — 真实模型数 2，目标 500+；采集器未接入真实 API，数据为种子占位 -2. **Explorer 数据源未接入** — `mapAPIResponseToModels` 注释掉了，TODO 写着"接入真实 API" -3. **Dashboard 无真实组件** — 所有 Dashboard 组件均为占位（`price-trend-chart` 等） -4. **无定时任务** — 日报生成为手动触发，无 cron/调度机制 -5. **数据库未实际运行** — migration 文件存在，但无 PostgreSQL 连接验证 -6. **无部署机制** — 无 Dockerfile、docker-compose 或部署脚本 -7. **`PRD.md` 未提交** — unstaged 新文件，与最近一次提交（3 天前）存在状态断层 -8. **最后代码提交 3 天前** — 无持续开发节奏 - ---- - -## 伪进展 / 文档与实现不一致项 - -| 文档声明 | 实际情况 | 差距 | -|----------|----------|------| -| "模型商覆盖率 20+ 厂商" | 当前只有 2 个模型（OpenAI + Anthropic） | 真实覆盖率 < 10% | -| "模型总量 500+" | 只有 2 个模型条目 | 0.4% | -| "每日 08:00 自动触发报告" | 手动运行 generate_daily_report.go | 无自动化 | -| "30+ 云平台/中转站" | 只有 OpenRouter 一个数据源 | 无多源聚合 | -| "Explorer 接入真实 API" | 代码注释为占位 + TODO | 未实现 | - ---- - -## 最大 5 个关键 Gap - -**Gap 1 — 数据资产空白（最严重）** -采集器代码存在但未接入真实 API，数据只有 2 条种子记录。Phase 1 的核心价值——覆盖全球 500+ 模型——完全未实现。 - -**Gap 2 — Explorer 数据层断连** -`frontend/src/pages/Explorer.tsx` 标注"接入真实 API"，实际 `mapAPIResponseToModels` 为占位实现，页面会渲染但无真实数据流入。 - -**Gap 3 — 无调度机制** -日报生成为手动触发，无法实现 PRD 承诺的"每日 08:00 自动触发"。用户必须手动运行才有报告。 - -**Gap 4 — 多数据源未开始** -Phase 1 要求覆盖 20+ 厂商 + 30+ 平台，当前只有 OpenRouter 采集器。硅基流动、Kimi、DeepSeek、阿里云等均无接入。 - -**Gap 5 — 验证器工具依赖问题** -`verification_executor.go` 使用 `rg`（ripgrep）执行 T-1.1 和 T-3.2 的验证命令，但系统未安装 `rg`，导致任务失败而非真正缺失功能。这会误导任务状态。 - ---- - -## 下一轮最值得推进的 3 件事 - -1. **接入 OpenRouter 真实 API，填充 100+ 模型数据** - - 当前采集器是脚手架，需要将 `fetch_openrouter.go` 连接真实 endpoint - - 验证：`go run scripts/fetch_openrouter.go` 应产出含 100+ 模型的 JSON - - 优先级：P0（数据是 Phase 1 核心价值） - -2. **完成 Explorer 数据绑定** - - 实现 `mapAPIResponseToModels`，从 `latest_models.json` 真实读取并渲染 - - 验证：浏览器打开 Explorer 应能看到真实模型列表，而非空白/占位 - - 优先级：P0（前台是唯一用户可见产出） - -3. **修复验证器 `rg` 依赖问题 + 建立 commit 节奏** - - 将 `rg` 替换为 `grep`（系统自带），避免工具导致的验证失败 - - `PRD.md` 应立即提交，停止 unstaged 状态 - - 目标：每日至少一次 commit，推进节奏可见 - - 优先级：P1（影响开发状态可信度） - ---- - -*Review 时间：2026-05-07 22:48 Asia/Shanghai | 验证器：scripts/verification_executor.go | 任务总数：10* \ No newline at end of file diff --git a/reports/openclaw/2026-05-08-0905-review.md b/reports/openclaw/2026-05-08-0905-review.md deleted file mode 100644 index 5b39b7e..0000000 --- a/reports/openclaw/2026-05-08-0905-review.md +++ /dev/null @@ -1,134 +0,0 @@ -# OpenClaw Multi Review — 2026-05-08 09:05 - -## Executive Summary - -项目完成度：**Phase 1 骨架 100% 就绪，数据资产仍为种子级别，验证器工具链缺陷持续误导状态**。 - -- 10/10 任务的功能实体全部存在 ✅（采集器、migration、日报、Explorer、验证器、任务清单） -- `verification_executor.go` 仍因 `rg` 未安装错误报告 2 个 FAIL（T-1.1、T-3.2）— 这是**工具链问题，不是业务问题** -- 手动验收脚本 `verify_t32.sh` ~ `verify_t35.sh` **全部 PASS** -- 真实模型数：**2 条**（vs PRD 目标 500+）— **数据资产空白仍是最大 gap** -- 最后代码提交：**4 天前**（2026-05-04），`PRD.md` 修改（补充 Phase 1 范围/非目标/验收标准）未提交，处于 unstaged -- `OPENROUTER_API_KEY` 未配置，采集器只能回退到硬编码种子数据 - -**结论**：从"文档阶段→实现阶段"的切换已完成，实现骨架全部搭好。当前瓶颈从"缺代码"变为"缺真实数据"和"缺运行环境（API Key + PostgreSQL + 调度）"。 - ---- - -## 当前真实阶段 - -``` -[文档] ████████████████████ 100% PRD / 市场分析 / 技术设计 / 执行说明 -[骨架] ████████████████████ 100% 采集器 / migration / 日报 / Explorer / 验证器 -[数据] ███░░░░░░░░░░░░░░░░░ 5% 2 模型 vs 目标 500+ -[连接] ██████░░░░░░░░░░░░░░ 30% 采集器→DB 未接通；Explorer→API 未接通；无自动调度 -[验证] ████████████████░░░░ 80% 8/10 自动通过（2 个 rg 误报），4/4 手动脚本通过 -``` - ---- - -## 本次执行的验证命令与结果 - -| 命令 | 结果 | 说明 | -|------|------|------| -| `git status --short` | ⚠️ | PRD.md 修改未提交；大量新增文件未跟踪 | -| `git log --oneline -5` | ⚠️ | 最后提交 4 天前（2026-05-04） | -| `go build ./scripts/fetch_openrouter.go` | ✅ PASS | 编译通过，无错误 | -| `bash scripts/test.sh` | ✅ PASS | 单元测试通过（2 模型种子数据） | -| `go run verification_executor.go` | ⚠️ 8/10 | T-1.1、T-3.2 FAIL（rg exit 127），其余 PASS | -| `bash scripts/verify_t32.sh` | ✅ PASS | 表格、badge、chart、react 占位均通过 | -| `bash scripts/verify_t33.sh` | ✅ PASS | filterModels、shared variable、dual-view 均通过 | -| `bash scripts/verify_t34.sh` | ✅ PASS | JSON schema、mapping、import 均通过 | -| `bash scripts/verify_t35.sh` | ✅ PASS | latest_models.json 写入、fallback、pricing 归一化均通过 | -| `test -z "$OPENROUTER_API_KEY" && echo 未设置` | ❌ 未设置 | 无法连接真实 API | -| `find db/migrations -name "*.sql"` | ✅ PASS | 001_phase1_core_tables.sql 存在 | -| `ls reports/daily/` | ✅ 4 文件 | 3 份日报 + 1 份 models.json | - ---- - -## 已完成项 - -1. **T-1.1 Phase 1 范围冻结** — PRD.md 已补充 Phase 1 范围/非目标/验收标准（功能完成，仅未提交） -2. **T-1.2 文档冲突清理** — `FEATURE_LIST.md` / `TECHNICAL_DESIGN.md` 中无"等待技术设计完成后启动"等冲突标记 -3. **T-2.1 OpenRouter 采集器** — `fetch_openrouter.go` 存在、可编译、含测试、含重试/超时/健壮解析 -4. **T-2.2 PostgreSQL migration** — `db/migrations/001_phase1_core_tables.sql` 含 models / model_prices / report_runs 三张表 + 索引 -5. **T-2.3 日报生成器** — `generate_daily_report.go` 存在，可产出 `reports/daily/daily_report_*.md` + `latest_models.json` -6. **T-3.1 Explorer 页面脚手架** — `frontend/src/pages/Explorer.tsx` 存在，React + TypeScript -7. **T-3.2 Dashboard 最小组件** — 表格视图、卡片视图、免费 badge、价格渲染、图表占位均存在（`verify_t32.sh` 通过） -8. **T-3.3 筛选过滤逻辑** — provider / modality / maxInputPrice / keyword 四项筛选，shared variable 设计（`verify_t33.sh` 通过） -9. **T-3.4 Explorer 接入 Schema JSON** — `mapAPIResponseToModels` 存在，`models.json` 含 5 模型，schema 合规（`verify_t34.sh` 通过） -10. **T-3.5 日报→Explorer 数据同步** — `latest_models.json` 优先 + `models.json` fallback，免费模型 pricing 显式归一化为 0（`verify_t35.sh` 通过） -11. **T-4.1 项目本地任务清单** — `GOALS.md` + `TASKS.md` 存在 -12. **T-4.2 验证器项目本地化** — `verification_executor.go` 默认读取本项目 `TASKS.md` -13. **T-4.3 项目执行说明** — `OPENCLAW_EXECUTION.md` 存在，角色拆分明确 - ---- - -## 未完成项 - -1. **PRD.md 修改未提交** — Phase 1 范围/非目标/验收标准已写入但未 `git add` -2. **数据资产空白** — 真实模型数 2，目标 500+；`OPENROUTER_API_KEY` 未配置 -3. **采集器→PostgreSQL 未接通** — `summarize()` 里 TODO 写着"接入 PostgreSQL"，当前只写 JSON 文件 -4. **Explorer 无实时数据入口** — `mapAPIResponseToModels` 从本地 JSON 加载，无 API 后端 -5. **无自动调度** — 日报为手动触发，无 cron / systemd timer / CI schedule -6. **无部署配置** — 无 Dockerfile、docker-compose、部署脚本 -7. **无前端构建系统** — `frontend/` 无 `package.json` / `tsconfig.json` / `vite.config.*`，无法独立构建 -8. **验证器 `rg` 依赖未修复** — 持续导致 T-1.1 / T-3.2 误报 FAIL - ---- - -## 伪进展 / 文档与实现不一致项 - -| 文档/PRD 声明 | 实际情况 | 差距 | -|---------------|----------|------| -| "模型商覆盖率 20+ 厂商" | 当前只有 2 个模型（OpenAI + Anthropic） | 真实覆盖率 ≈ 0% | -| "模型总量 500+" | 只有 2 个模型条目（种子数据） | 0.4% | -| "每日 08:00 自动触发报告" | 手动运行 `generate_daily_report.go` | 无自动化 | -| "30+ 云平台/中转站" | 只有 OpenRouter 一个数据源 | 无多源聚合 | -| "采集器抓取结果写入 PostgreSQL" | 采集器只写入 JSON 文件，DB 未接通 | `summarize()` 含 TODO | -| "Explorer 接入真实 API" | 从本地 `latest_models.json` / `models.json` 加载 | 无后端 API | -| "PRD.md 含 Phase 1 验收标准" | 内容已写但处于 unstaged 修改 | 未提交 | - ---- - -## 最大 5 个关键 Gap - -**Gap 1 — 数据资产空白（最严重，P0）** -采集器代码完整但未接入真实 API，数据只有 2 条种子记录。Phase 1 的核心价值——覆盖全球 500+ 模型——完全未实现。根因：`OPENROUTER_API_KEY` 未配置。 - -**Gap 2 — 采集器→数据库未接通（P0）** -`fetch_openrouter.go` 的 `summarize()` 明确 TODO"接入 PostgreSQL"，当前只输出 JSON。即使拿到 API Key，数据也无法入库，日报生成器同样只读 JSON 不写 DB。 - -**Gap 3 — 前端无构建系统（P1）** -`frontend/src/pages/Explorer.tsx` 存在且逻辑正确，但整个 `frontend/` 目录没有 `package.json`、`tsconfig.json`、构建脚本。这意味着页面无法被独立构建、测试或部署，目前只是"代码片段"而非"可运行前端"。 - -**Gap 4 — 无自动调度机制（P1）** -日报生成为手动触发，无法实现 PRD 承诺的"每日 08:00 自动触发"。无 cron、无 CI schedule、无 systemd timer。 - -**Gap 5 — 验证器 `rg` 依赖持续误报（P1）** -`verification_executor.go` 使用 `rg` 执行 T-1.1 和 T-3.2 验证命令，但执行环境未安装 ripgrep，导致 `exit status 127`。这连续两次 review 都将真实 PASS 的任务标记为 FAIL，状态可信度受损。 - ---- - -## 下一轮最值得推进的 3 件事 - -1. **配置 `OPENROUTER_API_KEY` 并接入真实 API，填充 100+ 模型数据** - - 当前采集器是完整脚手架，只差 API Key - - 验证：`go run scripts/fetch_openrouter.go -api-key $KEY` 应产出含 100+ 模型的 JSON - - 同时完成 `summarize()` 里的 PostgreSQL TODO，让数据真正入库 - - 优先级：P0（数据是 Phase 1 核心价值） - -2. **补齐前端构建系统（package.json + tsconfig + 构建脚本）** - - `Explorer.tsx` 逻辑已完整且通过全部验收脚本，但缺构建骨架 - - 验证：`cd frontend && npm install && npm run build` 应成功 - - 优先级：P1（让前台从"代码片段"变成"可运行产物"） - -3. **修复验证器 `rg` 依赖 + 建立 commit 节奏** - - 将 `rg` 替换为 `grep`（系统自带），或增加 toolchain readiness check - - `PRD.md` 修改应立即提交，停止 unstaged 状态 - - 目标：每日至少一次 commit，推进节奏可见 - - 优先级：P1（影响开发状态可信度和 review 准确性） - ---- - -*Review 时间：2026-05-08 09:05 Asia/Shanghai | 验证器：scripts/verification_executor.go | 手动验收脚本：verify_t32.sh ~ verify_t35.sh | 任务总数：10* diff --git a/reports/openclaw/2026-05-08-0912-review.md b/reports/openclaw/2026-05-08-0912-review.md deleted file mode 100644 index 432455f..0000000 --- a/reports/openclaw/2026-05-08-0912-review.md +++ /dev/null @@ -1,157 +0,0 @@ -# OpenClaw Multi Review — 2026-05-08 09:12 - -## Executive Summary - -**状态冻结判定**：距上一次 review（09:05）仅 7 分钟，零 commit、零文件变更、零环境变化。本次 review 是 cron 触发的时间驱动 review，但仓库真实状态未发生任何推进。 - -- 10/10 任务的功能实体全部存在 ✅（与 09:05 review 完全一致） -- `verification_executor.go` 仍因 `rg` 未安装错误报告 2 个 FAIL（T-1.1、T-3.2）— **工具链问题持续存在，未修复** -- 手动验收脚本 `verify_t32.sh` ~ `verify_t35.sh` **全部 PASS**（无变化） -- 真实模型数：**2 条**（种子数据）vs PRD 目标 500+ — **数据资产空白仍是最大 gap，未改善** -- `OPENROUTER_API_KEY` 未配置 — **未改善** -- `PRD.md` 修改（Phase 1 范围/非目标/验收标准）仍处 unstaged — **未提交** -- 最后代码提交：**4 天前**（2026-05-04）— **无推进** - -**结论**：这是一个典型的"空转 review"——cron 按时触发，但项目无实质进展。所有 gap 与 09:05 review 100% 复刻。OpenClaw cron review 机制本身也暴露出一个新缺口：时间驱动 review 在没有代码/配置/数据变动时，产出重复结论，浪费 token 与注意力。 - ---- - -## 当前真实阶段 - -``` -[文档] ████████████████████ 100% PRD / 市场分析 / 技术设计 / 执行说明 -[骨架] ████████████████████ 100% 采集器 / migration / 日报 / Explorer / 验证器 -[数据] ███░░░░░░░░░░░░░░░░░ 5% 2 模型 vs 目标 500+ -[连接] ██████░░░░░░░░░░░░░░ 30% 采集器→DB 未接通；Explorer→API 未接通；无自动调度 -[验证] ████████████████░░░░ 80% 8/10 自动通过（2 个 rg 误报），4/4 手动脚本通过 -[推进] ░░░░░░░░░░░░░░░░░░░░ 0% 4 天零 commit，无任何实质性推进 -``` - ---- - -## 本次执行的验证命令与结果 - -| 命令 | 结果 | 说明 | -|------|------|------| -| `git status --short` | ⚠️ | PRD.md 修改未提交；17 个未跟踪文件；与 09:05 完全一致 | -| `git log --since="2026-05-08 09:05" --oneline` | ❌ | **零新提交**，距上次 review 无变化 | -| `git log --oneline -3` | ⚠️ | 最后提交仍为 2026-05-04（dbdf13e），已 4 天 | -| `go build ./scripts/fetch_openrouter.go` | ✅ PASS | 编译通过，无变化 | -| `bash scripts/test.sh` | ✅ PASS | 单元测试通过，无变化 | -| `go run verification_executor.go` | ⚠️ 8/10 | T-1.1、T-3.2 FAIL（rg exit 127），**与 09:05 完全一致** | -| `bash scripts/verify_t32.sh` | ✅ PASS | 无变化 | -| `bash scripts/verify_t33.sh` | ✅ PASS | 无变化 | -| `bash scripts/verify_t34.sh` | ✅ PASS | 无变化 | -| `bash scripts/verify_t35.sh` | ✅ PASS | 无变化 | -| `printenv \| grep OPENROUTER_API_KEY` | ❌ 未设置 | **未配置，无变化** | -| `find db/migrations -name "*.sql"` | ✅ PASS | 001_phase1_core_tables.sql 存在，无变化 | -| `ls reports/daily/` | ✅ 4 文件 | 3 份日报 + models.json，无变化 | -| `test -f frontend/package.json` | ❌ 不存在 | **前端仍无可构建系统**，无变化 | - ---- - -## 已完成项 - -与 09:05 review 完全一致，无新增完成项： - -1. **T-1.1 Phase 1 范围冻结** — PRD.md 已补充 Phase 1 范围/非目标/验收标准（内容完成，仅未提交） -2. **T-1.2 文档冲突清理** — 无冲突标记 -3. **T-2.1 OpenRouter 采集器** — `fetch_openrouter.go` 存在、可编译、含测试 -4. **T-2.2 PostgreSQL migration** — `db/migrations/001_phase1_core_tables.sql` 完整 -5. **T-2.3 日报生成器** — `generate_daily_report.go` 存在且可运行 -6. **T-3.1 Explorer 页面脚手架** — `Explorer.tsx` 存在 -7. **T-3.2 Dashboard 最小组件** — 表格/卡片/免费 badge/图表占位均存在 -8. **T-3.3 筛选过滤逻辑** — provider/modality/price/keyword 四项筛选 -9. **T-3.4 Explorer 接入 Schema JSON** — `mapAPIResponseToModels` 存在 -10. **T-3.5 日报→Explorer 数据同步** — `latest_models.json` 优先 + fallback -11. **T-4.1 项目本地任务清单** — `GOALS.md` + `TASKS.md` 存在 -12. **T-4.2 验证器项目本地化** — 默认读取本项目 `TASKS.md` -13. **T-4.3 项目执行说明** — `OPENCLAW_EXECUTION.md` 存在 - ---- - -## 未完成项 - -与 09:05 review 完全一致，无改善： - -1. **PRD.md 修改未提交** — 4 天 unstaged -2. **数据资产空白** — 真实模型数 2，目标 500+；`OPENROUTER_API_KEY` 未配置 -3. **采集器→PostgreSQL 未接通** — `summarize()` 里 TODO 未实现 -4. **Explorer 无实时数据入口** — 只读本地 JSON，无 API 后端 -5. **无自动调度** — 日报为手动触发，无 cron / CI schedule -6. **无部署配置** — 无 Dockerfile、docker-compose -7. **无前端构建系统** — `frontend/` 无 `package.json` / `tsconfig.json` / 构建脚本 -8. **验证器 `rg` 依赖未修复** — 连续两次 review（09:05、09:12）均误报 FAIL - ---- - -## 伪进展 / 文档与实现不一致项 - -与 09:05 review 完全一致： - -| 文档/PRD 声明 | 实际情况 | 差距 | -|---------------|----------|------| -| "模型商覆盖率 20+ 厂商" | 当前只有 2 个模型（OpenAI + Anthropic） | 真实覆盖率 ≈ 0% | -| "模型总量 500+" | 只有 2 个模型条目（种子数据） | 0.4% | -| "每日 08:00 自动触发报告" | 手动运行 `generate_daily_report.go` | 无自动化 | -| "30+ 云平台/中转站" | 只有 OpenRouter 一个数据源 | 无多源聚合 | -| "采集器抓取结果写入 PostgreSQL" | 采集器只写入 JSON 文件，DB 未接通 | `summarize()` 含 TODO | -| "Explorer 接入真实 API" | 从本地 `latest_models.json` / `models.json` 加载 | 无后端 API | -| "PRD.md 含 Phase 1 验收标准" | 内容已写但处于 unstaged 修改 | 未提交 | - ---- - -## 最大 5 个关键 Gap - -**Gap 1 — 数据资产空白（最严重，P0）** -采集器代码完整但未接入真实 API，数据只有 2 条种子记录。Phase 1 的核心价值——覆盖全球 500+ 模型——完全未实现。根因：`OPENROUTER_API_KEY` 未配置。**4 天零改善。** - -**Gap 2 — 采集器→数据库未接通（P0）** -`fetch_openrouter.go` 的 `summarize()` 明确 TODO"接入 PostgreSQL"，当前只输出 JSON。即使拿到 API Key，数据也无法入库。**4 天零改善。** - -**Gap 3 — 前端无构建系统（P1）** -`frontend/` 无 `package.json`、`tsconfig.json`、构建脚本。页面无法被独立构建、测试或部署。**4 天零改善。** - -**Gap 4 — 无自动调度机制（P1）** -日报生成为手动触发，无法实现 PRD 承诺的"每日 08:00 自动触发"。**4 天零改善。** - -**Gap 5 — 验证器 `rg` 依赖持续误报（P1）** -连续两次 review（09:05、09:12）均因 `rg` 未安装将真实 PASS 任务标记为 FAIL。状态可信度受损。**零修复动作。** - ---- - -## 本轮 review 的特有问题：空转判定 - -本次 review 暴露出一个**流程层面**的问题：cron 触发的时间驱动 review 在仓库状态未变化时，产出了与 7 分钟前完全相同的结论。这造成： - -- **Token 浪费**：两次 review 读取、分析、写盘的计算量完全重复 -- **注意力稀释**：用户看到两份几乎一样的报告，难以分辨是否有新进展 -- **行动噪音**：如果 review 自动触发子 agent 修复，会导致重复任务 spawn - -**建议**：为 cron review 增加"delta gate"——如果自上次 review 以来 git 无新 commit、无文件变更、无环境变量变化，则输出极简摘要并跳过全量分析。 - ---- - -## 下一轮最值得推进的 3 件事 - -与 09:05 review 推荐完全一致，因为**没有任何进展**： - -1. **配置 `OPENROUTER_API_KEY` 并接入真实 API，填充 100+ 模型数据** - - 当前采集器是完整脚手架，只差 API Key - - 同时完成 `summarize()` 里的 PostgreSQL TODO，让数据真正入库 - - 优先级：P0（数据是 Phase 1 核心价值） - -2. **补齐前端构建系统（package.json + tsconfig + 构建脚本）** - - `Explorer.tsx` 逻辑已完整且通过全部验收脚本，但缺构建骨架 - - 验证：`cd frontend && npm install && npm run build` 应成功 - - 优先级：P1 - -3. **修复验证器 `rg` 依赖 + 建立 commit 节奏** - - 将 `TASKS.md` 中的 `rg` 命令替换为 `grep -n` - - `PRD.md` 修改应立即提交，停止 unstaged 状态 - - 目标：每日至少一次 commit，推进节奏可见 - - 优先级：P1 - ---- - -*Review 时间：2026-05-08 09:12 Asia/Shanghai | 验证器：scripts/verification_executor.go | 手动验收脚本：verify_t32.sh ~ verify_t35.sh | 任务总数：10 | Delta vs 上次 review：零变化* diff --git a/reports/openclaw/2026-05-08-0936-review.md b/reports/openclaw/2026-05-08-0936-review.md deleted file mode 100644 index 508007c..0000000 --- a/reports/openclaw/2026-05-08-0936-review.md +++ /dev/null @@ -1,158 +0,0 @@ -# OpenClaw Multi Review — 2026-05-08 09:36 - -## Executive Summary - -**空转判定：确认。** 距上一次 review（09:12）24 分钟，零 commit、零文件变更、零环境变化。本次 review 是 cron 触发的第 3 次时间驱动 review（今日 09:05、09:12、09:36），仓库真实状态未发生任何推进。 - -- 10/10 任务的功能实体全部存在 ✅（与 09:12 review 完全一致） -- `verification_executor.go` 仍因 `rg` 未安装错误报告 2 个 FAIL（T-1.1、T-3.2）— **工具链问题持续存在，连续 3 次 review 未修复** -- 手动验收脚本 `verify_t32.sh` ~ `verify_t35.sh` **全部 PASS**（无变化） -- 真实模型数：**2 条**（种子数据）vs PRD 目标 500+ — **数据资产空白仍是最大 gap，未改善** -- `OPENROUTER_API_KEY` 未配置 — **未改善** -- `PRD.md` 修改（Phase 1 范围/非目标/验收标准）仍处 unstaged — **未提交，第 4 天** -- 最后代码提交：**4 天前**（2026-05-04）— **零推进** - -**结论**：这是连续第 3 次空转 review。 cron review 机制的时间驱动特性在没有代码/配置/数据变动时，持续产出重复结论，浪费 token 与注意力。 - ---- - -## 当前真实阶段 - -``` -[文档] ████████████████████ 100% PRD / 市场分析 / 技术设计 / 执行说明 -[骨架] ████████████████████ 100% 采集器 / migration / 日报 / Explorer / 验证器 -[数据] ███░░░░░░░░░░░░░░░░░ 5% 2 模型 vs 目标 500+ -[连接] ██████░░░░░░░░░░░░░░ 30% 采集器→DB 未接通；Explorer→API 未接通；无自动调度 -[验证] ████████████████░░░░ 80% 8/10 自动通过（2 个 rg 误报），4/4 手动脚本通过 -[推进] ░░░░░░░░░░░░░░░░░░░░ 0% 4 天零 commit，无任何实质性推进 -``` - ---- - -## 本次执行的验证命令与结果 - -| 命令 | 结果 | 说明 | -|------|------|------| -| `git status --short` | ⚠️ | PRD.md 修改未提交；17 个未跟踪文件；与 09:12 完全一致 | -| `git log --since="2026-05-08 09:12" --oneline` | ❌ | **零新提交**，距上次 review 无变化 | -| `git log --oneline -3` | ⚠️ | 最后提交仍为 2026-05-04（dbdf13e），已 4 天 | -| `which rg` | ❌ 未安装 | **环境零变化**，持续导致 T-1.1 / T-3.2 误报 | -| `go build ./scripts/fetch_openrouter.go` | ✅ PASS | 编译通过，无变化 | -| `bash scripts/test.sh` | ✅ PASS | 单元测试通过，无变化 | -| `go run verification_executor.go` | ⚠️ 8/10 | T-1.1、T-3.2 FAIL（rg exit 127），**连续 3 次 review 完全一致** | -| `bash scripts/verify_t32.sh` | ✅ PASS | 无变化 | -| `bash scripts/verify_t33.sh` | ✅ PASS | 无变化 | -| `bash scripts/verify_t34.sh` | ✅ PASS | 无变化 | -| `bash scripts/verify_t35.sh` | ✅ PASS | 无变化 | -| `printenv \| grep OPENROUTER_API_KEY` | ❌ 未设置 | **未配置，无变化** | -| `find db/migrations -name "*.sql"` | ✅ PASS | 001_phase1_core_tables.sql 存在，无变化 | -| `ls reports/daily/` | ✅ 4 文件 | 3 份日报 + models.json，无变化 | -| `test -f frontend/package.json` | ❌ 不存在 | **前端仍无可构建系统**，无变化 | - ---- - -## 已完成项 - -与 09:12 review 完全一致，无新增完成项： - -1. **T-1.1 Phase 1 范围冻结** — PRD.md 已补充 Phase 1 范围/非目标/验收标准（内容完成，仅未提交） -2. **T-1.2 文档冲突清理** — 无冲突标记 -3. **T-2.1 OpenRouter 采集器** — `fetch_openrouter.go` 存在、可编译、含测试 -4. **T-2.2 PostgreSQL migration** — `db/migrations/001_phase1_core_tables.sql` 完整 -5. **T-2.3 日报生成器** — `generate_daily_report.go` 存在且可运行 -6. **T-3.1 Explorer 页面脚手架** — `Explorer.tsx` 存在 -7. **T-3.2 Dashboard 最小组件** — 表格/卡片/免费 badge/图表占位均存在 -8. **T-3.3 筛选过滤逻辑** — provider/modality/price/keyword 四项筛选 -9. **T-3.4 Explorer 接入 Schema JSON** — `mapAPIResponseToModels` 存在 -10. **T-3.5 日报→Explorer 数据同步** — `latest_models.json` 优先 + fallback -11. **T-4.1 项目本地任务清单** — `GOALS.md` + `TASKS.md` 存在 -12. **T-4.2 验证器项目本地化** — 默认读取本项目 `TASKS.md` -13. **T-4.3 项目执行说明** — `OPENCLAW_EXECUTION.md` 存在 - ---- - -## 未完成项 - -与 09:12 review 完全一致，无改善： - -1. **PRD.md 修改未提交** — 4 天 unstaged -2. **数据资产空白** — 真实模型数 2，目标 500+；`OPENROUTER_API_KEY` 未配置 -3. **采集器→PostgreSQL 未接通** — `summarize()` 里 TODO 未实现 -4. **Explorer 无实时数据入口** — 只读本地 JSON，无 API 后端 -5. **无自动调度** — 日报为手动触发，无 cron / CI schedule -6. **无部署配置** — 无 Dockerfile、docker-compose -7. **无前端构建系统** — `frontend/` 无 `package.json` / `tsconfig.json` / 构建脚本 -8. **验证器 `rg` 依赖未修复** — 连续 3 次 review（09:05、09:12、09:36）均误报 FAIL - ---- - -## 伪进展 / 文档与实现不一致项 - -与 09:12 review 完全一致： - -| 文档/PRD 声明 | 实际情况 | 差距 | -|---------------|----------|------| -| "模型商覆盖率 20+ 厂商" | 当前只有 2 个模型（OpenAI + Anthropic） | 真实覆盖率 ≈ 0% | -| "模型总量 500+" | 只有 2 个模型条目（种子数据） | 0.4% | -| "每日 08:00 自动触发报告" | 手动运行 `generate_daily_report.go` | 无自动化 | -| "30+ 云平台/中转站" | 只有 OpenRouter 一个数据源 | 无多源聚合 | -| "采集器抓取结果写入 PostgreSQL" | 采集器只写入 JSON 文件，DB 未接通 | `summarize()` 含 TODO | -| "Explorer 接入真实 API" | 从本地 `latest_models.json` / `models.json` 加载 | 无后端 API | -| "PRD.md 含 Phase 1 验收标准" | 内容已写但处于 unstaged 修改 | 未提交 | - ---- - -## 最大 5 个关键 Gap - -**Gap 1 — 数据资产空白（最严重，P0）** -采集器代码完整但未接入真实 API，数据只有 2 条种子记录。Phase 1 的核心价值——覆盖全球 500+ 模型——完全未实现。根因：`OPENROUTER_API_KEY` 未配置。**连续 3 次 review 零改善。** - -**Gap 2 — 采集器→数据库未接通（P0）** -`fetch_openrouter.go` 的 `summarize()` 明确 TODO"接入 PostgreSQL"，当前只输出 JSON。即使拿到 API Key，数据也无法入库。**连续 3 次 review 零改善。** - -**Gap 3 — 前端无构建系统（P1）** -`frontend/` 无 `package.json`、`tsconfig.json`、构建脚本。页面无法被独立构建、测试或部署。**连续 3 次 review 零改善。** - -**Gap 4 — 无自动调度机制（P1）** -日报生成为手动触发，无法实现 PRD 承诺的"每日 08:00 自动触发"。**连续 3 次 review 零改善。** - -**Gap 5 — 验证器 `rg` 依赖持续误报（P1）** -连续 3 次 review（09:05、09:12、09:36）均因 `rg` 未安装将真实 PASS 任务标记为 FAIL。状态可信度受损。**零修复动作。** - ---- - -## 本轮 review 的特有问题：连续空转确认 - -本次 review 是今日第 3 次 cron 触发 review（09:05、09:12、09:36），三次结论 100% 相同。这进一步确认： - -- **Token 浪费已实际发生 3 次**：三次 review 读取、分析、写盘的计算量完全重复 -- **注意力稀释效应加剧**：用户/父 agent 收到三份相同报告，"狼来了"效应升级 -- **Delta gate 缺失的代价可量化**：仅今日 3 次 review，预估额外消耗 >15k token，产出为零 - -**建议**：立即在 `OPENCLAW_MULTI_REVIEW_PROMPT.md` 中植入 delta gate，状态指纹未变时跳过全量分析。 - ---- - -## 下一轮最值得推进的 3 件事 - -与 09:12 review 推荐完全一致，因为**没有任何进展**： - -1. **配置 `OPENROUTER_API_KEY` 并接入真实 API，填充 100+ 模型数据** - - 当前采集器是完整脚手架，只差 API Key - - 同时完成 `summarize()` 里的 PostgreSQL TODO，让数据真正入库 - - 优先级：P0（数据是 Phase 1 核心价值） - -2. **补齐前端构建系统（package.json + tsconfig + 构建脚本）** - - `Explorer.tsx` 逻辑已完整且通过全部验收脚本，但缺构建骨架 - - 验证：`cd frontend && npm install && npm run build` 应成功 - - 优先级：P1 - -3. **修复验证器 `rg` 依赖 + 建立 commit 节奏** - - 将 `TASKS.md` 中的 `rg` 命令替换为 `grep -n` - - `PRD.md` 修改应立即提交，停止 unstaged 状态 - - 目标：每日至少一次 commit，推进节奏可见 - - 优先级：P1 - ---- - -*Review 时间：2026-05-08 09:36 Asia/Shanghai | 验证器：scripts/verification_executor.go | 手动验收脚本：verify_t32.sh ~ verify_t35.sh | 任务总数：10 | Delta vs 上次 review：零变化 | 今日空转次数：3/3* diff --git a/reports/openclaw/2026-05-08-1430-review.md b/reports/openclaw/2026-05-08-1430-review.md deleted file mode 100644 index 6759acb..0000000 --- a/reports/openclaw/2026-05-08-1430-review.md +++ /dev/null @@ -1,160 +0,0 @@ -# OpenClaw Review Report - -**Review Time**: 2026-05-08 14:30 Asia/Shanghai (2026-05-08 06:30 UTC) -**Trigger**: cron `llm-intelligence-afternoon-review` -**Reviewer**: OpenClaw Agent (llm-intelligence) - ---- - -## Executive Summary - -仓库距上次 commit（`ba054f0`，May 7）已有约 **28 小时**，且 `PRD.md` 的 Phase 1 范围/非目标/验收标准修改仍处于 **unstaged** 状态（4 天未 commit）。验证器 `verification_executor.go` 在 **非 dry-run 模式下仍为 8/10 PASS，2 个 FAIL 全部是 `rg` 缺失导致的 `exit status 127`（工具误报，非业务失败）**。 - -**核心判断**：Phase 1 骨架（采集器、migration、日报生成器、验证器）已落地，但 **真实数据链路因缺失 `OPENROUTER_API_KEY` 与 `DATABASE_URL` 而未打通**。前端 `Explorer.tsx` 存在但无 `package.json`，项目不可构建。项目处于"代码骨架完成，环境与集成未闭环"的阶段。 - ---- - -## 当前真实阶段判断 - -**阶段**：Phase 1 骨架搭建完成 → **环境与集成缺口阻塞中** - -- ✅ 本地任务体系（TASKS.md / GOALS.md / OPENCLAW_EXECUTION.md）已闭环 -- ✅ 验证器已本地化，默认读取本项目 TASKS.md -- ✅ OpenRouter 采集器 `scripts/fetch_openrouter.go` 存在且可编译、单测通过 -- ✅ PostgreSQL migration `db/migrations/001_phase1_core_tables.sql` 存在 -- ✅ 日报生成器 `scripts/generate_daily_report.go` 存在且可运行 -- ✅ 前端 Explorer.tsx 页面代码存在 -- ❌ 关键环境变量未配置，真实数据链路未跑通 -- ❌ 前端无构建系统，不可编译 -- ❌ PRD.md 修改未 commit，git 状态碎片化 - ---- - -## 本次执行的验证命令与结果 - -| # | 验证命令 | 结果 | 说明 | -|---|---------|------|------| -| 1 | `git status --short` | PRD.md 修改未 stage；7 个 untracked 文件 | 4 天无代码 commit | -| 2 | `git log --oneline -20` | 4 条 commit，最新 `ba054f0` (May 7) | 提交频率极低 | -| 3 | `go run verification_executor.go` | **8 passed, 2 failed** | T-1.1 / T-3.2 因 `rg` 缺失误报 | -| 4 | `go run verification_executor.go --dry-run` | 10/10 打印通过 | dry-run 不执行命令，不产生误报 | -| 5 | `make test-fetch-openrouter` | PASS | 单测通过（2 条种子数据） | -| 6 | `go run scripts/fetch_openrouter.go` | 仅采集 2 条种子数据 | 无 API Key，回退到 mock | -| 7 | `go run scripts/generate_daily_report.go` | 产出 2 模型日报 | 无真实数据 | -| 8 | `test -f frontend/package.json` | **missing** | 前端不可构建 | -| 9 | `printenv \| grep OPENROUTER_API_KEY` | **未设置** | 采集器无法拉真实数据 | -| 10 | `printenv \| grep DATABASE_URL` | **未设置** | 采集器无法写入 PG | -| 11 | `which psql` | `/usr/bin/psql` 存在 | PG 客户端可用，但连接串未知 | -| 12 | `cat reports/daily/models.json` | 2 条模型 | 与种子数据一致 | - ---- - -## 已完成项 - -1. ✅ **项目本地任务体系**（T-4.1）：GOALS.md、TASKS.md 存在且结构清晰 -2. ✅ **验证器项目本地化**（T-4.2）：`verification_executor.go` 默认读取 `/home/long/project/立交桥/projects/llm-intelligence/TASKS.md` -3. ✅ **OpenRouter 采集器代码**（T-2.1）：`scripts/fetch_openrouter.go` 存在，支持 `-api-key`、`-db`、`-out`、`-retry` 等参数，单测通过 -4. ✅ **PostgreSQL migration 文件**（T-2.2）：`db/migrations/001_phase1_core_tables.sql` 含 `models`、`model_prices`、`report_runs` 三张表及索引 -5. ✅ **日报生成器代码**（T-2.3）：`scripts/generate_daily_report.go` 存在，支持 `-json`、`-out`、`-top` 参数 -6. ✅ **日报目录与产物**：`reports/daily/` 有 2026-05-05 ~ 2026-05-08 共 4 份日报 + `models.json` -7. ✅ **Explorer 页面代码**（T-3.1）：`frontend/src/pages/Explorer.tsx` 含筛选逻辑、mock 数据加载、`mapAPIResponseToModels` -8. ✅ **项目执行说明**（T-4.3）：`OPENCLAW_EXECUTION.md` 存在 -9. ✅ **Phase 1 范围已写入 PRD.md**（但未 commit）：范围、非目标、验收标准清晰 -10. ✅ **采集器 Makefile 入口**：`build-fetch-openrouter`、`test-fetch-openrouter`、`ci-fetch-openrouter` 可用 - ---- - -## 未完成项 - -1. 🔴 **环境变量配置**：`OPENROUTER_API_KEY` 与 `DATABASE_URL` 均未设置，真实数据链路断裂 -2. 🔴 **PRD.md commit**：Phase 1 范围修改已 4 天未 commit -3. 🔴 **前端构建系统**：无 `package.json`、`tsconfig.json`、构建脚本，`Explorer.tsx` 无法编译运行 -4. 🔴 **数据库 migration 应用**：无证据表明 `001_phase1_core_tables.sql` 已 apply 到任何数据库实例 -5. 🔴 **验证器 rg 依赖**：`TASKS.md` 中 T-1.1 和 T-3.2 仍使用 `rg`，环境中无 ripgrep，持续误报 -6. 🔴 **真实数据采集**：采集器只能回退到 2 条种子数据，未对接 OpenRouter 真实 API -7. 🔴 **日报内容单薄**：4 份日报均仅含 2 条模型，无实际情报价值 -8. 🟡 **Dashboard 最小组件验证**：手动验收脚本 `verify_t32.sh` 通过，但验证器因 rg 误报 - ---- - -## 伪进展 / 文档与实现不一致项 - -| 项目 | 文档/验收状态 | 真实状态 | 风险 | -|------|-------------|---------|------| -| **验证器 8/10 PASS** | 报告显示 8 passed | 2 个 FAIL 全是工具缺失（rg），非业务失败 | 状态可信度受损，cron 可能误判触发修复任务 | -| **前端 T-3.1/T-3.2** | 验证器显示 PASS（artifact_present 模式） | `package.json` 缺失，不可构建 | 给人"前端完成"错觉，实际无法运行 | -| **日报生成器 T-2.3** | 验证器显示 PASS（目录存在） | 日报仅 2 条种子数据，无情报价值 | 目录存在 ≠ 功能可用 | -| **数据库 T-2.2** | migration 文件存在 | 无证据已 apply，无 DATABASE_URL | 文件存在 ≠ 表已创建 | -| **采集器 T-2.1** | 验证器显示 PASS（文件存在） | 无 API Key，无法拉真实数据 | 文件存在 ≠ 采集链路闭环 | - -**核心问题**：当前 `TASKS.md` 的 verification 模式以 `artifact_present` 为主，只能检测"文件是否存在"，**无法检测"是否能运行/是否能连通真实服务"**。这是伪进展的主要来源。 - ---- - -## 最大 5 个关键 Gap - -### Gap 1：环境变量缺失阻塞真实数据链路 [P0] -- **根因**：`OPENROUTER_API_KEY` 与 `DATABASE_URL` 未配置 -- **影响**：采集器只能回退到 2 条 mock 数据，日报无价值，数据库无写入，Phase 1 三条主链路（采集→存储→报告）名义上存在，实际上只跑了"空转" -- **修复**：配置 API Key 与 DB 连接串，执行一次端到端采集→入库→日报验证 - -### Gap 2：验证器 rg 依赖导致持续误报 [P0] -- **根因**：`TASKS.md` 中 T-1.1 / T-3.2 使用 `rg`，环境未安装 ripgrep -- **影响**：连续 5 次 review（05-07 22:50 → 05-08 14:30）均受误报干扰，浪费诊断注意力 -- **修复**：将 `rg` 替换为 `grep -n`（POSIX 便携），或在验证器内增加 toolchain readiness check - -### Gap 3：前端不可构建 [P1] -- **根因**：`frontend/` 只有 `.tsx` 源码和 `.json` 数据文件，无 `package.json`、无构建工具链 -- **影响**：Explorer 页面无法编译、无法部署，Phase 1 的"可交付前台"目标未达成 -- **修复**：补充 `package.json`（React + TypeScript + Vite 最小配置）、`tsconfig.json`、构建脚本 - -### Gap 4：PRD.md 修改 4 天未 commit [P1] -- **根因**：Phase 1 范围/非目标/验收标准的修改一直停留在 unstaged -- **影响**：项目 commit 历史停滞，git 状态碎片化，T-1.1 验证器无法通过（rg 搜索 unstaged 修改可能搜不到） -- **修复**：`git add PRD.md && git commit -m "docs: 补充 Phase 1 范围、非目标与验收标准"` - -### Gap 5：验收模式只能检测文件存在，无法检测功能可用 [P1] -- **根因**：`TASKS.md` 的 verification 全部使用 `artifact_present` 模式 -- **影响**：文件存在即可 PASS，但实际无法构建/无法连接/无真实数据，产生大量伪进展 -- **修复**：增加 `build_test` / `connectivity_test` 验收模式，对 Go 代码执行 `go test`，对前端执行 `npm run build`，对数据库执行 `pg_isready` - ---- - -## 下一轮最值得推进的 3 件事 - -1. **配置环境变量并跑一次端到端验证**（最高优先级） - - 设置 `OPENROUTER_API_KEY` 和 `DATABASE_URL` - - 执行：`go run scripts/fetch_openrouter.go -db "$DATABASE_URL"` → 检查 PG 是否有数据 → 执行日报生成器 → 确认日报含真实模型数 - - 这是 Phase 1 三条链路首次真实闭环 - -2. **修复验证器 rg 依赖 + 补充构建级验收**（基础工程） - - 将 `TASKS.md` 中的 `rg` 替换为 `grep -n` - - 为 T-3.x 增加前端构建验证（检测 `package.json` 存在，或尝试 `npm run build`） - - 让 `verification_executor.go` 支持三级状态：PASS / WARN（工具缺失）/ FAIL（业务不符） - -3. **补齐前端构建骨架 + commit PRD.md**（产出完整性） - - 在 `frontend/` 下补充最小 React+TS+Vite 脚手架，使 `Explorer.tsx` 可编译 - - 将当前 `PRD.md` 修改与所有 untracked 文件梳理后 commit - - 产出一次干净的 git 快照，消除"项目停滞"观感 - ---- - -## 环境快照 - -| 项目 | 值 | -|------|-----| -| Git HEAD | `ba054f0` (feat(phase1): OpenRouter采集器接入PostgreSQL，数据链路闭环) | -| HEAD 时间 | May 7 2026 | -| 距上次 commit | ~28 小时 | -| Unstaged 文件 | `PRD.md` | -| Untracked 文件 | `.openclaw/`, `BUSINESS_MODEL.md`, `FEATURE_LIST.md`, `fetch_openrouter`, `fetch_openrouter_test`, `scripts/fetch_openrouter` (binary?), `scripts/review/` | -| OpenRouter API Key | ❌ 未设置 | -| DATABASE_URL | ❌ 未设置 | -| PostgreSQL 客户端 | ✅ `/usr/bin/psql` | -| Go 版本 | `go1.22.x`（可编译） | -| Node/npm | 待确认（frontend 无 package.json） | -| ripgrep (rg) | ❌ 未安装 | - ---- - -*Report generated by OpenClaw cron review | 文件路径：`reports/openclaw/2026-05-08-1430-review.md`* diff --git a/reports/openclaw/2026-05-08-2130-review.md b/reports/openclaw/2026-05-08-2130-review.md deleted file mode 100644 index b4de468..0000000 --- a/reports/openclaw/2026-05-08-2130-review.md +++ /dev/null @@ -1,168 +0,0 @@ -# OpenClaw Review Report - -**Review Time**: 2026-05-08 21:30 Asia/Shanghai (2026-05-08 13:30 UTC) -**Trigger**: cron `llm-intelligence-night-review` -**Reviewer**: OpenClaw Agent (llm-intelligence) - ---- - -## Executive Summary - -距上次 review（14:30）约 **7 小时**，仓库状态**零变化**——无新 commit、无文件变更、无环境变更。距最后一次真实 commit（`ba054f0`，May 8 13:49）约 **8 小时**。 - -**验证器 `verification_executor.go` 非 dry-run 继续 8/10 FAIL**，T-1.1 与 T-3.2 仍为 `rg` 缺失导致的 `exit status 127`。手动验收脚本 `verify_t32.sh` ~ `verify_t35.sh` 全部 PASS。**关键环境变量（`OPENROUTER_API_KEY`、`DATABASE_URL`）仍未配置**，真实数据链路未打通。前端 `frontend/` 依然无 `package.json`，不可构建。 - -**核心判断**：Phase 1 骨架代码落地后进入 **8 小时停滞期**。无新增代码产出，无 commit，无环境修复，无 backlog 问题被解决。 - ---- - -## 当前真实阶段判断 - -**阶段**：Phase 1 骨架完成 → **停滞中（stagnation）** - -| 维度 | 状态 | -|------|------| -| 代码骨架 | ✅ 采集器 / migration / 日报 / 验证器 / Explorer 均存在 | -| 构建可运行 | ⚠️ Go 代码可编译；前端不可构建；数据库未确认连通 | -| 真实数据 | ❌ 仅有 2 条 seed 数据，未对接 OpenRouter 真实 API | -| 环境配置 | ❌ API Key 与 DB URL 均未设置 | -| 任务验证 | ⚠️ 手动脚本全绿，自动验证器 20% 误报 | -| 版本控制 | ❌ 多个文件 4 天+ 未 commit，untracked 文件堆积 | -| 进展速度 | ❌ 8 小时零 commit、零代码变更 | - ---- - -## 本次执行的验证命令与结果 - -| # | 验证命令 | 结果 | 说明 | -|---|---------|------|------| -| 1 | `git status --short` | `M PRD.md TASKS.md OPENCLAW_CAPABILITY_BACKLOG.md`; 7 个 untracked | 与 14:30 review 完全一致 | -| 2 | `git log --oneline -15` | 4 条 commit，最新 `ba054f0` (May 8 13:49) | 8 小时内无新提交 | -| 3 | `go run verification_executor.go` | **8 passed, 2 failed** | T-1.1 / T-3.2 `exit status 127`（rg 缺失） | -| 4 | `go run verification_executor.go --dry-run` | 10/10 | dry-run 不执行命令，无误报 | -| 5 | `make build-fetch-openrouter` | PASS | 采集器可编译 | -| 6 | `make test-fetch-openrouter` | PASS | 单测通过（2 条种子数据） | -| 7 | `bash scripts/verify_t32.sh` | **all PASS** | 前端表格 / 免费标签 / 图表占位 | -| 8 | `bash scripts/verify_t33.sh` | **all PASS** | 筛选逻辑 / dual-view | -| 9 | `bash scripts/verify_t34.sh` | **all PASS** | JSON schema / mapping | -| 10 | `bash scripts/verify_t35.sh` | **all PASS** | latest_models.json 同步 + pricing 归一 | -| 11 | `go run scripts/fetch_openrouter.go` | 2 条 seed 数据 | 无 API Key，回退 mock | -| 12 | `go run scripts/generate_daily_report.go` | 产出 2 模型日报 | 无真实数据 | -| 13 | `test -f frontend/package.json` | **missing** | 前端不可构建 | -| 14 | `test -f frontend/tsconfig.json` | **missing** | TypeScript 未配置 | -| 15 | `printenv \| grep OPENROUTER_API_KEY` | **未设置** | 真实采集阻塞 | -| 16 | `printenv \| grep DATABASE_URL` | **未设置** | 数据库写入阻塞 | -| 17 | `cat reports/daily/daily_report_2026-05-08.md` | 2 模型（seed） | 今日日报已生成但无情报价值 | - ---- - -## 已完成项 - -1. ✅ **项目本地任务体系**（T-4.1）：GOALS.md、TASKS.md 存在 -2. ✅ **验证器项目本地化**（T-4.2）：默认读取本项目 TASKS.md -3. ✅ **OpenRouter 采集器代码**（T-2.1）：可编译、可运行、单测通过 -4. ✅ **PostgreSQL migration 文件**（T-2.2）：三张表 + 索引完整 -5. ✅ **日报生成器代码**（T-2.3）：支持参数化，产出 Markdown + latest_models.json -6. ✅ **日报目录与产物**：`reports/daily/` 有 05-05 ~ 05-08 共 4 份日报 -7. ✅ **Explorer 页面代码**（T-3.1）：含筛选、卡片/表格双视图、免费标记 -8. ✅ **项目执行说明**（T-4.3）：`OPENCLAW_EXECUTION.md` 存在 -9. ✅ **Phase 1 范围已写入 PRD.md**（但未 commit） -10. ✅ **Makefile 入口**：build / test / ci / check / help 可用 -11. ✅ **手动验收脚本**：t32 ~ t35 全部 PASS，覆盖前端表格、筛选、JSON 同步、pricing 归一 - ---- - -## 未完成项 - -1. 🔴 **环境变量配置**：`OPENROUTER_API_KEY`、`DATABASE_URL` 未设置 -2. 🔴 **前端构建系统**：无 `package.json`、`tsconfig.json`、构建脚本 -3. 🔴 **PRD.md / TASKS.md / BACKLOG commit**：多个文件修改多日未 stage -4. 🔴 **数据库 migration apply**：无证据表明 SQL 已执行到 PG 实例 -5. 🔴 **验证器 rg 依赖修复**：`TASKS.md` 中仍用 `rg`，持续误报 2 个任务 -6. 🔴 **真实数据采集**：仅 2 条 seed 数据，371+ 真实模型未拉取 -7. 🔴 **日报内容单薄**：4 份日报均仅 2 条模型 -8. 🔴 **代码提交停滞**：8 小时零 commit（从 May 8 13:49 到 May 8 21:30） - ---- - -## 伪进展 / 文档与实现不一致项 - -| 项目 | 表面状态 | 真实状态 | 风险 | -|------|---------|---------|------| -| **验证器 8/10 PASS** | 8 个通过 | 2 个 FAIL 全是 `rg` 工具缺失，非业务失败 | 状态可信度归零 | -| **前端 T-3.1/T-3.2** | artifact_present 模式 PASS | 无 `package.json`，`Explorer.tsx` 无法编译 | 给人"前端完成"错觉 | -| **日报 T-2.3** | 目录存在 PASS | 仅 2 条 seed 数据，无情报价值 | 目录存在 ≠ 功能可用 | -| **数据库 T-2.2** | migration 文件存在 PASS | 无 DATABASE_URL，无 apply 证据 | 文件存在 ≠ 表已创建 | -| **采集器 T-2.1** | 文件存在 PASS | 无 API Key，无法拉真实数据 | 文件存在 ≠ 链路闭环 | -| **手动验收脚本全绿** | t32~t35 PASS | 只能 grep 代码文本，不验证构建/运行/连通 | 给人"全部完成"错觉 | - ---- - -## 最大 5 个关键 Gap - -### Gap 1：环境变量缺失阻塞真实数据链路 [P0] -- **根因**：`OPENROUTER_API_KEY` 与 `DATABASE_URL` 未配置 -- **影响**：采集器只能回退到 2 条 mock 数据，日报无价值，数据库无写入 -- **修复**：配置环境变量，执行一次端到端采集→入库→日报验证 - -### Gap 2：验证器 rg 依赖导致持续误报 [P0] -- **根因**：`TASKS.md` 中 T-1.1 / T-3.2 使用 `rg`，环境未安装 ripgrep -- **影响**：连续 **6 次 review**（05-07 22:50 → 05-08 21:30）均受误报干扰 -- **修复**：将 `rg` 替换为 `grep -n`（POSIX 便携） - -### Gap 3：项目提交停滞 [P1] -- **根因**：8 小时无 commit，多个文件修改多日未 stage/untracked 堆积 -- **影响**：项目状态碎片化，外部观察者认为"项目停滞" -- **修复**：`git add` 当前修改，`git commit`，清理 untracked 文件（决定保留或删除） - -### Gap 4：前端不可构建 [P1] -- **根因**：`frontend/` 只有 `.tsx` 源码，无 `package.json`、无构建工具链 -- **影响**：Explorer 页面无法编译、无法部署 -- **修复**：补充最小 React+TS+Vite 脚手架 - -### Gap 5：验收模式只能检测文件存在 [P1] -- **根因**：`TASKS.md` 全部 verification 使用 `artifact_present` 模式 -- **影响**：文件存在即可 PASS，无法检测构建/连通/真实数据，系统性伪进展 -- **修复**：增加 `build_test` / `connectivity_test` 模式，Go 执行 `go test`，前端执行 `npm run build`，数据库执行 `pg_isready` - ---- - -## 下一轮最值得推进的 3 件事 - -1. **修复 rg 依赖 + commit 当前修改**（最低成本、最高信号价值） - - 将 `TASKS.md` 中 `rg` 替换为 `grep -n` - - `git add PRD.md TASKS.md` 并 commit - - 清理 untracked 文件（`fetch_openrouter` 二进制、`.openclaw/workspace-state.json` 等决定保留/删除） - - 让验证器恢复到 10/10 真实 PASS，消除误报噪声 - -2. **配置环境变量并跑一次端到端验证**（Phase 1 真实闭环） - - 设置 `OPENROUTER_API_KEY` 和 `DATABASE_URL` - - 执行：`go run scripts/fetch_openrouter.go -db "$DATABASE_URL"` → 检查 PG 数据 → 执行日报生成器 → 确认日报含真实模型数 - - 这是 Phase 1 首次真实数据跑通 - -3. **补齐前端构建骨架**（可交付前台） - - 在 `frontend/` 下补充 `package.json`（React + TypeScript + Vite）、`tsconfig.json` - - 使 `Explorer.tsx` 可编译 - - 产出一次可运行的前端页面 - ---- - -## 环境快照 - -| 项目 | 值 | -|------|-----| -| Git HEAD | `ba054f0` (feat(phase1): OpenRouter采集器接入PostgreSQL，数据链路闭环) | -| HEAD 时间 | 2026-05-08 13:49 +0800 | -| 距上次 commit | ~8 小时 | -| Unstaged 文件 | `PRD.md`, `TASKS.md`, `reports/openclaw/OPENCLAW_CAPABILITY_BACKLOG.md` | -| Untracked 文件 | `.openclaw/`, `BUSINESS_MODEL.md`, `FEATURE_LIST.md`, `fetch_openrouter`, `fetch_openrouter_test`, `models.json`, `reports/openclaw/2026-05-08-1430-review.md`, `scripts/fetch_openrouter`, `scripts/review/` | -| OpenRouter API Key | ❌ 未设置 | -| DATABASE_URL | ❌ 未设置 | -| PostgreSQL 客户端 | ✅ `/usr/bin/psql` | -| Go 版本 | `go1.22.x`（可编译） | -| Node/npm | ❌ frontend 无 package.json，不可确认 | -| ripgrep (rg) | ❌ 未安装 | - ---- - -*Report generated by OpenClaw cron review | 文件路径：`reports/openclaw/2026-05-08-2130-review.md`* diff --git a/reports/openclaw/2026-05-09-0930-review.md b/reports/openclaw/2026-05-09-0930-review.md deleted file mode 100644 index 9a4821c..0000000 --- a/reports/openclaw/2026-05-09-0930-review.md +++ /dev/null @@ -1,175 +0,0 @@ -# OpenClaw Review Report - -**Review Time**: 2026-05-09 09:30 Asia/Shanghai (2026-05-09 01:30 UTC) -**Trigger**: cron `llm-intelligence-morning-review` -**Reviewer**: OpenClaw Agent (llm-intelligence) - ---- - -## Executive Summary - -距上次 review（2026-05-08 21:30）约 **12 小时**，仓库状态**零变化**——无新 commit、无文件变更、无环境变更。距最后一次真实 commit（`ba054f0`，May 8 13:49）已过去 **约 20 小时**。 - -**验证器 `verification_executor.go` 非 dry-run 继续 8/10 FAIL**，T-1.1 与 T-3.2 仍为 `rg` 缺失导致的 `exit status 127`。手动验收脚本 `verify_t32.sh` ~ `verify_t35.sh` 全部 PASS。**关键环境变量（`OPENROUTER_API_KEY`、`DATABASE_URL`）仍未配置**，真实数据链路未打通。前端 `frontend/` 依然无 `package.json`，不可构建。 - -**核心判断**：Phase 1 骨架代码落地后进入 **20 小时停滞期**。无新增代码产出，无 commit，无环境修复，无 backlog 问题被解决。连续 **7 次 review**（05-07 22:50 → 05-09 09:30）结论 100% 相同。 - ---- - -## 当前真实阶段判断 - -**阶段**：Phase 1 骨架完成 → **深度停滞中（deep stagnation）** - -| 维度 | 状态 | -|------|------| -| 代码骨架 | ✅ 采集器 / migration / 日报 / 验证器 / Explorer 均存在 | -| 构建可运行 | ⚠️ Go 代码可编译；前端不可构建；数据库未确认连通 | -| 真实数据 | ❌ 仅有 2 条 seed 数据，未对接 OpenRouter 真实 API | -| 环境配置 | ❌ API Key 与 DB URL 均未设置 | -| 任务验证 | ⚠️ 手动脚本全绿，自动验证器 20% 误报 | -| 版本控制 | ❌ 多个文件 5 天+ 未 commit，untracked 文件堆积 | -| 进展速度 | ❌ 20 小时零 commit、零代码变更 | -| review 空转 | ❌ 连续 7 次 review 结论相同，token 持续浪费 | - ---- - -## 本次执行的验证命令与结果 - -| # | 验证命令 | 结果 | 说明 | -|---|---------|------|------| -| 1 | `git log --oneline -5 --since="2026-05-08 21:30"` | **(no output)** | 12 小时内零 commit | -| 2 | `git status --short` | `M PRD.md TASKS.md OPENCLAW_CAPABILITY_BACKLOG.md`; 7 个 untracked | 与 21:30 review 完全一致 | -| 3 | `git log --oneline -1` | `ba054f0` (May 8 13:49) | 距本次 review 约 20 小时 | -| 4 | `go run verification_executor.go` | **8 passed, 2 failed** | T-1.1 / T-3.2 `exit status 127`（rg 缺失） | -| 5 | `go run verification_executor.go --dry-run` | 10/10 | dry-run 不执行命令，无误报 | -| 6 | `make build-fetch-openrouter` | PASS | 采集器可编译 | -| 7 | `make test-fetch-openrouter` | PASS | 单测通过（2 条种子数据） | -| 8 | `bash scripts/verify_t32.sh` | **all PASS** | 前端表格 / 免费标签 / 图表占位 | -| 9 | `bash scripts/verify_t33.sh` | **all PASS** | 筛选逻辑 / dual-view | -| 10 | `bash scripts/verify_t34.sh` | **all PASS** | JSON schema / mapping | -| 11 | `bash scripts/verify_t35.sh` | **all PASS** | latest_models.json 同步 + pricing 归一 | -| 12 | `go run scripts/fetch_openrouter.go` | 2 条 seed 数据 | 无 API Key，回退 mock | -| 13 | `test -f frontend/package.json` | **missing** | 前端不可构建 | -| 14 | `test -f frontend/tsconfig.json` | **missing** | TypeScript 未配置 | -| 15 | `printenv \| grep OPENROUTER_API_KEY` | **未设置** | 真实采集阻塞 | -| 16 | `printenv \| grep DATABASE_URL` | **未设置** | 数据库写入阻塞 | -| 17 | `cat reports/daily/daily_report_2026-05-08.md` | 2 模型（seed） | 昨日日报已生成但无情报价值 | - ---- - -## 已完成项 - -1. ✅ **项目本地任务体系**（T-4.1）：GOALS.md、TASKS.md 存在 -2. ✅ **验证器项目本地化**（T-4.2）：默认读取本项目 TASKS.md -3. ✅ **OpenRouter 采集器代码**（T-2.1）：可编译、可运行、单测通过 -4. ✅ **PostgreSQL migration 文件**（T-2.2）：三张表 + 索引完整 -5. ✅ **日报生成器代码**（T-2.3）：支持参数化，产出 Markdown + latest_models.json -6. ✅ **日报目录与产物**：`reports/daily/` 有 05-05 ~ 05-08 共 4 份日报 -7. ✅ **Explorer 页面代码**（T-3.1）：含筛选、卡片/表格双视图、免费标记 -8. ✅ **项目执行说明**（T-4.3）：`OPENCLAW_EXECUTION.md` 存在 -9. ✅ **Phase 1 范围已写入 PRD.md**（但未 commit） -10. ✅ **Makefile 入口**：build / test / ci / check / help 可用 -11. ✅ **手动验收脚本**：t32 ~ t35 全部 PASS - ---- - -## 未完成项 - -1. 🔴 **环境变量配置**：`OPENROUTER_API_KEY`、`DATABASE_URL` 未设置 -2. 🔴 **前端构建系统**：无 `package.json`、`tsconfig.json`、构建脚本 -3. 🔴 **PRD.md / TASKS.md / BACKLOG commit**：多个文件修改 5 天+ 未 stage -4. 🔴 **数据库 migration apply**：无证据表明 SQL 已执行到 PG 实例 -5. 🔴 **验证器 rg 依赖修复**：`TASKS.md` 中仍用 `rg`，连续 7 次 review 误报 -6. 🔴 **真实数据采集**：仅 2 条 seed 数据，371+ 真实模型未拉取 -7. 🔴 **日报内容单薄**：4 份日报均仅 2 条模型 -8. 🔴 **代码提交停滞**：20 小时零 commit（从 May 8 13:49 到 May 9 09:30） -9. 🔴 **review 空转**：连续 7 次 review 结论相同，未触发 delta gate - ---- - -## 伪进展 / 文档与实现不一致项 - -| 项目 | 表面状态 | 真实状态 | 风险 | -|------|---------|---------|------| -| **验证器 8/10 PASS** | 8 个通过 | 2 个 FAIL 全是 `rg` 工具缺失，非业务失败 | 状态可信度归零 | -| **前端 T-3.1/T-3.2** | artifact_present 模式 PASS | 无 `package.json`，`Explorer.tsx` 无法编译 | 给人"前端完成"错觉 | -| **日报 T-2.3** | 目录存在 PASS | 仅 2 条 seed 数据，无情报价值 | 目录存在 ≠ 功能可用 | -| **数据库 T-2.2** | migration 文件存在 PASS | 无 DATABASE_URL，无 apply 证据 | 文件存在 ≠ 表已创建 | -| **采集器 T-2.1** | 文件存在 PASS | 无 API Key，无法拉真实数据 | 文件存在 ≠ 链路闭环 | -| **手动验收脚本全绿** | t32~t35 PASS | 只能 grep 代码文本，不验证构建/运行/连通 | 给人"全部完成"错觉 | - ---- - -## 最大 5 个关键 Gap - -### Gap 1：环境变量缺失阻塞真实数据链路 [P0] -- **根因**：`OPENROUTER_API_KEY` 与 `DATABASE_URL` 未配置 -- **影响**：采集器只能回退到 2 条 mock 数据，日报无价值，数据库无写入 -- **修复**：配置环境变量，执行一次端到端采集→入库→日报验证 -- **状态**：❌ 连续 7 次 review 均未修复 - -### Gap 2：验证器 rg 依赖导致持续误报 [P0] -- **根因**：`TASKS.md` 中 T-1.1 / T-3.2 使用 `rg`，环境未安装 ripgrep -- **影响**：连续 **7 次 review**（05-07 22:50 → 05-09 09:30）均受误报干扰 -- **修复**：将 `rg` 替换为 `grep -n`（POSIX 便携） -- **状态**：❌ 连续 7 次 review 均未修复，已成为最具破坏性的基础工程债务 - -### Gap 3：项目提交停滞 [P1] -- **根因**：20 小时无 commit，多个文件修改 5 天+ 未 stage/untracked 堆积 -- **影响**：项目状态碎片化，外部观察者认为"项目停滞" -- **修复**：`git add` 当前修改，`git commit`，清理 untracked 文件 -- **状态**：❌ 连续 7 次 review 均未修复 - -### Gap 4：前端不可构建 [P1] -- **根因**：`frontend/` 只有 `.tsx` 源码，无 `package.json`、无构建工具链 -- **影响**：Explorer 页面无法编译、无法部署 -- **修复**：补充最小 React+TS+Vite 脚手架 -- **状态**：❌ 连续 7 次 review 均未修复 - -### Gap 5：review 流程无 delta gate，持续空转 [P1] -- **根因**：cron 按固定间隔触发 review，仓库无变化时仍执行全量分析 -- **影响**：连续 7 次 review 结论 100% 相同，累计 token 浪费 **~42k-70k**，产出为零 -- **修复**：在 `OPENCLAW_MULTI_REVIEW_PROMPT.md` 中增加 delta gate 步骤 -- **状态**：❌ 连续 6 次 review 均未修复（本次 review 因 prompt 要求 "execute it fully now" 未触发 gate） - ---- - -## 下一轮最值得推进的 3 件事 - -1. **修复 rg 依赖 + commit 当前修改**（最低成本、最高信号价值） - - 将 `TASKS.md` 中 `rg` 替换为 `grep -n` - - `git add PRD.md TASKS.md` 并 commit - - 清理 untracked 文件（`fetch_openrouter` 二进制、`.openclaw/workspace-state.json` 等决定保留/删除） - - 让验证器恢复到 10/10 真实 PASS，消除误报噪声 - -2. **配置环境变量并跑一次端到端验证**（Phase 1 真实闭环） - - 设置 `OPENROUTER_API_KEY` 和 `DATABASE_URL` - - 执行：`go run scripts/fetch_openrouter.go -db "$DATABASE_URL"` → 检查 PG 数据 → 执行日报生成器 → 确认日报含真实模型数 - - 这是 Phase 1 首次真实数据跑通 - -3. **补齐前端构建骨架**（可交付前台） - - 在 `frontend/` 下补充 `package.json`（React + TypeScript + Vite）、`tsconfig.json` - - 使 `Explorer.tsx` 可编译 - - 产出一次可运行的前端页面 - ---- - -## 环境快照 - -| 项目 | 值 | -|------|-----| -| Git HEAD | `ba054f0` (feat(phase1): OpenRouter采集器接入PostgreSQL，数据链路闭环) | -| HEAD 时间 | 2026-05-08 13:49 +0800 | -| 距上次 commit | ~20 小时 | -| Unstaged 文件 | `PRD.md`, `TASKS.md`, `reports/openclaw/OPENCLAW_CAPABILITY_BACKLOG.md` | -| Untracked 文件 | `.openclaw/`, `BUSINESS_MODEL.md`, `FEATURE_LIST.md`, `fetch_openrouter`, `fetch_openrouter_test`, `models.json`, `reports/openclaw/2026-05-08-1430-review.md`, `scripts/fetch_openrouter`, `scripts/review/` | -| OpenRouter API Key | ❌ 未设置 | -| DATABASE_URL | ❌ 未设置 | -| PostgreSQL 客户端 | ✅ `/usr/bin/psql` | -| Go 版本 | `go1.22.x`（可编译） | -| Node/npm | ❌ frontend 无 package.json，不可确认 | -| ripgrep (rg) | ❌ 未安装 | - ---- - -*Report generated by OpenClaw cron review | 文件路径：`reports/openclaw/2026-05-09-0930-review.md`* diff --git a/reports/openclaw/2026-05-09-1430-review.md b/reports/openclaw/2026-05-09-1430-review.md deleted file mode 100644 index 2b6f4b8..0000000 --- a/reports/openclaw/2026-05-09-1430-review.md +++ /dev/null @@ -1,178 +0,0 @@ -# OpenClaw Review Report - -**Review Time**: 2026-05-09 14:30 Asia/Shanghai (2026-05-09 06:30 UTC) -**Trigger**: cron `llm-intelligence-afternoon-review` -**Reviewer**: OpenClaw Agent (llm-intelligence) - ---- - -## Executive Summary - -距上次 review（2026-05-09 09:30）约 **5 小时**，仓库状态**零变化**——无新 commit、无文件变更、无环境变更。距最后一次真实 commit（`ba054f0`，May 8 13:49）已过去 **约 25 小时**。 - -**验证器 `verification_executor.go` 非 dry-run 继续 8/10 FAIL**，T-1.1 与 T-3.2 仍为 `rg` 缺失导致的 `exit status 127`。手动验收脚本 `verify_t32.sh` ~ `verify_t35.sh` 全部 PASS。**关键环境变量（`OPENROUTER_API_KEY`、`DATABASE_URL`）仍未配置**，真实数据链路未打通。前端 `frontend/` 依然无 `package.json`，不可构建。 - -**核心判断**：Phase 1 骨架代码落地后进入 **25 小时深度停滞期（deep stagnation）**。无新增代码产出，无 commit，无环境修复，无 backlog 问题被解决。连续 **8 次 review**（05-07 22:50 → 05-09 14:30）结论 100% 相同。 - -> 🔴 **Commit 健康警告**：`git status --short` 非空，最后 commit 距今 25 小时，存在 3 个 unstaged 文件和 11 个 untracked 文件。 - ---- - -## 当前真实阶段判断 - -**阶段**：Phase 1 骨架完成 → **深度停滞中（deep stagnation）** - -| 维度 | 状态 | -|------|------| -| 代码骨架 | ✅ 采集器 / migration / 日报 / 验证器 / Explorer 均存在 | -| 构建可运行 | ⚠️ Go 代码可编译；前端不可构建；数据库未确认连通 | -| 真实数据 | ❌ 仅有 2 条 seed 数据，未对接 OpenRouter 真实 API | -| 环境配置 | ❌ API Key 与 DB URL 均未设置 | -| 任务验证 | ⚠️ 手动脚本全绿，自动验证器 20% 误报 | -| 版本控制 | ❌ 多个文件 5 天+ 未 commit，untracked 文件堆积 | -| 进展速度 | ❌ 25 小时零 commit、零代码变更 | -| review 空转 | ❌ 连续 8 次 review 结论相同，token 持续浪费 | - ---- - -## 本次执行的验证命令与结果 - -| # | 验证命令 | 结果 | 说明 | -|---|---------|------|------| -| 1 | `git log --oneline -5 --since="2026-05-09 09:30"` | **(no output)** | 5 小时内零 commit | -| 2 | `git status --short` | `M PRD.md TASKS.md OPENCLAW_CAPABILITY_BACKLOG.md`; 11 个 untracked | 与 09:30 review 完全一致 | -| 3 | `git log --oneline -1` | `ba054f0` (May 8 13:49) | 距本次 review 约 25 小时 | -| 4 | `go run verification_executor.go` | **8 passed, 2 failed** | T-1.1 / T-3.2 `exit status 127`（rg 缺失） | -| 5 | `go run verification_executor.go --dry-run` | 10/10 | dry-run 不执行命令，无误报 | -| 6 | `make build-fetch-openrouter` | PASS | 采集器可编译 | -| 7 | `make test-fetch-openrouter` | PASS | 单测通过（2 条种子数据） | -| 8 | `bash scripts/verify_t32.sh` | **all PASS** | 前端表格 / 免费标签 / 图表占位 | -| 9 | `bash scripts/verify_t33.sh` | **all PASS** | 筛选逻辑 / dual-view | -| 10 | `bash scripts/verify_t34.sh` | **all PASS** | JSON schema / mapping | -| 11 | `bash scripts/verify_t35.sh` | **all PASS** | latest_models.json 同步 + pricing 归一 | -| 12 | `go run scripts/fetch_openrouter.go` | 2 条 seed 数据 | 无 API Key，回退 mock | -| 13 | `test -f frontend/package.json` | **missing** | 前端不可构建 | -| 14 | `test -f frontend/tsconfig.json` | **missing** | TypeScript 未配置 | -| 15 | `printenv \| grep OPENROUTER_API_KEY` | **未设置** | 真实采集阻塞 | -| 16 | `printenv \| grep DATABASE_URL` | **未设置** | 数据库写入阻塞 | -| 17 | `cat reports/daily/daily_report_2026-05-08.md` | 2 模型（seed） | 昨日日报已生成但无情报价值 | -| 18 | `ls -la db/migrations/` | `001_phase1_core_tables.sql` 存在 | migration 文件完整，但未 apply | - ---- - -## 已完成项 - -1. ✅ **项目本地任务体系**（T-4.1）：GOALS.md、TASKS.md 存在 -2. ✅ **验证器项目本地化**（T-4.2）：默认读取本项目 TASKS.md -3. ✅ **OpenRouter 采集器代码**（T-2.1）：可编译、可运行、单测通过 -4. ✅ **PostgreSQL migration 文件**（T-2.2）：三张表 + 索引完整 -5. ✅ **日报生成器代码**（T-2.3）：支持参数化，产出 Markdown + latest_models.json -6. ✅ **日报目录与产物**：`reports/daily/` 有 05-05 ~ 05-08 共 4 份日报 -7. ✅ **Explorer 页面代码**（T-3.1）：含筛选、卡片/表格双视图、免费标记 -8. ✅ **项目执行说明**（T-4.3）：`OPENCLAW_EXECUTION.md` 存在 -9. ✅ **Phase 1 范围已写入 PRD.md**（但未 commit） -10. ✅ **Makefile 入口**：build / test / ci / check / help 可用 -11. ✅ **手动验收脚本**：t32 ~ t35 全部 PASS - ---- - -## 未完成项 - -1. 🔴 **环境变量配置**：`OPENROUTER_API_KEY`、`DATABASE_URL` 未设置 -2. 🔴 **前端构建系统**：无 `package.json`、`tsconfig.json`、构建脚本 -3. 🔴 **PRD.md / TASKS.md / BACKLOG commit**：多个文件修改 5 天+ 未 stage -4. 🔴 **数据库 migration apply**：无证据表明 SQL 已执行到 PG 实例 -5. 🔴 **验证器 rg 依赖修复**：`TASKS.md` 中仍用 `rg`，连续 8 次 review 误报 -6. 🔴 **真实数据采集**：仅 2 条 seed 数据，371+ 真实模型未拉取 -7. 🔴 **日报内容单薄**：4 份日报均仅 2 条模型 -8. 🔴 **代码提交停滞**：25 小时零 commit（从 May 8 13:49 到 May 9 14:30） -9. 🔴 **review 空转**：连续 8 次 review 结论相同，未触发 delta gate - ---- - -## 伪进展 / 文档与实现不一致项 - -| 项目 | 表面状态 | 真实状态 | 风险 | -|------|---------|---------|------| -| **验证器 8/10 PASS** | 8 个通过 | 2 个 FAIL 全是 `rg` 工具缺失，非业务失败 | 状态可信度归零 | -| **前端 T-3.1/T-3.2** | artifact_present 模式 PASS | 无 `package.json`，`Explorer.tsx` 无法编译 | 给人"前端完成"错觉 | -| **日报 T-2.3** | 目录存在 PASS | 仅 2 条 seed 数据，无情报价值 | 目录存在 ≠ 功能可用 | -| **数据库 T-2.2** | migration 文件存在 PASS | 无 DATABASE_URL，无 apply 证据 | 文件存在 ≠ 表已创建 | -| **采集器 T-2.1** | 文件存在 PASS | 无 API Key，无法拉真实数据 | 文件存在 ≠ 链路闭环 | -| **手动验收脚本全绿** | t32~t35 PASS | 只能 grep 代码文本，不验证构建/运行/连通 | 给人"全部完成"错觉 | - ---- - -## 最大 5 个关键 Gap - -### Gap 1：环境变量缺失阻塞真实数据链路 [P0] -- **根因**：`OPENROUTER_API_KEY` 与 `DATABASE_URL` 未配置 -- **影响**：采集器只能回退到 2 条 mock 数据，日报无价值，数据库无写入 -- **修复**：配置环境变量，执行一次端到端采集→入库→日报验证 -- **状态**：❌ 连续 8 次 review 均未修复 - -### Gap 2：验证器 rg 依赖导致持续误报 [P0] -- **根因**：`TASKS.md` 中 T-1.1 / T-3.2 使用 `rg`，环境未安装 ripgrep -- **影响**：连续 **8 次 review**（05-07 22:50 → 05-09 14:30）均受误报干扰 -- **修复**：将 `rg` 替换为 `grep -n`（POSIX 便携） -- **状态**：❌ 连续 8 次 review 均未修复，已成为最具破坏性的基础工程债务 - -### Gap 3：项目提交停滞 [P1] -- **根因**：25 小时无 commit，多个文件修改 5 天+ 未 stage/untracked 堆积 -- **影响**：项目状态碎片化，外部观察者认为"项目停滞" -- **修复**：`git add` 当前修改，`git commit`，清理 untracked 文件 -- **状态**：❌ 连续 8 次 review 均未修复 - -### Gap 4：前端不可构建 [P1] -- **根因**：`frontend/` 只有 `.tsx` 源码，无 `package.json`、无构建工具链 -- **影响**：Explorer 页面无法编译、无法部署 -- **修复**：补充最小 React+TS+Vite 脚手架 -- **状态**：❌ 连续 8 次 review 均未修复 - -### Gap 5：review 流程无 delta gate，持续空转 [P1] -- **根因**：cron 按固定间隔触发 review，仓库无变化时仍执行全量分析 -- **影响**：连续 8 次 review 结论 100% 相同，累计 token 浪费 **~48k-80k**，产出为零 -- **修复**：在 `OPENCLAW_MULTI_REVIEW_PROMPT.md` 中增加 delta gate 步骤 -- **状态**：❌ 连续 7 次 review 均未修复（本次 review 因 prompt 要求 "execute it fully now" 未触发 gate） - ---- - -## 下一轮最值得推进的 3 件事 - -1. **修复 rg 依赖 + commit 当前修改**（最低成本、最高信号价值） - - 将 `TASKS.md` 中 `rg` 替换为 `grep -n` - - `git add PRD.md TASKS.md` 并 commit - - 清理 untracked 文件（`fetch_openrouter` 二进制、`.openclaw/workspace-state.json` 等决定保留/删除） - - 让验证器恢复到 10/10 真实 PASS，消除误报噪声 - -2. **配置环境变量并跑一次端到端验证**（Phase 1 真实闭环） - - 设置 `OPENROUTER_API_KEY` 和 `DATABASE_URL` - - 执行：`go run scripts/fetch_openrouter.go -db "$DATABASE_URL"` → 检查 PG 数据 → 执行日报生成器 → 确认日报含真实模型数 - - 这是 Phase 1 首次真实数据跑通 - -3. **补齐前端构建骨架**（可交付前台） - - 在 `frontend/` 下补充 `package.json`（React + TypeScript + Vite）、`tsconfig.json` - - 使 `Explorer.tsx` 可编译 - - 产出一次可运行的前端页面 - ---- - -## 环境快照 - -| 项目 | 值 | -|------|-----| -| Git HEAD | `ba054f0` (feat(phase1): OpenRouter采集器接入PostgreSQL，数据链路闭环) | -| HEAD 时间 | 2026-05-08 13:49 +0800 | -| 距上次 commit | ~25 小时 | -| Unstaged 文件 | `PRD.md`, `TASKS.md`, `reports/openclaw/OPENCLAW_CAPABILITY_BACKLOG.md` | -| Untracked 文件 | `.openclaw/`, `BUSINESS_MODEL.md`, `FEATURE_LIST.md`, `fetch_openrouter`, `fetch_openrouter_test`, `models.json`, `reports/openclaw/2026-05-08-1430-review.md`, `reports/openclaw/2026-05-08-2130-review.md`, `reports/openclaw/2026-05-09-0930-review.md`, `scripts/fetch_openrouter`, `scripts/review/` | -| OpenRouter API Key | ❌ 未设置 | -| DATABASE_URL | ❌ 未设置 | -| PostgreSQL 客户端 | ✅ `/usr/bin/psql` | -| Go 版本 | `go1.22.x`（可编译） | -| Node/npm | ❌ frontend 无 package.json，不可确认 | -| ripgrep (rg) | ❌ 未安装 | - ---- - -*Report generated by OpenClaw cron review | 文件路径：`reports/openclaw/2026-05-09-1430-review.md`* diff --git a/reports/openclaw/2026-05-09-2130-review.md b/reports/openclaw/2026-05-09-2130-review.md deleted file mode 100644 index 6e1bec7..0000000 --- a/reports/openclaw/2026-05-09-2130-review.md +++ /dev/null @@ -1,178 +0,0 @@ -# OpenClaw Review Report - -**Review Time**: 2026-05-09 21:30 Asia/Shanghai (2026-05-09 13:30 UTC) -**Trigger**: cron `llm-intelligence-night-review` -**Reviewer**: OpenClaw Agent (llm-intelligence) - ---- - -## Executive Summary - -距上次 review（2026-05-09 14:30）约 **7 小时**，仓库状态**零变化**——无新 commit、无文件变更、无环境变更。距最后一次真实 commit（`ba054f0`，May 8 13:49）已过去 **约 32 小时**。 - -**验证器 `verification_executor.go` 非 dry-run 继续 8/10 FAIL**，T-1.1 与 T-3.2 仍为 `rg` 缺失导致的 `exit status 127`。手动验收脚本 `verify_t32.sh` ~ `verify_t35.sh` 全部 PASS。**关键环境变量（`OPENROUTER_API_KEY`、`DATABASE_URL`）仍未配置**，真实数据链路未打通。前端 `frontend/` 依然无 `package.json`，不可构建。 - -**核心判断**：Phase 1 骨架代码落地后进入 **32 小时深度停滞期（deep stagnation）**。无新增代码产出，无 commit，无环境修复，无 backlog 问题被解决。连续 **9 次 review**（05-07 22:50 → 05-09 21:30）结论 100% 相同。 - -> 🔴 **Commit 健康警告**：`git status --short` 非空，最后 commit 距今 32 小时，存在 3 个 unstaged 文件和 13 个 untracked 文件。 - ---- - -## 当前真实阶段判断 - -**阶段**：Phase 1 骨架完成 → **深度停滞中（deep stagnation）** - -| 维度 | 状态 | -|------|------| -| 代码骨架 | ✅ 采集器 / migration / 日报 / 验证器 / Explorer 均存在 | -| 构建可运行 | ⚠️ Go 代码可编译；前端不可构建；数据库未确认连通 | -| 真实数据 | ❌ 仅有 2 条 seed 数据，未对接 OpenRouter 真实 API | -| 环境配置 | ❌ API Key 与 DB URL 均未设置 | -| 任务验证 | ⚠️ 手动脚本全绿，自动验证器 20% 误报 | -| 版本控制 | ❌ 多个文件 5 天+ 未 commit，untracked 文件堆积 | -| 进展速度 | ❌ 32 小时零 commit、零代码变更 | -| review 空转 | ❌ 连续 9 次 review 结论相同，token 持续浪费 | - ---- - -## 本次执行的验证命令与结果 - -| # | 验证命令 | 结果 | 说明 | -|---|---------|------|------| -| 1 | `git log --oneline -5 --since="2026-05-09 14:30"` | **(no output)** | 7 小时内零 commit | -| 2 | `git status --short` | `M PRD.md TASKS.md OPENCLAW_CAPABILITY_BACKLOG.md`; 13 个 untracked | 与 14:30 review 完全一致 | -| 3 | `git log --oneline -1` | `ba054f0` (May 8 13:49) | 距本次 review 约 32 小时 | -| 4 | `go run verification_executor.go` | **8 passed, 2 failed** | T-1.1 / T-3.2 `exit status 127`（rg 缺失） | -| 5 | `go run verification_executor.go --dry-run` | 10/10 | dry-run 不执行命令，无误报 | -| 6 | `make build-fetch-openrouter` | PASS | 采集器可编译 | -| 7 | `make test-fetch-openrouter` | PASS | 单测通过（2 条种子数据） | -| 8 | `bash scripts/verify_t32.sh` | **all PASS** | 前端表格 / 免费标签 / 图表占位 | -| 9 | `bash scripts/verify_t33.sh` | **all PASS** | 筛选逻辑 / dual-view | -| 10 | `bash scripts/verify_t34.sh` | **all PASS** | JSON schema / mapping | -| 11 | `bash scripts/verify_t35.sh` | **all PASS** | latest_models.json 同步 + pricing 归一 | -| 12 | `go run scripts/fetch_openrouter.go` | 2 条 seed 数据 | 无 API Key，回退 mock | -| 13 | `test -f frontend/package.json` | **missing** | 前端不可构建 | -| 14 | `test -f frontend/tsconfig.json` | **missing** | TypeScript 未配置 | -| 15 | `printenv \| grep OPENROUTER_API_KEY` | **未设置** | 真实采集阻塞 | -| 16 | `printenv \| grep DATABASE_URL` | **未设置** | 数据库写入阻塞 | -| 17 | `cat reports/daily/daily_report_2026-05-08.md` | 2 模型（seed） | 昨日日报已生成但无情报价值 | -| 18 | `ls -la db/migrations/` | `001_phase1_core_tables.sql` 存在 | migration 文件完整，但未 apply | - ---- - -## 已完成项 - -1. ✅ **项目本地任务体系**（T-4.1）：GOALS.md、TASKS.md 存在 -2. ✅ **验证器项目本地化**（T-4.2）：默认读取本项目 TASKS.md -3. ✅ **OpenRouter 采集器代码**（T-2.1）：可编译、可运行、单测通过 -4. ✅ **PostgreSQL migration 文件**（T-2.2）：三张表 + 索引完整 -5. ✅ **日报生成器代码**（T-2.3）：支持参数化，产出 Markdown + latest_models.json -6. ✅ **日报目录与产物**：`reports/daily/` 有 05-05 ~ 05-08 共 4 份日报 -7. ✅ **Explorer 页面代码**（T-3.1）：含筛选、卡片/表格双视图、免费标记 -8. ✅ **项目执行说明**（T-4.3）：`OPENCLAW_EXECUTION.md` 存在 -9. ✅ **Phase 1 范围已写入 PRD.md**（但未 commit） -10. ✅ **Makefile 入口**：build / test / ci / check / help 可用 -11. ✅ **手动验收脚本**：t32 ~ t35 全部 PASS - ---- - -## 未完成项 - -1. 🔴 **环境变量配置**：`OPENROUTER_API_KEY`、`DATABASE_URL` 未设置 -2. 🔴 **前端构建系统**：无 `package.json`、`tsconfig.json`、构建脚本 -3. 🔴 **PRD.md / TASKS.md / BACKLOG commit**：多个文件修改 5 天+ 未 stage -4. 🔴 **数据库 migration apply**：无证据表明 SQL 已执行到 PG 实例 -5. 🔴 **验证器 rg 依赖修复**：`TASKS.md` 中仍用 `rg`，连续 9 次 review 误报 -6. 🔴 **真实数据采集**：仅 2 条 seed 数据，371+ 真实模型未拉取 -7. 🔴 **日报内容单薄**：4 份日报均仅 2 条模型 -8. 🔴 **代码提交停滞**：32 小时零 commit（从 May 8 13:49 到 May 9 21:30） -9. 🔴 **review 空转**：连续 9 次 review 结论相同，未触发 delta gate - ---- - -## 伪进展 / 文档与实现不一致项 - -| 项目 | 表面状态 | 真实状态 | 风险 | -|------|---------|---------|------| -| **验证器 8/10 PASS** | 8 个通过 | 2 个 FAIL 全是 `rg` 工具缺失，非业务失败 | 状态可信度归零 | -| **前端 T-3.1/T-3.2** | artifact_present 模式 PASS | 无 `package.json`，`Explorer.tsx` 无法编译 | 给人"前端完成"错觉 | -| **日报 T-2.3** | 目录存在 PASS | 仅 2 条 seed 数据，无情报价值 | 目录存在 ≠ 功能可用 | -| **数据库 T-2.2** | migration 文件存在 PASS | 无 DATABASE_URL，无 apply 证据 | 文件存在 ≠ 表已创建 | -| **采集器 T-2.1** | 文件存在 PASS | 无 API Key，无法拉真实数据 | 文件存在 ≠ 链路闭环 | -| **手动验收脚本全绿** | t32~t35 PASS | 只能 grep 代码文本，不验证构建/运行/连通 | 给人"全部完成"错觉 | - ---- - -## 最大 5 个关键 Gap - -### Gap 1：环境变量缺失阻塞真实数据链路 [P0] -- **根因**：`OPENROUTER_API_KEY` 与 `DATABASE_URL` 未配置 -- **影响**：采集器只能回退到 2 条 mock 数据，日报无价值，数据库无写入 -- **修复**：配置环境变量，执行一次端到端采集→入库→日报验证 -- **状态**：❌ 连续 9 次 review 均未修复 - -### Gap 2：验证器 rg 依赖导致持续误报 [P0] -- **根因**：`TASKS.md` 中 T-1.1 / T-3.2 使用 `rg`，环境未安装 ripgrep -- **影响**：连续 **9 次 review**（05-07 22:50 → 05-09 21:30）均受误报干扰 -- **修复**：将 `rg` 替换为 `grep -n`（POSIX 便携） -- **状态**：❌ 连续 9 次 review 均未修复，已成为最具破坏性的基础工程债务 - -### Gap 3：项目提交停滞 [P1] -- **根因**：32 小时无 commit，多个文件修改 5 天+ 未 stage/untracked 堆积 -- **影响**：项目状态碎片化，外部观察者认为"项目停滞" -- **修复**：`git add` 当前修改，`git commit`，清理 untracked 文件 -- **状态**：❌ 连续 9 次 review 均未修复 - -### Gap 4：前端不可构建 [P1] -- **根因**：`frontend/` 只有 `.tsx` 源码，无 `package.json`、无构建工具链 -- **影响**：Explorer 页面无法编译、无法部署 -- **修复**：补充最小 React+TS+Vite 脚手架 -- **状态**：❌ 连续 9 次 review 均未修复 - -### Gap 5：review 流程无 delta gate，持续空转 [P1] -- **根因**：cron 按固定间隔触发 review，仓库无变化时仍执行全量分析 -- **影响**：连续 9 次 review 结论 100% 相同，累计 token 浪费 **~54k-90k**，产出为零 -- **修复**：在 `OPENCLAW_MULTI_REVIEW_PROMPT.md` 中增加 delta gate 步骤 -- **状态**：❌ 连续 8 次 review 均未修复（本次 review 因 prompt 要求 "execute it fully now" 未触发 gate） - ---- - -## 下一轮最值得推进的 3 件事 - -1. **修复 rg 依赖 + commit 当前修改**（最低成本、最高信号价值） - - 将 `TASKS.md` 中 `rg` 替换为 `grep -n` - - `git add PRD.md TASKS.md` 并 commit - - 清理 untracked 文件（`fetch_openrouter` 二进制、`.openclaw/workspace-state.json` 等决定保留/删除） - - 让验证器恢复到 10/10 真实 PASS，消除误报噪声 - -2. **配置环境变量并跑一次端到端验证**（Phase 1 真实闭环） - - 设置 `OPENROUTER_API_KEY` 和 `DATABASE_URL` - - 执行：`go run scripts/fetch_openrouter.go -db "$DATABASE_URL"` → 检查 PG 数据 → 执行日报生成器 → 确认日报含真实模型数 - - 这是 Phase 1 首次真实数据跑通 - -3. **补齐前端构建骨架**（可交付前台） - - 在 `frontend/` 下补充 `package.json`（React + TypeScript + Vite）、`tsconfig.json` - - 使 `Explorer.tsx` 可编译 - - 产出一次可运行的前端页面 - ---- - -## 环境快照 - -| 项目 | 值 | -|------|-----| -| Git HEAD | `ba054f0` (feat(phase1): OpenRouter采集器接入PostgreSQL，数据链路闭环) | -| HEAD 时间 | 2026-05-08 13:49 +0800 | -| 距上次 commit | ~32 小时 | -| Unstaged 文件 | `PRD.md`, `TASKS.md`, `reports/openclaw/OPENCLAW_CAPABILITY_BACKLOG.md` | -| Untracked 文件 | `.openclaw/`, `BUSINESS_MODEL.md`, `FEATURE_LIST.md`, `fetch_openrouter`, `fetch_openrouter_test`, `models.json`, `reports/openclaw/2026-05-08-1430-review.md`, `reports/openclaw/2026-05-08-2130-review.md`, `reports/openclaw/2026-05-09-0930-review.md`, `reports/openclaw/2026-05-09-1430-review.md`, `scripts/fetch_openrouter`, `scripts/review/` | -| OpenRouter API Key | ❌ 未设置 | -| DATABASE_URL | ❌ 未设置 | -| PostgreSQL 客户端 | ✅ `/usr/bin/psql` | -| Go 版本 | `go1.22.x`（可编译） | -| Node/npm | ❌ frontend 无 package.json，不可确认 | -| ripgrep (rg) | ❌ 未安装 | - ---- - -*Report generated by OpenClaw cron review | 文件路径：`reports/openclaw/2026-05-09-2130-review.md`* diff --git a/reports/openclaw/2026-05-10-0930-review.md b/reports/openclaw/2026-05-10-0930-review.md deleted file mode 100644 index 7e61692..0000000 --- a/reports/openclaw/2026-05-10-0930-review.md +++ /dev/null @@ -1,170 +0,0 @@ -# OpenClaw Review — 2026-05-10 09:30 (morning-review) - -## Executive Summary - -**仓库状态：连续 47 小时零变化，所有已知问题持续未修复。** - -距上次 commit（`ba054f0`，2026-05-08 13:49）已过去 **约 44 小时**，期间无任何新 commit、文件变更或环境变化。本次 review 为 cron 触发的第 10 次全量 review，结论与此前 9 次 100% 一致。 - -**核心判断**：本项目 Phase 1 骨架代码已落地（采集器、迁移、日报、前端脚手架），但三条主链路无一真正跑通真实数据；验证器存在 P0 级基础工程债务；review 系统本身陷入"空转循环"。 - ---- - -## 当前真实阶段判断 - -| 维度 | 状态 | 说明 | -|------|------|------| -| 规划文档 | ✅ 冻结 | PRD v0.3、FEATURE_LIST、TECHNICAL_DESIGN 已对齐 | -| 采集器代码 | ✅ 存在 | `fetch_openrouter.go` 逻辑完整，支持 PostgreSQL 写入 | -| 数据库迁移 | ✅ 存在 | `001_phase1_core_tables.sql` 三张表定义完整 | -| 日报生成器 | ✅ 存在 | `generate_daily_report.go` 可产出 Markdown | -| 前端脚手架 | ✅ 存在 | `Explorer.tsx` 含筛选、表格/卡片视图、免费标记 | -| **采集器真实数据** | 🔴 未跑通 | 无 `OPENROUTER_API_KEY`，只能回退到 2 条模拟数据 | -| **数据库真实写入** | 🔴 未验证 | `DATABASE_URL` 未配置，无法确认 migration 已 apply | -| **日报真实内容** | 🔴 空洞 | 基于 2 条模拟数据生成，非真实 OpenRouter 数据 | -| **前端可构建** | 🔴 不可 | 无 `package.json`、无构建系统，代码片段不可运行 | -| **cron 自动采集** | 🔴 未配置 | 无定时任务配置，无自动触发机制 | - -**结论**：Phase 1 处于"代码存在但链路未通"状态，距离"可交付"还差：API Key 配置、数据库连接验证、前端构建系统、cron 集成。 - ---- - -## 本次执行的验证命令与结果 - -### 1. Git 状态 -```bash -git status --short -``` -**结果**：17 个未跟踪文件 + 5 个修改未 stage（`M MARKET_ANALYSIS.md`, `M OPENCLAW_EXECUTION.md`, `M PRD.md`, `M TASKS.md`, `M TECHNICAL_DESIGN.md`）。 - -### 2. 最近提交 -```bash -git log --oneline -10 -``` -**结果**： -``` -ba054f0 feat(phase1): OpenRouter采集器接入PostgreSQL，数据链路闭环 -dbdf13e docs: v3 market analysis + PRD v0.3 data update -c34bfd5 docs: PRD v0.2 + 市场调研报告 v2.0 - 覆盖全球LLM情报 -9c9a520 docs: LLM Intelligence Hub - PRD v0.1 + 市场调研报告 v1.0 -``` -**分析**：仅 4 个 commit，最后一个为 2026-05-08 13:49，距今 44 小时。 - -### 3. 环境变量检查 -```bash -printenv | grep -E "OPENROUTER_API_KEY|DATABASE_URL" -``` -**结果**：`环境变量未设置`。两个关键变量均未配置。 - -### 4. 验证器 dry-run -```bash -go run scripts/verification_executor.go --dry-run -``` -**结果**：10/10 PASS（dry-run 不执行命令，仅打印）。 - -### 5. 验证器真实执行 -```bash -go run scripts/verification_executor.go -``` -**结果**：8/10 PASS，2 FAILED： -- ❌ T-1.1 `exit status 127`（`rg` 命令不存在） -- ❌ T-3.2 `exit status 127`（`rg` 命令不存在） - -### 6. 前端构建检查 -```bash -ls frontend/ && cat frontend/package.json -``` -**结果**：无 `package.json`，前端不可构建。 - -### 7. 日报内容检查 -```bash -cat reports/daily/daily_report_2026-05-08.md -``` -**结果**：基于 2 条模拟数据（gpt-4o + claude-3.5-sonnet:free），非真实 OpenRouter 数据。 - ---- - -## 已完成项 - -1. ✅ PRD / FEATURE_LIST / TECHNICAL_DESIGN 文档对齐，Phase 1 范围冻结 -2. ✅ `fetch_openrouter.go` 采集器代码完成（含 PostgreSQL 写入逻辑） -3. ✅ `db/migrations/001_phase1_core_tables.sql` 三张表定义 -4. ✅ `generate_daily_report.go` 日报生成器代码完成 -5. ✅ `Explorer.tsx` 前端页面脚手架（筛选、表格/卡片、免费标记） -6. ✅ `TASKS.md` / `GOALS.md` / `OPENCLAW_EXECUTION.md` 项目管理文档 -7. ✅ `verification_executor.go` 验证器框架 - ---- - -## 未完成项 - -1. 🔴 配置 `OPENROUTER_API_KEY` 并验证真实数据采集 -2. 🔴 配置 `DATABASE_URL` 并验证 migration 已 apply + 采集器可写入 -3. 🔴 前端构建系统（`package.json`、`tsconfig.json`、构建脚本） -4. 🔴 cron 定时自动采集 + 日报生成 -5. 🔴 修复验证器 `rg` 依赖（替换为 `grep`） -6. 🔴 提交堆积的文档修改（5 个 modified + 17 个 untracked） - ---- - -## 伪进展 / 文档与实现不一致项 - -| 文档声明 | 真实状态 | 差距 | -|----------|----------|------| -| "采集器可运行并写入 DB" | 代码存在，但无 API Key 和 DB 连接 | 无法运行真实采集 | -| "日报生成命令可重放" | 基于 2 条模拟数据 | 非真实数据 | -| "Explorer 页面可展示模型表格" | 代码片段存在，无构建系统 | 不可运行 | -| "验证器 10/10 PASS" | dry-run 全绿，真实执行 8/10 | `rg` 缺失导致误报 | - ---- - -## 最大 5 个关键 Gap - -1. **🔴 Gap-1：环境变量缺失导致数据链路完全不通** - - `OPENROUTER_API_KEY` 和 `DATABASE_URL` 均未配置 - - 采集器只能回退到 2 条模拟数据，日报内容空洞 - - **修复**：配置环境变量 → 运行采集器 → 验证 DB 写入 → 重放日报 - -2. **🔴 Gap-2：前端不可构建** - - 无 `package.json`、`tsconfig.json`、构建脚本 - - `Explorer.tsx` 是孤立代码片段，无法运行和部署 - - **修复**：初始化前端项目（Vite/React + TypeScript）→ 迁移现有代码 → 验证构建 - -3. **🟡 Gap-3：验证器 `rg` 依赖持续误报（P0 工程债务）** - - 连续 10 次 review 均受此问题影响，已持续 47 小时 - - 导致 T-1.1、T-3.2 被错误标记为 FAIL - - **修复**：将 `TASKS.md` 中的 `rg` 替换为 `grep -n` - -4. **🟡 Gap-4：项目提交停滞 44 小时** - - 5 个核心文档修改未 stage，17 个 untracked 文件 - - 外部观感为"项目停滞" - - **修复**：`git add` 核心文档 + `git commit` + 清理 untracked（`.openclaw/` 等可 `.gitignore`） - -5. **🟡 Gap-5：review 系统空转** - - 连续 10 次 review 在零变化仓库上执行全量分析 - - 累计 token 浪费预估 60k-100k，产出为零 - - **修复**：在 `OPENCLAW_MULTI_REVIEW_PROMPT.md` 中增加 delta gate - ---- - -## 下一轮最值得推进的 3 件事 - -1. **配置环境变量并打通数据链路**（最高优先级） - - 设置 `OPENROUTER_API_KEY` 和 `DATABASE_URL` - - 运行 `fetch_openrouter` → 验证 DB 写入 → 运行 `generate_daily_report` - - 这是 Phase 1 从"代码存在"到"链路跑通"的关键一跃 - -2. **修复验证器 `rg` 依赖 + 提交堆积文件** - - 替换 `TASKS.md` 中的 `rg` 为 `grep -n` - - `git add` + `git commit` 核心文档修改 - - 恢复项目 git 健康状态 - -3. **初始化前端构建系统** - - 创建 `frontend/package.json`（Vite + React + TypeScript） - - 迁移现有 `Explorer.tsx` 和数据文件 - - 验证 `npm install && npm run build` 通过 - ---- - -*Review 完成时间：2026-05-10 09:30 Asia/Shanghai* -*触发源：cron `llm-intelligence-morning-review`* diff --git a/reports/openclaw/2026-05-10-1430-review.md b/reports/openclaw/2026-05-10-1430-review.md deleted file mode 100644 index 4057540..0000000 --- a/reports/openclaw/2026-05-10-1430-review.md +++ /dev/null @@ -1,219 +0,0 @@ -# OpenClaw Review — 2026-05-10 14:30 (afternoon-review) - -## Executive Summary - -**仓库状态：连续 49 小时零代码变化，所有已知问题持续未修复。** - -距上次 commit（`ba054f0`，2026-05-08 13:49）已过去 **约 49 小时**，期间无任何新 commit、文件变更或环境变化。本次 review 为 cron 触发的第 11 次全量 review，结论与此前 10 次高度一致。 - -**唯一新发现**：PostgreSQL 数据库实际已存在且包含 2 条记录（与 `.env.example` 中的 `DATABASE_URL` 配置一致），但 `DATABASE_URL` 环境变量仍未在 shell 中导出，导致验证器 T-5.3 持续 FAIL。 - -**核心判断**：Phase 1 骨架代码已落地，但三条主链路无一真正跑通真实 OpenRouter 数据；验证器存在 P0 级基础工程债务；review 系统陷入"空转循环"；项目提交停滞接近 50 小时。 - ---- - -## 当前真实阶段判断 - -| 维度 | 状态 | 说明 | -|------|------|------| -| 规划文档 | ✅ 冻结 | PRD v0.3、FEATURE_LIST、TECHNICAL_DESIGN 已对齐 | -| 采集器代码 | ✅ 存在 | `fetch_openrouter.go` 逻辑完整，支持 PostgreSQL 写入 | -| 数据库迁移 | ✅ 已 apply | `models`、`model_prices`、`report_runs` 三张表存在 | -| 数据库数据 | 🟡 2 条模拟记录 | DB 中有 2 条记录，但非真实 OpenRouter 采集结果 | -| 日报生成器 | ✅ 存在 | `generate_daily_report.go` 可产出 Markdown | -| 日报内容 | 🔴 空洞 | 基于 2 条模拟数据，非真实 OpenRouter 数据 | -| 前端脚手架 | ✅ 存在 | `Explorer.tsx` 含筛选、表格/卡片视图、免费标记 | -| 前端可构建 | 🔴 不可 | 无 `package.json`，代码片段不可运行 | -| **采集器真实数据** | 🔴 未跑通 | 无 `OPENROUTER_API_KEY`，只能回退到模拟数据 | -| **环境变量配置** | 🔴 未导出 | `.env.example` 存在但 `.env`/`.env.local` 未创建 | -| **cron 自动采集** | 🔴 未配置 | 无定时任务配置 | -| 验证器 dry-run | ✅ 15/15 PASS | 不执行命令，仅打印 | -| 验证器真实执行 | 🟡 12/15 PASS | T-5.3/T-5.4/T-5.5 为真实 FAIL（非工具误报） | - -**结论**：Phase 1 处于"代码存在但链路未通"状态。相比 09:30 review，唯一变化是确认 DB 已 apply（2 条记录），但数据来源仍是模拟数据而非真实 OpenRouter API。 - ---- - -## 本次执行的验证命令与结果 - -### 1. Git 状态 -```bash -git status --short -``` -**结果**：17 个未跟踪文件 + 5 个修改未 stage（`M MARKET_ANALYSIS.md`, `M Makefile`, `M OPENCLAW_EXECUTION.md`, `M PRD.md`, `M TASKS.md`, `M TECHNICAL_DESIGN.md`）。 - -### 2. 最近提交 -```bash -git log --oneline -10 -``` -**结果**： -``` -ba054f0 feat(phase1): OpenRouter采集器接入PostgreSQL，数据链路闭环 -dbdf13e docs: v3 market analysis + PRD v0.3 data update -c34bfd5 docs: PRD v0.2 + 市场调研报告 v2.0 - 覆盖全球LLM情报 -9c9a520 docs: LLM Intelligence Hub - PRD v0.1 + 市场调研报告 v1.0 -``` -**分析**：仅 4 个 commit，最后一个为 2026-05-08 13:49，距今 49 小时。 - -### 3. 环境变量检查 -```bash -printenv | grep -E "OPENROUTER_API_KEY|DATABASE_URL" -``` -**结果**：`环境变量未设置`。两个关键变量均未在 shell 中导出。 - -### 4. 验证器 dry-run -```bash -go run scripts/verification_executor.go --dry-run -``` -**结果**：15/15 PASS（dry-run 不执行命令，仅打印）。 - -### 5. 验证器真实执行 -```bash -go run scripts/verification_executor.go -``` -**结果**：12/15 PASS，3 FAILED： -- ❌ T-5.3 `exit status 1`（`printenv | grep OPENROUTER_API_KEY` 无输出）— **真实 FAIL** -- ❌ T-5.4 `exit status 1`（`test -f frontend/package.json` 不存在）— **真实 FAIL** -- ❌ T-5.5 `llm-intelligence` 未在 crontab 中找到 — **真实 FAIL** - -> **重要变化**：T-1.1 和 T-3.2 不再 FAIL。对比 09:30 review 的 `8/10 FAIL（rg 缺失）`，本次 `12/15 PASS` 说明 `rg` 依赖问题**已在 TASKS.md 中修复**（`rg` 被替换为 `grep -nE`）。这是 11 次 review 以来首次看到验证器误报问题得到缓解。 - -### 6. 前端构建检查 -```bash -ls frontend/ && cat frontend/package.json -``` -**结果**：`frontend/` 仅含 `src/` 目录，无 `package.json`、无 `tsconfig.json`、无构建脚本。前端不可构建。 - -### 7. 数据库状态检查（本次新增） -```bash -psql "host=/var/run/postgresql dbname=llm_intelligence user=long sslmode=disable" -c "\dt" -``` -**结果**：`models`、`model_prices`、`report_runs` 三张表均存在，Owner 为 `long`。 - -```bash -psql "host=/var/run/postgresql dbname=llm_intelligence user=long sslmode=disable" -c "SELECT COUNT(*) FROM models;" -``` -**结果**：`count = 2`。DB 中有 2 条记录。 - -### 8. Makefile 验证 -```bash -make build-fetch-openrouter -``` -**结果**：`go build -o /dev/null ./scripts/fetch_openrouter.go` — **编译通过**。 - -```bash -make test-fetch-openrouter -``` -**结果**： -``` -=== RUN TestParseModels ---- PASS: TestParseModels (0.00s) -=== RUN TestRunNoAPIKey -警告: 未提供 API Key，使用模拟数据 -采集完成: 共 2 模型（免费 1 / 付费 1） ---- PASS: TestRunNoAPIKey (0.00s) -PASS -ok command-line-arguments 0.002s -``` - -### 9. 日报内容检查 -```bash -cat reports/daily/daily_report_2026-05-09.md -``` -**结果**：模型总数 = 2（gpt-4o + claude-3.5-sonnet:free），与 DB 记录数一致，均为模拟数据。 - -### 10. `.env` 文件检查 -```bash -cat .env.example -``` -**结果**：`.env.example` 存在，包含 `OPENROUTER_API_KEY=` 和 `DATABASE_URL=host=/var/run/postgresql...` 模板，但 `.env` 和 `.env.local` 均未创建。 - ---- - -## 已完成项 - -1. ✅ PRD / FEATURE_LIST / TECHNICAL_DESIGN / IMPLEMENTATION_PLAN 文档对齐，Phase 1 范围冻结 -2. ✅ `fetch_openrouter.go` 采集器代码完成（含 PostgreSQL 写入逻辑） -3. ✅ `db/migrations/001_phase1_core_tables.sql` 三张表定义并 **已 apply** -4. ✅ `generate_daily_report.go` 日报生成器代码完成 -5. ✅ `Explorer.tsx` 前端页面脚手架（筛选、表格/卡片、免费标记） -6. ✅ `TASKS.md` / `GOALS.md` / `OPENCLAW_EXECUTION.md` 项目管理文档 -7. ✅ `verification_executor.go` 验证器框架（15 个任务） -8. ✅ `Makefile` 构建入口（`build-fetch-openrouter`、`test-fetch-openrouter`、`ci-fetch-openrouter` 等） -9. ✅ `scripts/run_real_pipeline.sh` 真实采集流水线脚本（需 `.env`） -10. ✅ `scripts/apply_migration.sh` 数据库迁移脚本 -11. ✅ `.env.example` 环境变量模板 - ---- - -## 未完成项 - -1. 🔴 配置 `OPENROUTER_API_KEY` 并验证真实数据采集 -2. 🔴 配置 `DATABASE_URL` 环境变量（DB 已存在但 shell 未导出） -3. 🔴 前端构建系统（`package.json`、`tsconfig.json`、构建脚本） -4. 🔴 cron 定时自动采集 + 日报生成 -5. 🔴 提交堆积的文档修改（5 个 modified + 17 个 untracked） - ---- - -## 伪进展 / 文档与实现不一致项 - -| 文档声明 | 真实状态 | 差距 | -|----------|----------|------| -| "采集器可运行并写入 DB" | 代码存在，DB 已 apply 且有 2 条记录 | 记录为模拟数据，非真实 OpenRouter API 采集 | -| "日报生成命令可重放" | 基于 2 条模拟数据 | 非真实数据 | -| "Explorer 页面可展示模型表格" | 代码片段存在，无构建系统 | 不可运行 | -| "验证器 15/15 PASS" | dry-run 全绿，真实执行 12/15 | T-5.3/5.4/5.5 为真实环境/构建/调度缺失 | - ---- - -## 最大 5 个关键 Gap - -1. **🔴 Gap-1：环境变量缺失导致数据链路完全不通** - - `OPENROUTER_API_KEY` 未配置，`DATABASE_URL` 未在 shell 中导出 - - 采集器只能回退到 2 条模拟数据，日报内容空洞 - - `.env.example` 已提供模板，但 `.env` 或 `.env.local` 未创建 - - **修复**：`cp .env.example .env.local` → 填入 API Key → `source .env.local` → 运行 `make run-real-pipeline` - -2. **🔴 Gap-2：前端不可构建** - - 无 `package.json`、`tsconfig.json`、构建脚本 - - `Explorer.tsx` 是孤立代码片段，无法运行和部署 - - **修复**：初始化前端项目（Vite/React + TypeScript）→ 迁移现有代码 → 验证构建 - -3. **🟡 Gap-3：项目提交停滞 49 小时** - - 5 个核心文档修改未 stage，17 个 untracked 文件 - - 外部观感为"项目停滞" - - **修复**：`git add` 核心文档 + `git commit` + 清理 untracked（`.openclaw/` 等可 `.gitignore`） - -4. **🟡 Gap-4：review 系统空转** - - 连续 11 次 review 在零变化仓库上执行全量分析 - - 累计 token 浪费预估 66k-110k，产出为零 - - **修复**：在 `OPENCLAW_MULTI_REVIEW_PROMPT.md` 中增加 delta gate - -5. **🟡 Gap-5：日报数据空洞** - - DB 中只有 2 条模拟记录，无法支撑有意义的日报内容 - - 即使 cron 配置完成，每日产出的仍是"2 模型 / 1 免费"的重复空洞报告 - - **修复**：先打通 Gap-1（真实采集），再配置 cron - ---- - -## 本轮最值得推进的 3 件事 - -1. **配置环境变量并打通真实数据链路**（最高优先级） - - 创建 `.env.local`，填入 `OPENROUTER_API_KEY` 和 `DATABASE_URL` - - 执行 `make run-real-pipeline` 验证真实采集 → DB 写入 → 日报生成 - - 这是 Phase 1 从"代码存在"到"链路跑通"的关键一跃 - -2. **提交堆积文件 + 初始化前端构建系统** - - `git add` + `git commit` 核心文档修改，恢复 git 健康状态 - - 创建 `frontend/package.json`（Vite + React + TypeScript），迁移现有 `Explorer.tsx` - - 验证 `npm install && npm run build` 通过 - -3. **review 系统自我修复：delta gate + BACKLOG 分层** - - 在 `OPENCLAW_MULTI_REVIEW_PROMPT.md` 中增加"仓库无变化时跳过全量分析"规则 - - 将 `OPENCLAW_CAPABILITY_BACKLOG.md` 重构为"顶部速查表 + 归档日志"分层结构，控制文件膨胀 - ---- - -*Review 完成时间：2026-05-10 14:30 Asia/Shanghai* -*触发源：cron `llm-intelligence-afternoon-review`* diff --git a/reports/openclaw/2026-05-10-2130-review.md b/reports/openclaw/2026-05-10-2130-review.md deleted file mode 100644 index a11b973..0000000 --- a/reports/openclaw/2026-05-10-2130-review.md +++ /dev/null @@ -1,222 +0,0 @@ -# OpenClaw Night Review — 2026-05-10 21:30 Asia/Shanghai - -> **Review ID**: llm-intelligence-night-review -> **Trigger**: cron `b769d061-e102-4f82-9e9f-3a659e79f6e7` -> **Reviewer**: 宰相（AI Agent） -> **Scope**: 高频真实状态 review，非破坏性，不改业务代码 - ---- - -## Executive Summary - -**项目状态：Phase 1~5 全部验收通过，但存在严重的提交停滞（commit stagnation）和文档-实现一致性风险。** - -距上一次 review（14:30）约 **7 小时**，距最后一次真实 commit（`ba054f0`，2026-05-08 13:49）已过去 **约 56 小时**。仓库状态**零代码变更**（无新 commit），但 12 个 tracked 文件和 17 个 untracked 文件持续累积未 stage。 - -Phase 1~5 验证脚本全部 PASS（52/52 检查项通过），说明**功能实现层面已达预 Phase 6 标准**。然而，git 工作区严重脏污，存在大量未提交的文档修改和新增文件，构成**伪进展风险**——文档声称的功能可能已修改但尚未落盘到 git 历史。 - ---- - -## 当前真实阶段判断 - -| 维度 | 判断 | 依据 | -|------|------|------| -| 功能实现 | **Phase 5 完成，预 Phase 6 通过** | verify_phase1~5.sh 全部 PASS，verify_pre_phase6.sh PASS | -| 代码提交 | **严重停滞** | 56 小时无 commit，12 tracked + 17 untracked 文件 | -| 文档一致性 | **高风险** | PRD.md / TASKS.md / OPENCLAW_EXECUTION.md / TECHNICAL_DESIGN.md 均有未提交修改 | -| 数据链路 | **真实运行中** | models=377, report_runs=2, 今日日报已生成 | -| 前端构建 | **通过** | `npm run build` 在 verify_phase4 中验证通过 | -| CI/CD | **配置存在，未验证运行** | `.github/workflows/` 存在，但未触发过真实 Actions run | - -**阶段结论**：功能上已越过 Phase 1~5，但工程纪律（提交、版本控制、CI 验证）严重滞后，构成**最大风险项**。 - ---- - -## 本次执行的验证命令与结果 - -### 1. 基础状态检查 - -```bash -git status --short -``` -**结果**：12 个 modified 文件 + 17 个 untracked 文件（含 .github/、cmd/、internal/、frontend/ 等核心目录）。 - -```bash -git log --oneline -10 -``` -**结果**：最后 commit `ba054f0`（2026-05-08），仅 4 个 commit 历史，项目历史极短。 - -### 2. Phase 验收脚本（全部执行） - -| 脚本 | 结果 | 通过/总计 | -|------|------|-----------| -| `verify_phase1.sh` | **PASS** | 9/9 | -| `verify_phase2.sh` | **PASS** | 9/9 | -| `verify_phase3.sh` | **PASS** | 10/10 | -| `verify_phase4.sh` | **PASS** | 10/10 | -| `verify_phase5.sh` | **PASS** | 14/14 | -| `verify_pre_phase6.sh` | **PASS** | 52/52 | - -### 3. 验证器执行 - -```bash -go run scripts/verification_executor.go --dry-run -``` -**结果**：15/15 Tasks 全部 PASS（T-1.1 ~ T-5.5）。 - -### 4. 数据链路验证 - -```bash -# 通过 verify_phase2.sh 间接验证 -models 总量: 377 (期望 >= 371) ✅ -models 审计日志: 383 (期望 >= 371) ✅ -国内厂商模型数: 89 (期望 >= 10) ✅ -CNY 定价记录: 10 (期望 >= 10) ✅ -``` - -### 5. 日报产物验证 - -```bash -ls reports/daily/2026/05/ -``` -**结果**：`daily_report_2026-05-10.md` 和 `.html` 均存在，今日日报已生成。 - -### 6. 环境变量验证 - -```bash -cat .env | grep -v "^#" | grep -v "^$" -``` -**结果**：`OPENROUTER_API_KEY` 和 `DATABASE_URL` 均已配置，真实数据链路已打通。 - ---- - -## 已完成项 - -### Phase 1~5 全部完成（功能层面） - -| 任务 | 状态 | 验证证据 | -|------|------|----------| -| T-1.1 Phase 1 范围冻结 | ✅ | PRD.md 含"Phase 1 范围"、"非目标"、"验收标准" | -| T-1.2 文档冲突清理 | ✅ | FEATURE_LIST.md / TECHNICAL_DESIGN.md 无冲突描述 | -| T-2.1 OpenRouter 采集器 | ✅ | `scripts/fetch_openrouter.go` 存在，可构建运行 | -| T-2.2 PostgreSQL migration | ✅ | `db/migrations/*.sql` 存在，8 张表已落库 | -| T-2.3 日报生成器 | ✅ | `reports/daily/` 存在，今日已生成 | -| T-3.1 Explorer 页面 | ✅ | `frontend/src/pages/Explorer.tsx` 存在，含分页/排序/筛选 | -| T-3.2 Dashboard 组件 | ✅ | `frontend/src/pages/Dashboard.tsx` 存在，集成 ECharts | -| T-4.1 项目本地任务清单 | ✅ | `GOALS.md` / `TASKS.md` 存在 | -| T-4.2 验证器本地化 | ✅ | `verification_executor.go` 默认读取本项目 TASKS.md | -| T-4.3 项目执行说明 | ✅ | `OPENCLAW_EXECUTION.md` 存在 | -| T-5.1 生产级实施计划 | ✅ | `IMPLEMENTATION_PLAN.md` 含国内厂商/数据质量/降级/审计日志 | -| T-5.2 任务清单对齐 | ✅ | TASKS.md 含生产级收口任务 | -| T-5.3 环境变量与真实数据链路 | ✅ | `.env` 已配置，真实采集+写库+日报通过 | -| T-5.4 前端构建系统初始化 | ✅ | `package.json` / `tsconfig.json` / `vite.config.ts` 存在，构建通过 | -| T-5.5 自动采集与日报调度 | ✅ | `crontab` 已配置，日报降级逻辑存在 | - -### 新增完成（本次 review 首次确认） - -| 任务 | 说明 | -|------|------| -| Sprint 1 扩展表全部存在 | 8 张表（含 audit_log），verify_phase1 确认 | -| CHECK 约束已落地 | 5 个约束，verify_phase1 确认 | -| updated_at 触发器 | 8 个表均挂载，verify_phase1 确认 | -| 厂商种子数据 61 条 | 远超期望 6 条，verify_phase1 确认 | -| region_pricing 380 条 | 含迁移数据，verify_phase1 确认 | -| batch_id 血缘字段回填完成 | `COUNT(*) WHERE batch_id IS NULL = 0`，verify_phase1 确认 | -| ProviderMapper 单元测试通过 | verify_phase2 确认 | -| 重试组件单元测试通过 | verify_phase2 确认 | -| 采集成功率统计 8 条 | verify_phase2 确认 | -| 前端生产构建通过 | verify_phase4 确认 | -| Explorer stale 状态显示 | verify_phase4 确认 | -| Explorer pricing unavailable 显示 | verify_phase4 确认 | -| Dockerfile / docker-compose / nginx 配置 | verify_phase5 确认 | -| GitHub Actions CI 配置 | verify_phase5 确认 | -| 数据库备份/恢复脚本 | verify_phase5 确认 | -| 健康检查脚本 | verify_phase5 确认 | -| 日志轮转配置 | verify_phase5 确认 | - ---- - -## 未完成项 - -### 工程纪律层面（严重） - -| 缺口 | 影响 | 当前状态 | -|------|------|----------| -| **56 小时无 commit** | 所有文档/代码修改未落盘，版本历史断裂，回滚能力丧失 | 🔴 未修复 | -| **12 tracked 文件未 stage** | PRD.md / TASKS.md / OPENCLAW_EXECUTION.md / TECHNICAL_DESIGN.md 等核心文档修改未提交，文档-实现一致性无法追溯 | 🔴 未修复 | -| **17 untracked 文件** | 含 .github/workflows/、cmd/、internal/、frontend/ 完整代码，这些文件在 verify 中被依赖但不在 git 历史中 | 🔴 未修复 | -| **CI 从未真实运行** | `.github/workflows/` 存在但未触发过，无法验证 CI 配置是否有效 | 🔴 未验证 | - -### 功能层面（Phase 6 待启动） - -| 缺口 | 影响 | 当前状态 | -|------|------|----------| -| Phase 6 范围未定义 | 预 Phase 6 已通过，但 Phase 6 目标（API Server？多数据源？推送？）未在 PRD/IMPLEMENTATION_PLAN 中明确 | 🟡 待定义 | -| API Server 未启动 | TECHNICAL_DESIGN.md 中 Service Layer 的 API Server 标记为"Phase 2 评估"，但当前已越过 Phase 5 | 🟡 待评估 | -| 飞书推送未验证 | `scripts/feishu_alert.sh` 存在且可执行（verify_phase3 确认），但未验证真实推送成功 | 🟡 未验证 | -| 国内厂商采集器 | 当前为种子数据录入（89 条模型），非真实 API 采集 | 🟡 Phase 2 规划 | - ---- - -## 伪进展/文档与实现不一致项 - -### 1. 文档修改未提交导致的"最新版"幻觉 - -- **PRD.md**：`git diff` 显示 148 行修改，但当前 git 历史中的版本是 2026-05-09，工作区版本可能已更新到 v0.4 或更高，但未提交。 -- **TECHNICAL_DESIGN.md**：`git diff` 显示 1196 行修改，这是最大的文档变更，可能包含 Sprint 2~6 的技术设计，但不在 git 历史中。 -- **TASKS.md**：`git diff` 显示 98 行修改，可能已添加 Phase 6 任务，但未提交。 - -**风险**：如果工作区因任何原因丢失（磁盘故障、误操作），这些文档变更将全部消失，且无法通过 git 恢复。 - -### 2. `IMPLEMENTATION_PLAN.md.bak-corrupt-20260510-0905` - -- 存在一个 5 字节的损坏备份文件（`IMPLEMENTATION_PLAN.md.bak-corrupt-20260510-0905`），说明之前有文件写入失败的历史。 -- 当前 `IMPLEMENTATION_PLAN.md` 和 `IMPLEMENTATION_PLAN_v1.1.md` 同时存在，内容可能相同或不同，造成混淆。 - -### 3. `fetch_openrouter` / `fetch_openrouter_test` 二进制文件 - -- 根目录存在两个巨大的二进制文件（7.5MB / 8.5MB），在 `.gitignore` 中可能未排除（或不在 `.gitignore` 中）。 -- 这些二进制文件不应提交到 git，但当前状态显示它们可能是 untracked 或已被跟踪。 - ---- - -## 最大 5 个关键 Gap - -| 优先级 | Gap | 影响 | 建议行动 | -|--------|-----|------|----------| -| **P0** | **56 小时 commit 停滞** | 所有工作成果未落盘，存在丢失风险；团队协作无法基于 git 进行 | 立即执行 `git add` + `git commit`，提交所有已验证的变更 | -| **P0** | **untracked 核心代码未入版本控制** | `.github/`、`cmd/`、`internal/` 等目录不在 git 中，CI 和核心服务代码无版本保护 | 同上，一并提交 | -| **P1** | **CI 配置未验证** | `.github/workflows/` 存在但未触发过，可能配置错误导致首次 push 时 CI 失败 | 提交后观察 GitHub Actions 首次运行结果 | -| **P1** | **Phase 6 范围未定义** | 项目已完成 Phase 1~5，但下一步目标模糊，可能导致方向漂移 | 更新 PRD/IMPLEMENTATION_PLAN，明确 Phase 6 范围 | -| **P1** | **BACKLOG 文件持续膨胀** | `OPENCLAW_CAPABILITY_BACKLOG.md` 已从 ~6KB 膨胀到 ~34KB，每次 review 读取成本递增 | 实施分层归档，将已修复问题移入独立归档文件 | - ---- - -## 下一轮最值得推进的 3 件事 - -1. **立即提交所有变更**：`git add -A && git commit -m "feat: Phase 1-5 全量验收通过，预 Phase 6 就绪"`。这是当前最紧急的工程纪律修复。 -2. **验证 CI 首次运行**：提交后观察 GitHub Actions 是否成功，修复任何 CI 配置问题。 -3. **定义 Phase 6 范围**：更新 PRD/IMPLEMENTATION_PLAN，明确 Phase 6 目标（建议：API Server 最小可用 + 多数据源采集器框架）。 - ---- - -## 附录：验证命令完整输出 - -### verify_pre_phase6.sh - -``` -PRE_PHASE6_RESULT: PASS -(52/52 检查项全部通过，详见上文) -``` - -### verification_executor.go --dry-run - -``` -Tasks checked: 15 | Dry-run: true | TASKS: /home/long/project/llm-intelligence/TASKS.md -15/15 PASS -``` - ---- - -*Review 完成时间：2026-05-10 21:35 Asia/Shanghai* -*下次 review 建议：提交完成后立即做一次 delta review，确认 git 状态清洁。* diff --git a/reports/openclaw/2026-05-11-0930-review.md b/reports/openclaw/2026-05-11-0930-review.md deleted file mode 100644 index 52da3a0..0000000 --- a/reports/openclaw/2026-05-11-0930-review.md +++ /dev/null @@ -1,302 +0,0 @@ -# OpenClaw Morning Review — 2026-05-11 09:30 Asia/Shanghai - -> **Review ID**: llm-intelligence-morning-review -> **Trigger**: cron `175a61b2-c2e7-4df4-a994-2fcacdbd24c6` -> **Reviewer**: 宰相（AI Agent） -> **Scope**: 高频真实状态 review，非破坏性，不改业务代码 - ---- - -## Executive Summary - -**项目状态：Phase 1~6 全部验收通过，但 commit 停滞已恶化到 60+ 小时，工程纪律风险持续累积。** - -距上一次 review（05-10 21:30）约 **12 小时**，距最后一次真实 commit（`ba054f0`，2026-05-08 13:49）已过去 **约 60 小时**。仓库状态**零代码变更**（无新 commit），但 12 个 tracked 文件和 17 个 untracked 文件持续累积未 stage。 - -**关键变化**： -- `verify_phase6.sh` 首次在本轮 review 中执行并通过（14/14 检查项），确认 **Phase 6 综合验收已达标**。 -- 数据链路真实运行：models=377（全部 24h 内新鲜），report_runs=6，今日日报 09:31 已生成。 -- 12 张数据库表全部就位，audit_log=1494 条。 -- 工程纪律风险未改善：60 小时无 commit，所有文档/代码修改仍未落盘。 - ---- - -## 当前真实阶段判断 - -| 维度 | 判断 | 依据 | -|------|------|------| -| 功能实现 | **Phase 6 完成** | verify_phase1~6.sh 全部 PASS，verify_pre_phase6.sh PASS，Phase 6 综合验收 14/14 通过 | -| 代码提交 | **严重停滞（恶化）** | 60 小时无 commit，12 tracked + 17 untracked 文件 | -| 文档一致性 | **高风险** | PRD.md / TASKS.md / OPENCLAW_EXECUTION.md / TECHNICAL_DESIGN.md 均有未提交修改（累计 2298 行 diff） | -| 数据链路 | **真实运行中** | models=377（24h 新鲜 377），report_runs=6，今日日报已生成 | -| 前端构建 | **通过** | `npm run build` 在 verify_phase4 中验证通过 | -| CI/CD | **配置存在，未验证运行** | `.github/workflows/ci.yml` 存在（untracked），从未触发 Actions | -| API Server | **可构建 + 健康检查通过** | verify_phase6 确认 API `/health` 和 `/api/v1/models` 返回 200，响应 < 500ms | - -**阶段结论**：功能上已完成 Phase 1~6，API Server 已可运行。但工程纪律（提交、版本控制、CI 验证）严重滞后，构成**最大风险项**。 - ---- - -## 本次执行的验证命令与结果 - -### 1. 基础状态检查 - -```bash -git status --short -``` -**结果**：12 个 modified 文件 + 17 个 untracked 文件（与 12 小时前完全一致，零变化）。 - -```bash -git log --oneline -5 --since="2026-05-10" -``` -**结果**：无输出（05-10 至今零 commit）。 - -```bash -git diff --stat -``` -**结果**：14 个文件，2298 行新增 / 1055 行删除，累计 diff 未变。 - -### 2. Phase 验收脚本（全部执行） - -| 脚本 | 结果 | 通过/总计 | -|------|------|-----------| -| `verify_phase1.sh` | **PASS** | 9/9 | -| `verify_phase2.sh` | **PASS** | 9/9 | -| `verify_phase3.sh` | **PASS** | 10/10 | -| `verify_phase4.sh` | **PASS** | 10/10 | -| `verify_phase5.sh` | **PASS** | 14/14 | -| `verify_pre_phase6.sh` | **PASS** | 52/52 | -| `verify_phase6.sh` | **PASS** | **14/14** ⭐ 首次在本轮确认 | - -### 3. 构建与测试验证 - -```bash -make build-fetch-openrouter -``` -**结果**：`go build -o /dev/null ./scripts/fetch_openrouter.go` ✅ 通过 - -```bash -make ci-fetch-openrouter -``` -**结果**：构建 + 单元测试全部通过（TestParseModels PASS, TestRunNoAPIKey PASS）✅ - -### 4. 数据库状态验证 - -```bash -psql $DATABASE_URL -c "SELECT table_name FROM information_schema.tables WHERE table_schema='public' ORDER BY table_name;" -``` -**结果**：12 张表全部存在： -- `audit_log`, `collector_stats`, `daily_report`, `free_tier`, `model_prices`, `model_provider`, `models`, `operator`, `pricing_history`, `region_pricing`, `report_runs`, `user_subscription` - -```bash -psql $DATABASE_URL -c "SELECT COUNT(*) as models, COUNT(*) FILTER (WHERE updated_at >= NOW() - INTERVAL '24 hours') as fresh_24h FROM models;" -``` -**结果**：models=377，fresh_24h=377（**100% 24 小时内新鲜**）✅ - -```bash -psql $DATABASE_URL -c "SELECT COUNT(*) as report_runs, MAX(created_at) as last_run FROM report_runs;" -``` -**结果**：report_runs=6，last_run=2026-05-11 09:31:14 ✅ - -```bash -psql $DATABASE_URL -c "SELECT COUNT(*) as audit_logs FROM audit_log;" -``` -**结果**：audit_logs=1494 ✅ - -```bash -psql $DATABASE_URL -c "SELECT source, COUNT(*) FROM models GROUP BY source ORDER BY COUNT(*) DESC LIMIT 10;" -``` -**结果**：openrouter=365，manual=12（国内厂商种子数据）✅ - -### 5. 日报产物验证 - -```bash -ls -la reports/daily/daily_report_2026-05-11.md -``` -**结果**：18,762 字节，生成时间 09:31 ✅（cron 调度正常执行） - -```bash -ls -la reports/daily/html/ -``` -**结果**：`daily_report_2026-05-10.html` + `daily_report_2026-05-11.html` 均存在 ✅ - -### 6. API Server 验证（通过 verify_phase6 间接确认） - -verify_phase6 输出： -- `[PASS] API Server 可构建` -- `[PASS] API /health 可用` -- `[PASS] API /api/v1/models 返回 200` -- `[PASS] API 响应 < 500ms (当前: 0.003594s)` -- `[PASS] API 返回模型数据载荷` - -### 7. CI 配置审查 - -```bash -cat .github/workflows/ci.yml -``` -**结果**：配置完整，包含： -- PostgreSQL 16 服务容器 -- Go 测试 + 覆盖率门禁（80%） -- 脚本测试 -- 前端构建 -- Docker 构建 -- golangci-lint -- 产物上传 - -**状态**：untracked，从未触发过真实运行。 - ---- - -## 已完成项 - -### Phase 1~6 全部完成（功能层面） - -| 任务 | 状态 | 验证证据 | -|------|------|----------| -| T-1.1 Phase 1 范围冻结 | ✅ | PRD.md 含"Phase 1 范围"、"非目标"、"验收标准" | -| T-1.2 文档冲突清理 | ✅ | FEATURE_LIST.md / TECHNICAL_DESIGN.md 无冲突描述 | -| T-2.1 OpenRouter 采集器 | ✅ | `scripts/fetch_openrouter.go` 存在，可构建运行 | -| T-2.2 PostgreSQL migration | ✅ | `db/migrations/*.sql` 存在，12 张表已落库 | -| T-2.3 日报生成器 | ✅ | `reports/daily/` 存在，今日已生成 | -| T-3.1 Explorer 页面 | ✅ | `frontend/src/pages/Explorer.tsx` 存在，含分页/排序/筛选 | -| T-3.2 Dashboard 组件 | ✅ | `frontend/src/pages/Dashboard.tsx` 存在，集成 ECharts | -| T-4.1 项目本地任务清单 | ✅ | `GOALS.md` / `TASKS.md` 存在 | -| T-4.2 验证器本地化 | ✅ | `verification_executor.go` 默认读取本项目 TASKS.md | -| T-4.3 项目执行说明 | ✅ | `OPENCLAW_EXECUTION.md` 存在 | -| T-5.1 生产级实施计划 | ✅ | `IMPLEMENTATION_PLAN.md` 含国内厂商/数据质量/降级/审计日志 | -| T-5.2 任务清单对齐 | ✅ | TASKS.md 含生产级收口任务 | -| T-5.3 环境变量与真实数据链路 | ✅ | `.env` 已配置，真实采集+写库+日报通过 | -| T-5.4 前端构建系统初始化 | ✅ | `package.json` / `tsconfig.json` / `vite.config.ts` 存在，构建通过 | -| T-5.5 自动采集与日报调度 | ✅ | `crontab` 已配置，日报降级逻辑存在 | -| **Phase 6 综合验收** | **✅** | **verify_phase6.sh 14/14 PASS** | - -### Phase 6 新增确认项（本轮首次验证） - -| 检查项 | 说明 | -|--------|------| -| 全仓 Go 测试通过 | verify_phase6 确认 | -| 脚本级采集器单测通过 | verify_phase6 确认 | -| 真实采集并输出今日日报 | verify_phase6 确认（09:31 已生成） | -| API Server 可构建 | verify_phase6 确认 | -| 健康检查脚本通过 | verify_phase6 确认 | -| 密钥未硬编码进源码 | verify_phase6 确认 | -| 最近 7 次采集成功率 95% | verify_phase6 确认 | -| API /health 可用 | verify_phase6 确认 | -| API /api/v1/models 返回 200 | verify_phase6 确认 | -| API 响应 < 500ms | verify_phase6 确认（0.003594s） | -| API 返回模型数据载荷 | verify_phase6 确认 | -| Phase 6 性能文档存在 | verify_phase6 确认 | -| 前端已具备测试入口 | verify_phase6 确认 | - ---- - -## 未完成项 - -### 工程纪律层面（严重，持续恶化） - -| 缺口 | 影响 | 当前状态 | 变化 | -|------|------|----------|------| -| **60+ 小时无 commit** | 所有文档/代码修改未落盘，版本历史断裂，回滚能力丧失 | 🔴 未修复 | **恶化**（从 56h → 60h） | -| **12 tracked 文件未 stage** | PRD.md / TASKS.md / OPENCLAW_EXECUTION.md / TECHNICAL_DESIGN.md 等核心文档修改未提交 | 🔴 未修复 | 无变化 | -| **17 untracked 文件** | 含 .github/workflows/、cmd/、internal/、frontend/ 完整代码 | 🔴 未修复 | 无变化 | -| **CI 从未真实运行** | `.github/workflows/` 存在但未触发过 | 🔴 未验证 | 无变化 | - -### 功能层面（Phase 6 后待规划） - -| 缺口 | 影响 | 当前状态 | -|------|------|----------| -| Phase 6+ 范围未定义 | 项目已完成 Phase 1~6，但下一步目标模糊 | 🟡 待定义 | -| 飞书推送未验证真实成功 | `scripts/feishu_alert.sh` 存在且可执行，但未验证真实推送 | 🟡 未验证 | -| 国内厂商真实 API 采集 | 当前为种子数据录入（manual=12），非真实 API 采集 | 🟡 Phase 2 规划 | -| `collection_stats` 表名不一致 | verify_phase2 引用 `collection_stats`，实际表名为 `collector_stats` | 🟡 文档/脚本不一致 | - ---- - -## 伪进展/文档与实现不一致项 - -### 1. 文档修改未提交导致的"最新版"幻觉（恶化） - -- **TECHNICAL_DESIGN.md**：`git diff` 显示 1196 行修改（最大变更），已 60+ 小时未提交。 -- **OPENCLAW_EXECUTION.md**：`git diff` 显示 240 行修改。 -- **PRD.md**：`git diff` 显示 148 行修改。 -- **TASKS.md**：`git diff` 显示 98 行修改。 -- **scripts/fetch_openrouter.go**：`git diff` 显示 486 行修改。 -- **scripts/generate_daily_report.go**：`git diff` 显示 511 行修改。 - -**风险**：累计 2298 行新增 diff 未落盘，任何工作区丢失将导致 Phase 1~6 全部成果（含 API Server、CI 配置、前端完整代码）消失。 - -### 2. `collection_stats` vs `collector_stats` 表名不一致 - -- verify_phase2.sh 检查 `collection_stats` 表，但实际数据库中表名为 `collector_stats`。 -- verify_phase2 仍 PASS，说明检查逻辑可能通过其他方式满足（或检查的是不同指标）。 -- **建议**：统一表名或更新验证脚本。 - -### 3. `IMPLEMENTATION_PLAN.md` 双文件混乱 - -- `IMPLEMENTATION_PLAN.md` 和 `IMPLEMENTATION_PLAN_v1.1.md` 同时存在。 -- 存在 `IMPLEMENTATION_PLAN.md.bak-corrupt-20260510-0905`（5 字节损坏文件）。 -- **建议**：清理备份文件，确认主文件版本。 - -### 4. 根目录二进制文件 - -- `fetch_openrouter`（7.5MB）和 `fetch_openrouter_test`（8.5MB）仍在根目录。 -- 应加入 `.gitignore` 避免误提交。 - ---- - -## 最大 5 个关键 Gap - -| 优先级 | Gap | 影响 | 建议行动 | -|--------|-----|------|----------| -| **P0** | **60+ 小时 commit 停滞** | 所有工作成果未落盘，存在丢失风险；团队协作无法基于 git 进行；Phase 6 成果（API Server、CI、前端）全部在 git 外 | 立即执行 `git add` + `git commit`，提交所有已验证的变更 | -| **P0** | **untracked 核心代码未入版本控制** | `.github/`、`cmd/`、`internal/` 等目录不在 git 中，CI 和核心服务代码无版本保护 | 同上，一并提交；并更新 `.gitignore` 排除二进制文件 | -| **P1** | **CI 配置未验证** | `.github/workflows/ci.yml` 完整但未触发过，可能配置错误导致首次 push 时 CI 失败 | 提交后 push 到 GitHub，观察 Actions 首次运行结果 | -| **P1** | **Phase 6+ 范围未定义** | 项目已完成 Phase 1~6，但下一步目标模糊，可能导致方向漂移 | 更新 PRD/IMPLEMENTATION_PLAN，明确 Phase 6+ 范围（建议：多数据源采集器框架 + 飞书推送验证） | -| **P1** | **BACKLOG 文件持续膨胀** | `OPENCLAW_CAPABILITY_BACKLOG.md` 已从 ~6KB 膨胀到 ~38KB，每次 review 读取成本递增 | 实施分层归档，将已修复/重复问题移入独立归档文件 | - ---- - -## 下一轮最值得推进的 3 件事 - -1. **立即提交所有变更**：`git add -A && git commit -m "feat: Phase 1-6 全量验收通过"`。这是当前最紧急的工程纪律修复，已 60 小时未执行。 -2. **验证 CI 首次运行**：提交并 push 到 GitHub 后，观察 Actions 是否成功，修复任何 CI 配置问题（特别是 `internal/` 包路径、覆盖率门禁）。 -3. **定义 Phase 6+ 范围**：更新 PRD/IMPLEMENTATION_PLAN，明确 Phase 6 之后的目标（建议：① 多数据源采集器框架 ② 飞书推送真实验证 ③ 前端与 API 联调）。 - ---- - -## 附录：验证命令完整输出 - -### verify_phase6.sh - -``` -=== Phase 6 综合验收检查 === -[PASS] Phase 1~5 总门禁通过 -[PASS] 全仓 Go 测试通过 -[PASS] 脚本级采集器单测通过 -[PASS] 真实采集并输出今日日报 -[PASS] API Server 可构建 -[PASS] 健康检查脚本通过 -[PASS] 密钥未硬编码进源码 -[PASS] 最近 7 次采集成功率达到 95% -[PASS] API /health 可用 -[PASS] API /api/v1/models 返回 200 -[PASS] API 响应 < 500ms (当前: 0.003594s) -[PASS] API 返回模型数据载荷 -[PASS] Phase 6 性能文档存在 -[PASS] 前端已具备测试入口 - -SUMMARY pass=14 fail=0 warn=0 -PHASE_RESULT: PASS -``` - -### verify_pre_phase6.sh - -``` -PRE_PHASE6_RESULT: PASS -(52/52 检查项全部通过) -``` - ---- - -*Review 完成时间：2026-05-11 09:35 Asia/Shanghai* -*下次 review 建议：提交完成后立即做一次 delta review，确认 git 状态清洁。* diff --git a/reports/openclaw/2026-05-11-1430-review.md b/reports/openclaw/2026-05-11-1430-review.md deleted file mode 100644 index 4052996..0000000 --- a/reports/openclaw/2026-05-11-1430-review.md +++ /dev/null @@ -1,330 +0,0 @@ -# OpenClaw Afternoon Review — 2026-05-11 14:30 Asia/Shanghai - -> **Review ID**: llm-intelligence-afternoon-review -> **Trigger**: cron `830ba8ca-9863-4d4d-9c45-4e30860ea27a` -> **Reviewer**: 宰相（AI Agent） -> **Scope**: 高频真实状态 review，非破坏性，不改业务代码 - ---- - -## Context - -### Review Frame - -- **本次 review 的时间窗口**：距上一次 review（2026-05-11 09:30）约 **5 小时** -- **与最后一次真实 commit 的间隔**：距 `ba054f0`（2026-05-08 13:49）已过去 **约 73 小时** -- **本轮是否存在仓库状态变化**：**无 delta** — 与 09:30 review 相比，git 状态完全一致（14 tracked + 73 untracked 文件，零新增 commit） - -### Stage Judgment - -- **当前真实阶段**：Phase 1~6 全部验收通过（功能层面），但工程纪律严重滞后 -- **主要判断依据**： - - `runtime-verified`：verify_phase1~6.sh 全部 PASS（52+14 检查项），API Server 可构建且 `/health`、`/api/v1/models` 返回 200 - - `artifact-present`：14 tracked + 73 untracked 文件持续未提交，含核心代码（cmd/、internal/、frontend/）、CI 配置、验证脚本 - - `doc-claimed`：TASKS.md 标记 T-1~T-5 全部完成，但所有修改均不在 git 历史中 -- **本轮背景说明**： - - 这是 cron review 首次在 5 小时窗口内发现**零变化** — 说明 09:30→14:30 期间无任何代码/文档变更 - - 数据链路仍在自动运行（14:31 生成今日日报），cron 调度正常 - - 73 个 untracked 文件比 09:30 报告的 17 个大幅增加 — 原因是 09:30 的统计遗漏了 scripts/、reports/、docs/ 等目录下的新增文件 - ---- - -## Evidence - -### Evidence Grades - -- `runtime-verified`：验证脚本真实执行通过、数据库查询返回真实数据、API Server 可构建运行 -- `artifact-present`：文件存在但不在 git 历史中（untracked 或 modified 未 stage） -- `doc-claimed`：文档/任务表声称完成，但未提交到版本控制 - -### Verification Commands - -#### 1. 基础状态检查 - -```bash -git status --short -``` -**结果**：14 modified 文件 + 73 untracked 文件（与 09:30 完全一致，零变化）。 -- **证据等级**：`runtime-verified` - -```bash -git log --oneline -1 --since="2026-05-11" -``` -**结果**：无输出（05-11 至今零 commit）。 -- **证据等级**：`runtime-verified` - -```bash -git log --format="%H %ci %s" --since="2026-05-08" -``` -**结果**：无输出（05-08 13:49 后零 commit）。 -- **证据等级**：`runtime-verified` - -```bash -git diff --stat -``` -**结果**：14 个 tracked 文件，3006 行新增 / 1035 行删除。 -- **证据等级**：`runtime-verified` - -#### 2. Phase 验收脚本（全部执行） - -| 脚本 | 结果 | 通过/总计 | 证据等级 | -|------|------|-----------|----------| -| `verify_phase1.sh` | **PASS** | 9/9 | `runtime-verified` | -| `verify_phase2.sh` | **PASS** | 9/9 | `runtime-verified` | -| `verify_phase3.sh` | **PASS** | 10/10 | `runtime-verified` | -| `verify_phase4.sh` | **PASS** | 10/10 | `runtime-verified` | -| `verify_phase5.sh` | **PASS** | 14/14 | `runtime-verified` | -| `verify_pre_phase6.sh` | **PASS** | 52/52 | `runtime-verified` | -| `verify_phase6.sh` | **PASS** | **14/14** | `runtime-verified` | - -#### 3. 构建与测试验证 - -```bash -make ci-fetch-openrouter -``` -**结果**：构建 + 单元测试全部通过（TestParseModels PASS, TestRunNoAPIKey PASS）。 -- **证据等级**：`runtime-verified` - -#### 4. 数据库状态验证 - -```bash -psql $DATABASE_URL -c "SELECT table_name FROM information_schema.tables WHERE table_schema='public' ORDER BY table_name;" -``` -**结果**：12 张表全部存在（audit_log, collector_stats, daily_report, free_tier, model_prices, model_provider, models, operator, pricing_history, region_pricing, report_runs, user_subscription）。 -- **证据等级**：`runtime-verified` - -```bash -psql $DATABASE_URL -c "SELECT COUNT(*) as models, COUNT(*) FILTER (WHERE updated_at >= NOW() - INTERVAL '24 hours') as fresh_24h FROM models;" -``` -**结果**：models=377，fresh_24h=377（**100% 24 小时内新鲜**）。 -- **证据等级**：`runtime-verified` - -```bash -psql $DATABASE_URL -c "SELECT COUNT(*) as report_runs, MAX(created_at) as last_run FROM report_runs;" -``` -**结果**：report_runs=6，last_run=2026-05-11 14:31:14（cron 调度正常执行）。 -- **证据等级**：`runtime-verified` - -```bash -psql $DATABASE_URL -c "SELECT COUNT(*) as audit_logs FROM audit_log;" -``` -**结果**：audit_logs=1859（比 09:30 增加 365 条，说明 5 小时内又有采集/写库活动）。 -- **证据等级**：`runtime-verified` - -```bash -psql $DATABASE_URL -c "SELECT source, COUNT(*) FROM models GROUP BY source ORDER BY COUNT(*) DESC;" -``` -**结果**：openrouter=365，manual=12（国内厂商种子数据）。 -- **证据等级**：`runtime-verified` - -#### 5. 日报产物验证 - -```bash -ls -la reports/daily/daily_report_2026-05-11.md -``` -**结果**：7334 字节，生成时间 14:31（cron 调度正常执行）。 -- **证据等级**：`runtime-verified` - -```bash -ls -la reports/daily/html/ -``` -**结果**：`daily_report_2026-05-10.html` + `daily_report_2026-05-11.html` 均存在。 -- **证据等级**：`runtime-verified` - -#### 6. API Server 验证（通过 verify_phase6 间接确认） - -verify_phase6 输出： -- `[PASS] API Server 可构建` -- `[PASS] API /health 可用` -- `[PASS] API /api/v1/models 返回 200` -- `[PASS] API 响应 < 500ms (当前: 0.005496s)` -- `[PASS] API 返回模型数据载荷` -- **证据等级**：`runtime-verified` - -#### 7. CI 配置审查 - -```bash -cat .github/workflows/ci.yml -``` -**结果**：配置完整（PostgreSQL 16 服务、Go 测试+覆盖率门禁 80%、前端构建、Docker 构建、golangci-lint、产物上传）。 -- **证据等级**：`artifact-present`（文件存在但 untracked，从未触发过真实运行） - -#### 8. 表名一致性验证 - -```bash -psql $DATABASE_URL -c "SELECT table_name FROM information_schema.tables WHERE table_name IN ('collection_stats', 'collector_stats');" -``` -**结果**：仅 `collector_stats` 存在。 - -```bash -grep -n "collection_stats\|collector_stats" scripts/verify_phase2.sh -``` -**结果**：verify_phase2.sh 第 23 行正确引用 `collector_stats`（与 09:30 review 报告的 "collection_stats" 说法矛盾，实际脚本已正确）。 -- **证据等级**：`runtime-verified` -- **结论**：09:30 review 的 "collection_stats vs collector_stats" 问题为**误报**，实际脚本与 schema 一致。 - -### Completed - -#### Phase 1~6 全部完成（功能层面） - -| 任务 | 验证证据 | 证据等级 | -|------|----------|----------| -| T-1.1 Phase 1 范围冻结 | PRD.md 含"Phase 1 范围"、"非目标"、"验收标准" | `artifact-present`（未提交） | -| T-1.2 文档冲突清理 | FEATURE_LIST.md / TECHNICAL_DESIGN.md 无冲突描述 | `artifact-present`（未提交） | -| T-2.1 OpenRouter 采集器 | `scripts/fetch_openrouter.go` 存在，可构建运行 | `runtime-verified` | -| T-2.2 PostgreSQL migration | `db/migrations/*.sql` 存在，12 张表已落库 | `runtime-verified` | -| T-2.3 日报生成器 | `reports/daily/` 存在，今日 14:31 已生成 | `runtime-verified` | -| T-3.1 Explorer 页面 | `frontend/src/pages/Explorer.tsx` 存在，含分页/排序/筛选 | `artifact-present`（未提交） | -| T-3.2 Dashboard 组件 | `frontend/src/pages/Dashboard.tsx` 存在，集成 ECharts | `artifact-present`（未提交） | -| T-4.1 项目本地任务清单 | `GOALS.md` / `TASKS.md` 存在 | `artifact-present`（未提交） | -| T-4.2 验证器本地化 | `verification_executor.go` 默认读取本项目 TASKS.md | `runtime-verified` | -| T-4.3 项目执行说明 | `OPENCLAW_EXECUTION.md` 存在 | `artifact-present`（未提交） | -| T-5.1 生产级实施计划 | `IMPLEMENTATION_PLAN.md` 含国内厂商/数据质量/降级/审计日志 | `artifact-present`（未提交） | -| T-5.2 任务清单对齐 | TASKS.md 含生产级收口任务 | `artifact-present`（未提交） | -| T-5.3 环境变量与真实数据链路 | `.env` 已配置，真实采集+写库+日报通过 | `runtime-verified` | -| T-5.4 前端构建系统初始化 | `package.json` / `tsconfig.json` / `vite.config.ts` 存在，构建通过 | `runtime-verified` | -| T-5.5 自动采集与日报调度 | `crontab` 已配置，日报降级逻辑存在 | `runtime-verified` | -| **Phase 6 综合验收** | **verify_phase6.sh 14/14 PASS** | **`runtime-verified`** | - -### Incomplete - -#### 工程纪律层面（严重，持续恶化） - -| 缺口 | 影响 | 当前状态 | 变化 | -|------|------|----------|------| -| **73 小时无 commit** | 所有文档/代码修改未落盘，版本历史断裂，回滚能力丧失 | 🔴 未修复 | **恶化**（从 60h → 73h） | -| **14 tracked 文件未 stage** | PRD.md / TASKS.md / OPENCLAW_EXECUTION.md / TECHNICAL_DESIGN.md / scripts/ 等核心文件修改未提交 | 🔴 未修复 | 无变化 | -| **73 untracked 文件** | 含 .github/workflows/、cmd/、internal/、frontend/ 完整代码、验证脚本、review 报告、Docker 配置 | 🔴 未修复 | **恶化**（从 17 → 73，统计口径修正后发现更多） | -| **无 .gitignore** | 根目录二进制文件（fetch_openrouter 7.5MB、fetch_openrouter_test 8.5MB、generate_daily_report 9.6MB）可能被误提交 | 🔴 未修复 | 无变化 | -| **CI 从未真实运行** | `.github/workflows/ci.yml` 完整但未触发过 | 🔴 未验证 | 无变化 | - -#### 功能层面（Phase 6 后待规划） - -| 缺口 | 影响 | 当前状态 | -|------|------|----------| -| Phase 6+ 范围未定义 | 项目已完成 Phase 1~6，但下一步目标模糊 | 🟡 待定义 | -| 飞书推送未验证真实成功 | `scripts/feishu_alert.sh` 存在且可执行，但未验证真实推送 | 🟡 未验证 | -| 国内厂商真实 API 采集 | 当前为种子数据录入（manual=12），非真实 API 采集 | 🟡 Phase 2 规划 | - -### Inconsistencies - -#### 1. 文档修改未提交导致的"最新版"幻觉（恶化） - -- **TECHNICAL_DESIGN.md**：`git diff` 显示 1196 行修改（最大变更），已 73+ 小时未提交。 -- **OPENCLAW_EXECUTION.md**：`git diff` 显示 380 行修改。 -- **PRD.md**：`git diff` 显示 148 行修改。 -- **TASKS.md**：`git diff` 显示 119 行修改。 -- **scripts/fetch_openrouter.go**：`git diff` 显示 486 行修改。 -- **scripts/generate_daily_report.go**：`git diff` 显示 1028 行修改。 - -**风险**：累计 3006 行新增 diff 未落盘，任何工作区丢失将导致 Phase 1~6 全部成果（含 API Server、CI 配置、前端完整代码、验证脚本）消失。 - -#### 2. `IMPLEMENTATION_PLAN.md` 双文件 + 损坏备份 - -- `IMPLEMENTATION_PLAN.md` 和 `IMPLEMENTATION_PLAN_v1.1.md` 同时存在（内容相同）。 -- 存在 `IMPLEMENTATION_PLAN.md.bak-corrupt-20260510-0905`（损坏备份文件）。 -- **建议**：清理备份文件，确认主文件版本。 - -#### 3. 根目录二进制文件 - -- `fetch_openrouter`（7.5MB）、`fetch_openrouter_test`（8.5MB）、`generate_daily_report`（9.6MB）仍在根目录。 -- 无 `.gitignore` 文件，这些二进制文件有被误提交的风险。 - -#### 4. 09:30 review 误报修正 - -- 09:30 review 报告 "collection_stats vs collector_stats 表名不一致" 为**误报**。 -- 实际 verify_phase2.sh 第 23 行正确引用 `collector_stats`，与数据库 schema 一致。 -- **教训**：review 中声称的 "不一致" 必须二次验证，不能仅凭记忆或旧报告复制。 - -### Key Gaps - -| Gap | 优先级 | 影响 | 证据 | -|-----|--------|------|------| -| **73 小时 commit 停滞** | **P0** | 所有工作成果未落盘，存在丢失风险；团队协作无法基于 git 进行；Phase 6 成果全部在 git 外 | `runtime-verified`：git log 显示 05-08 13:49 后零 commit | -| **73 untracked 核心文件未入版本控制** | **P0** | `.github/`、`cmd/`、`internal/`、frontend/、scripts/、reports/ 等目录不在 git 中，CI 和核心服务代码无版本保护 | `runtime-verified`：git status --short 显示 73 个 ?? 文件 | -| **无 .gitignore** | **P1** | 二进制文件可能被误提交；未来编译产物、node_modules 等可能污染仓库 | `runtime-verified`：ls 显示根目录 3 个二进制文件，cat .gitignore 返回 "No .gitignore" | -| **CI 配置未验证** | **P1** | `.github/workflows/ci.yml` 完整但未触发过，可能配置错误导致首次 push 时 CI 失败 | `artifact-present`：ci.yml 存在但 untracked | -| **Phase 6+ 范围未定义** | **P1** | 项目已完成 Phase 1~6，但下一步目标模糊，可能导致方向漂移 | `doc-claimed`：PHASE2_REQUIREMENTS.md 存在但未明确优先级 | - ---- - -## Outcome - -### Executive Summary - -**项目状态：Phase 1~6 全部验收通过（功能层面），但 commit 停滞已恶化到 73+ 小时，工程纪律风险持续累积。** - -距上一次 review（05-11 09:30）约 **5 小时**，距最后一次真实 commit（`ba054f0`，2026-05-08 13:49）已过去 **约 73 小时**。仓库状态**零代码变更**（无新 commit），这是 cron review 首次在 5 小时窗口内发现完全零变化。 - -**关键变化（与 09:30 相比）**： -- **无 delta**：git 状态完全一致，09:30→14:30 期间无任何代码/文档变更。 -- **数据链路仍在运行**：models=377（100% 24h 新鲜），report_runs=6→6（14:31 新日报已生成），audit_logs=1494→1859（5 小时内新增 365 条）。 -- **09:30 误报修正**："collection_stats vs collector_stats" 实际为误报，verify_phase2.sh 与 schema 一致。 -- **untracked 文件统计修正**：09:30 报告 17 个 untracked，实际为 73 个（遗漏了 scripts/、reports/、docs/ 等目录）。 - -### Risk Judgment - -| 风险项 | 等级 | 趋势 | -|--------|------|------| -| commit 停滞 | 🔴 严重 | 恶化（60h → 73h） | -| untracked 核心代码 | 🔴 严重 | 统计修正后更严重 | -| 数据链路丢失 | 🟢 低 | 数据在自动运行，但代码未提交 | -| CI 首次运行失败 | 🟡 中 | 未变化 | -| Phase 6+ 方向漂移 | 🟡 中 | 未变化 | - -### Stage Conclusion - -功能上已完成 Phase 1~6，API Server 已可运行，数据链路 100% 新鲜。但工程纪律（提交、版本控制、CI 验证）严重滞后，构成**最大风险项**。73 小时无 commit 意味着所有 Phase 6 成果（API Server、前端完整代码、验证脚本、CI 配置）完全不在 git 历史中。 - -### Decisions - -- **本轮最重要的落地结论**： - 1. **必须立即执行 `git add -A && git commit`** — 73 小时无 commit 是不可接受的工程纪律缺口。 - 2. **必须先创建 `.gitignore`** — 排除二进制文件、node_modules、.env 等敏感/大文件。 - 3. **09:30 review 的 "collection_stats" 问题为误报** — 已在本轮修正，说明 review 中的声称必须二次验证。 -- **需要更新 `OPENCLAW_CAPABILITY_BACKLOG.md`**：是，新增本轮发现（无 .gitignore、review 误报教训）。 - ---- - -## Next - -### Priority Actions - -1. **立即提交所有变更** - - **Owner**：用户（人工决策，AI 不代执行 git commit） - - **预期证据**：`git log --oneline -1` 显示新 commit，时间戳在 2026-05-11 14:30 之后 - - **建议步骤**： - 1. 创建 `.gitignore`（排除二进制文件、node_modules、.env） - 2. `git add -A` - 3. `git commit -m "feat: Phase 1-6 全量验收通过，API Server + CI + 前端落地"` - 4. `git push origin main` - -2. **验证 CI 首次运行** - - **Owner**：用户（push 后自动触发） - - **预期证据**：GitHub Actions 页面显示首次 workflow run，状态为 pass/fail - - **注意**：CI 包含覆盖率门禁 80%，需确认 internal/ 包测试覆盖率达标 - -3. **定义 Phase 6+ 范围** - - **Owner**：产品架构师（宰相辅助） - - **预期证据**：PRD.md / IMPLEMENTATION_PLAN.md 更新 Phase 6+ 章节，明确 P0/P1/P2 - - **建议方向**： - 1. 多数据源采集器框架（国内厂商 API 接入） - 2. 飞书推送真实验证 - 3. 前端与 API Server 联调（当前前端使用本地 JSON 回退，未真实调用 API） - -### Follow-up Notes - -- **需要人工介入的事项**： - - `git commit` 和 `git push` 必须由用户执行（涉及版本控制决策） - - `.gitignore` 内容需用户确认（特别是 .env、密钥相关文件） - - Phase 6+ 优先级需用户确认 - -- **下轮 review 应重点复核的事项**： - - git 状态是否已清洁（新 commit 是否已落盘） - - GitHub Actions 是否已触发并 pass - - 09:30 review 误报教训：review 中的 "不一致" 声称必须二次验证，不能复制旧报告 - ---- - -*Review 完成时间：2026-05-11 14:35 Asia/Shanghai* -*下次 review 建议：提交完成后立即做一次 delta review，确认 git 状态清洁。* diff --git a/reports/openclaw/2026-05-11-2130-review.md b/reports/openclaw/2026-05-11-2130-review.md deleted file mode 100644 index 3a90111..0000000 --- a/reports/openclaw/2026-05-11-2130-review.md +++ /dev/null @@ -1,344 +0,0 @@ -# OpenClaw Night Review — 2026-05-11 21:30 Asia/Shanghai - -> **Review ID**: llm-intelligence-night-review -> **Trigger**: cron `b769d061-e102-4f82-9e9f-3a659e79f6e7` -> **Reviewer**: 宰相（AI Agent） -> **Scope**: 高频真实状态 review，非破坏性，不改业务代码 - ---- - -## Context - -### Review Frame - -- **本次 review 的时间窗口**：距上一次 review（2026-05-11 14:30）约 **7 小时** -- **与最后一次真实 commit 的间隔**：距 `ba054f0`（2026-05-08 13:49）已过去 **约 80 小时** -- **本轮是否存在仓库状态变化**：**有 delta** — 与 14:30 review 相比，出现两项关键回归 - -### Stage Judgment - -- **当前真实阶段**：Phase 1~6 功能层面已落地，但 **验收脚本出现回归 FAIL**，工程纪律持续恶化 -- **主要判断依据**： - - `runtime-verified`：verify_phase2~5.sh 仍 PASS，但 verify_phase1.sh 和 verify_phase6.sh 新出现 FAIL - - `artifact-present`：14 modified + 81 untracked 文件持续未提交，含核心代码、CI 配置、验证脚本 - - `doc-claimed`：TASKS.md 标记 T-1~T-5 全部完成，但所有修改均不在 git 历史中 -- **本轮背景说明**： - - 这是 cron review 首次发现 **验收脚本从 PASS 退化为 FAIL**（14:30 时 verify_phase1/phase6 均为 PASS） - - 数据链路仍在运行（21:31 生成今日日报），但数据库中 batch_id 回填出现 124 条未完成记录 - - scripts/ 目录下新增 import 脚本导致 `go test ./...` 编译失败（main 函数重定义） - ---- - -## Evidence - -### Evidence Grades - -- `runtime-verified`：验证脚本真实执行结果、数据库查询返回真实数据、API Server 可构建运行 -- `artifact-present`：文件存在但不在 git 历史中（untracked 或 modified 未 stage） -- `doc-claimed`：文档/任务表声称完成，但未提交到版本控制 - -### Verification Commands - -#### 1. 基础状态检查 - -```bash -git status --short -``` -**结果**：14 modified 文件 + 81 untracked 文件（untracked 比 14:30 增加 8 个）。 -- **证据等级**：`runtime-verified` - -```bash -git log --oneline -1 --since="2026-05-11" -``` -**结果**：无输出（05-11 全天零 commit）。 -- **证据等级**：`runtime-verified` - -```bash -git log --format="%H %ci %s" --since="2026-05-08" -``` -**结果**：无输出（05-08 13:49 后零 commit，累计 ~80 小时）。 -- **证据等级**：`runtime-verified` - -```bash -git diff --stat -``` -**结果**：14 个 tracked 文件，3560 行新增 / 1100 行删除（diff 规模比 14:30 增加 554 行新增）。 -- **证据等级**：`runtime-verified` - -#### 2. Phase 验收脚本（关键变化） - -| 脚本 | 14:30 结果 | 21:30 结果 | 变化 | 证据等级 | -|------|-----------|-----------|------|----------| -| `verify_phase1.sh` | **PASS** 9/9 | **FAIL** 8/9 | 🔴 **回归** | `runtime-verified` | -| `verify_phase2.sh` | **PASS** 9/9 | **PASS** 9/9 | 无变化 | `runtime-verified` | -| `verify_phase3.sh` | **PASS** 10/10 | **PASS** 10/10 | 无变化 | `runtime-verified` | -| `verify_phase4.sh` | **PASS** 10/10 | **PASS** 10/10 | 无变化 | `runtime-verified` | -| `verify_phase5.sh` | **PASS** 14/14 | **PASS** 14/14 | 无变化 | `runtime-verified` | -| `verify_pre_phase6.sh` | **PASS** 52/52 | **FAIL** 50/52 | 🔴 **回归** | `runtime-verified` | -| `verify_phase6.sh` | **PASS** 14/14 | **FAIL** 12/14 | 🔴 **回归** | `runtime-verified` | - -**关键 FAIL 详情**： - -1. **verify_phase1.sh FAIL** — `血缘字段 batch_id 已完成回填` - - 当前：124 条记录 batch_id 为空，期望 = 0 - - `psql` 验证：`SELECT COUNT(*) FROM models WHERE batch_id IS NULL OR batch_id = ''` → **124** - - **14:30 时此检查为 PASS**（当时 batch_id 可能已全部回填，或检查逻辑不同） - - **根因推测**：21:31 的日报生成或数据采集新写入了 124 条记录，但未回填 batch_id - -2. **verify_phase6.sh FAIL** — `Phase 1~5 总门禁通过` + `全仓 Go 测试通过` - - pre_phase6 因 phase1 FAIL 而连锁 FAIL - - Go 编译错误：`scripts/import_phase2_data.go`、`scripts/import_bytedance_data.go`、`scripts/import_zhipu_data.go` 三文件在同一 package 中重复声明 `main` 和 `ModelPricing` - - `import_zhipu_data.go:44`：`unknown field SceneTags in struct literal` - - **14:30 时此检查为 PASS**（当时这些 import 脚本可能不存在或未纳入全仓测试范围） - -#### 3. 构建与测试验证 - -```bash -make ci-fetch-openrouter -``` -**结果**：构建 + 单元测试全部通过（TestParseModels PASS, TestRunNoAPIKey PASS）。 -- **证据等级**：`runtime-verified` - -#### 4. 数据库状态验证 - -```bash -psql -d llm_intelligence -c "SELECT COUNT(*) as models, COUNT(*) FILTER (WHERE updated_at >= NOW() - INTERVAL '24 hours') as fresh_24h FROM models;" -``` -**结果**：models=501，fresh_24h=492（**98% 24 小时内新鲜**，比 14:30 的 100% 略降）。 -- **证据等级**：`runtime-verified` - -```bash -psql -d llm_intelligence -c "SELECT COUNT(*) as report_runs, MAX(created_at) as last_run FROM report_runs;" -``` -**结果**：report_runs=6，last_run=2026-05-11 09:31:14（**14:30→21:30 期间无新 report_run**）。 -- **证据等级**：`runtime-verified` - -```bash -psql -d llm_intelligence -c "SELECT COUNT(*) as audit_logs FROM audit_log;" -``` -**结果**：audit_logs=2224（比 14:30 增加 365 条，说明 7 小时内仍有采集/写库活动）。 -- **证据等级**：`runtime-verified` - -```bash -psql -d llm_intelligence -c "SELECT source, COUNT(*) FROM models GROUP BY source ORDER BY COUNT(*) DESC;" -``` -**结果**：openrouter=377，manual=12，其他=112（新增 112 条来自其他来源）。 -- **证据等级**：`runtime-verified` - -#### 5. 日报产物验证 - -```bash -ls -la reports/daily/daily_report_2026-05-11.md -``` -**结果**：18027 字节，生成时间 21:31（cron 调度正常执行，比 14:30 的 14:31 版本更新）。 -- **证据等级**：`runtime-verified` - -```bash -ls -la reports/daily/html/ -``` -**结果**：`daily_report_2026-05-10.html` + `daily_report_2026-05-11.html` 均存在（21:31 版本）。 -- **证据等级**：`runtime-verified` - -#### 6. API Server 验证 - -verify_phase6 输出（仍 PASS 的子项）： -- `[PASS] API Server 可构建` -- `[PASS] API /health 可用` -- `[PASS] API /api/v1/models 返回 200` -- `[PASS] API 响应 < 500ms (当前: 0.004164s)` -- `[PASS] API 返回模型数据载荷` -- **证据等级**：`runtime-verified` - -#### 7. CI 配置审查 - -```bash -cat .github/workflows/ci.yml -``` -**结果**：配置完整但未触发过（untracked）。 -- **证据等级**：`artifact-present` - -#### 8. .gitignore 检查 - -```bash -test -f .gitignore && cat .gitignore || echo "NO .gitignore" -``` -**结果**：**仍无 `.gitignore` 文件**。 -- **证据等级**：`runtime-verified` - -### Completed - -#### Phase 2~5 仍维持 PASS - -| 任务 | 验证证据 | 证据等级 | -|------|----------|----------| -| T-2.1 OpenRouter 采集器 | `make ci-fetch-openrouter` PASS | `runtime-verified` | -| T-2.2 PostgreSQL migration | 12 张表存在 | `runtime-verified` | -| T-2.3 日报生成器 | 21:31 日报已生成 | `runtime-verified` | -| T-3.1 Explorer 页面 | `verify_phase4.sh` PASS | `runtime-verified` | -| T-3.2 Dashboard 组件 | `verify_phase4.sh` PASS | `runtime-verified` | -| T-5.3 环境变量与真实数据链路 | models=501, fresh_24h=492 | `runtime-verified` | -| T-5.4 前端构建系统 | `verify_phase5.sh` PASS | `runtime-verified` | -| T-5.5 自动采集与日报调度 | `verify_phase3.sh` PASS | `runtime-verified` | - -### Incomplete - -#### 新回归项（14:30→21:30 期间出现） - -| 缺口 | 影响 | 当前状态 | 变化 | -|------|------|----------|------| -| **batch_id 回填 124 条未完成** | verify_phase1.sh 从 PASS→FAIL，血缘追踪不完整 | 🔴 **新回归** | 14:30 时 PASS | -| **scripts/ 下 import 脚本编译冲突** | `go test ./...` 失败，verify_phase6.sh 从 PASS→FAIL | 🔴 **新回归** | 14:30 时 PASS | - -#### 工程纪律层面（持续恶化） - -| 缺口 | 影响 | 当前状态 | 变化 | -|------|------|----------|------| -| **80 小时无 commit** | 所有文档/代码修改未落盘，版本历史断裂 | 🔴 未修复 | 恶化（73h → 80h） | -| **14 tracked 文件未 stage** | 核心文件修改未提交 | 🔴 未修复 | 无变化 | -| **81 untracked 文件** | 含 .github/、cmd/、internal/、frontend/、scripts/ | 🔴 未修复 | 恶化（73 → 81） | -| **无 .gitignore** | 根目录二进制文件可能被误提交 | 🔴 未修复 | 无变化 | -| **CI 从未真实运行** | `.github/workflows/ci.yml` 完整但未触发过 | 🔴 未验证 | 无变化 | - -#### 功能层面（Phase 6 后待规划） - -| 缺口 | 影响 | 当前状态 | -|------|------|----------| -| Phase 6+ 范围未定义 | 项目已完成 Phase 1~6，但下一步目标模糊 | 🟡 待定义 | -| 飞书推送未验证真实成功 | `scripts/feishu_alert.sh` 存在但未验证真实推送 | 🟡 未验证 | - -### Inconsistencies - -#### 1. 验收脚本出现真实回归（14:30 PASS → 21:30 FAIL） - -- **verify_phase1.sh**：`batch_id 已完成回填` 从 PASS 变为 FAIL（124 条未回填）。 - - 14:30 时 models=377，可能当时 batch_id 已全部回填；21:30 时 models=501，新增 124 条记录未回填 batch_id。 - - **根因**：数据采集流程写入了新记录，但 batch_id 回填逻辑未同步执行。 - - **证据等级**：`runtime-verified` - -- **verify_phase6.sh**：`全仓 Go 测试通过` 从 PASS 变为 FAIL。 - - 14:30→21:30 期间新增了 `scripts/import_bytedance_data.go`、`scripts/import_zhipu_data.go` 等文件。 - - 这些文件与已有的 `scripts/import_phase2_data.go` 在同一 package 中重复声明 `main` 和 `ModelPricing`。 - - `import_zhipu_data.go` 还引用了不存在的 `SceneTags` 字段。 - - **根因**：新增脚本未考虑 package 内符号冲突，且未运行全仓编译验证即落盘。 - - **证据等级**：`runtime-verified` - -#### 2. 文档修改未提交导致的"最新版"幻觉（持续恶化） - -- `git diff --stat` 显示 3560 行新增 diff 未落盘（比 14:30 增加 554 行）。 -- 新增 diff 主要来自 `scripts/generate_daily_report.go`（+1126 行）和 `scripts/fetch_openrouter.go`（+486 行）。 -- **风险**：任何工作区丢失将导致 Phase 1~6 全部成果消失，且新增代码量持续膨胀。 - -#### 3. report_runs 表与日报文件时间不一致 - -- `report_runs` 表 last_run=09:31:14，但 `daily_report_2026-05-11.md` 文件时间戳为 21:31。 -- **可能解释**：日报生成可能绕过了 report_runs 记录，或 report_runs 只记录特定类型的运行。 -- **影响**：无法通过 report_runs 表准确追踪日报生成历史。 - -### Key Gaps - -| Gap | 优先级 | 影响 | 证据 | -|-----|--------|------|------| -| **batch_id 回填 124 条未完成** | **P0** | verify_phase1.sh FAIL，血缘追踪断裂，影响数据可追溯性 | `runtime-verified`：psql 查询返回 124 条空 batch_id | -| **scripts/ 编译冲突导致 verify_phase6 FAIL** | **P0** | 全仓 Go 测试无法通过，CI 首次 push 时必然失败 | `runtime-verified`：`go test ./...` 报 main/ModelPricing 重定义 | -| **80 小时 commit 停滞** | **P0** | 所有工作成果未落盘，存在丢失风险；新增代码持续膨胀 | `runtime-verified`：git log 显示 05-08 后零 commit | -| **81 untracked 核心文件未入版本控制** | **P0** | CI、API Server、前端、验证脚本全部无版本保护 | `runtime-verified`：git status 显示 81 个 ?? 文件 | -| **无 .gitignore** | **P1** | 二进制文件、node_modules、.env 可能被误提交 | `runtime-verified`：根目录 3 个二进制文件共 25MB+ | -| **CI 配置未验证** | **P1** | 首次 push 时 CI 可能因编译冲突直接失败 | `artifact-present`：ci.yml 存在但 untracked | -| **Phase 6+ 范围未定义** | **P1** | 项目方向模糊，可能导致资源分散 | `doc-claimed`：PHASE2_REQUIREMENTS.md 存在但未明确优先级 | - ---- - -## Outcome - -### Executive Summary - -**项目状态：Phase 2~5 仍维持 PASS，但 Phase 1 和 Phase 6 验收脚本出现真实回归。80 小时无 commit，工程纪律风险持续累积。** - -距上一次 review（05-11 14:30）约 **7 小时**，距最后一次真实 commit（`ba054f0`，2026-05-08 13:49）已过去 **约 80 小时**。本轮 review 发现两项**关键回归**： - -1. **batch_id 回填失败**：verify_phase1.sh 从 PASS→FAIL，数据库中 124 条 models 记录 batch_id 为空。这与 models 总量从 377 增至 501 直接相关——新增记录未执行回填。 -2. **scripts/ 目录编译冲突**：verify_phase6.sh 从 PASS→FAIL，新增 import 脚本（bytedance、zhipu）与已有 phase2 import 脚本在同一 package 中重定义 main 和 ModelPricing，且 `SceneTags` 字段未定义。 - -**关键变化（与 14:30 相比）**： -- **两项验收回归**：verify_phase1.sh FAIL、verify_phase6.sh FAIL（14:30 时均为 PASS）。 -- **数据仍在增长**：models=377→501（+124），audit_logs=1859→2224（+365），说明采集链路仍在运行。 -- **日报已更新**：21:31 生成今日日报（文件比 14:30 的 14:31 版本更新）。 -- **untracked 文件增加**：73→81（+8），diff 规模 3006→3560 行（+554）。 -- **commit 停滞恶化**：73h→80h。 - -### Risk Judgment - -| 风险项 | 等级 | 趋势 | -|--------|------|------| -| 验收脚本回归（batch_id + 编译冲突） | 🔴 **严重** | **新出现** | -| commit 停滞 | 🔴 严重 | 恶化（73h → 80h） | -| untracked 核心代码 | 🔴 严重 | 恶化（73 → 81） | -| 数据链路丢失 | 🟢 低 | 数据在自动运行，但代码未提交 | -| CI 首次运行失败 | 🟡 中→🔴 高 | 编译冲突将直接导致 CI FAIL | -| Phase 6+ 方向漂移 | 🟡 中 | 未变化 | - -### Stage Conclusion - -功能上 Phase 2~5 仍稳定，但 **Phase 1 和 Phase 6 验收脚本在本轮 review 周期内出现真实回归**。这说明： -1. 数据采集流程写入了新记录但未同步执行 batch_id 回填 -2. 新增 import 脚本未经过全仓编译验证即落盘 -3. 80 小时无 commit 导致问题无法通过版本历史追溯 - -**最大风险项已从"工程纪律滞后"升级为"验收脚本回归 + 工程纪律滞后"的组合风险。** - -### Decisions - -- **本轮最重要的落地结论**： - 1. **必须立即修复 batch_id 回填** — 124 条空 batch_id 导致 verify_phase1.sh FAIL，影响数据血缘追踪。 - 2. **必须立即修复 scripts/ 编译冲突** — import_bytedance_data.go、import_zhipu_data.go、import_phase2_data.go 三文件冲突，导致 `go test ./...` 无法通过。 - 3. **必须立即执行 `git add -A && git commit`** — 80 小时无 commit，新增代码 3560 行未落盘，且编译冲突说明多文件协作已出现真实问题。 -- **需要更新 `OPENCLAW_CAPABILITY_BACKLOG.md`**：是，新增本轮发现（验收脚本回归、batch_id 回填缺失、编译冲突）。 - ---- - -## Next - -### Priority Actions - -1. **修复 batch_id 回填（阻塞 verify_phase1）** - - **Owner**：数据后端 - - **预期证据**：`bash scripts/verify_phase1.sh` 返回 PHASE_RESULT: PASS - - **建议步骤**： - 1. 检查 `scripts/fetch_openrouter.go` 或 `scripts/generate_daily_report.go` 中写入 models 表时是否遗漏 batch_id - 2. 对已有 124 条空 batch_id 记录执行回填（可用采集批次号或时间戳生成） - 3. 验证 `psql -d llm_intelligence -c "SELECT COUNT(*) FROM models WHERE batch_id IS NULL OR batch_id = ''"` 返回 0 - -2. **修复 scripts/ 编译冲突（阻塞 verify_phase6）** - - **Owner**：数据后端 - - **预期证据**：`go test ./...` 编译通过，`bash scripts/verify_phase6.sh` 返回 PHASE_RESULT: PASS - - **建议步骤**： - 1. 将 `import_bytedance_data.go`、`import_zhipu_data.go`、`import_phase2_data.go` 改为独立可构建文件（加 `//go:build` 标签或移入子目录） - 2. 修复 `import_zhipu_data.go:44` 的 `SceneTags` 未知字段错误 - 3. 运行 `go test ./...` 确认全仓编译通过 - -3. **立即提交所有变更（含上述修复）** - - **Owner**：用户（人工决策，AI 不代执行 git commit） - - **预期证据**：`git log --oneline -1` 显示新 commit，时间戳在 2026-05-11 21:30 之后 - - **建议步骤**： - 1. 先修复上述两项回归 - 2. 创建 `.gitignore`（排除二进制文件、node_modules、.env） - 3. `git add -A && git commit -m "feat: Phase 1-6 全量验收通过 + batch_id 修复 + 编译冲突修复"` - 4. `git push origin main` - -### Follow-up Notes - -- **需要人工介入的事项**： - - `git commit` 和 `git push` 必须由用户执行 - - `.gitignore` 内容需用户确认 - - batch_id 回填策略需确认（使用何种默认值/生成规则） - -- **下轮 review 应重点复核的事项**： - - verify_phase1.sh 和 verify_phase6.sh 是否已恢复 PASS - - git 状态是否已清洁（新 commit 是否已落盘） - - 新增 import 脚本是否已通过全仓编译验证 - - batch_id 回填是否已固化到采集流程中（避免再次回归） - ---- - -*Review 完成时间：2026-05-11 21:38 Asia/Shanghai* -*下次 review 建议：修复完成后立即做一次 delta review，确认验收脚本恢复 PASS 且 git 状态清洁。* diff --git a/reports/openclaw/2026-05-12-2246-review.md b/reports/openclaw/2026-05-12-2246-review.md deleted file mode 100644 index 5d5b525..0000000 --- a/reports/openclaw/2026-05-12-2246-review.md +++ /dev/null @@ -1,132 +0,0 @@ -# OpenClaw Review — 2026-05-12 22:46 Asia/Shanghai - -> **Review ID**: `llm-intelligence-morning-review` -> **Trigger**: `cron 175a61b2-c2e7-4df4-a994-2fcacdbd24c6` -> **Reviewer**: 宰相（AI Agent） -> **Scope**: 高频真实状态 review，非破坏性，不改业务代码 - ---- - -## Context - -### Review Frame - -- 本次 review 的时间窗口：2026-05-11 21:30 → 2026-05-12 22:46 Asia/Shanghai -- 与上一次 review 的间隔：约 25 小时 -- 与最后一次真实 commit 的间隔：约 33 小时（最后提交：`ba054f0 2026-05-08 13:49:12 +0800`） -- 本轮是否存在仓库状态变化：有 delta；工作区仍高度脏，且 untracked 数量继续扩大 - -### Stage Judgment - -- 当前真实阶段：Phase 1~6 验收门禁当前为可通过状态，但工程纪律与版本管理仍明显落后于实现进度 -- 主要判断依据： - - `runtime-verified`：`bash scripts/verify_phase1.sh`、`bash scripts/verify_phase2.sh`、`bash scripts/verify_phase6.sh` 本轮均 PASS - - `artifact-present`：前端构建入口、CI 配置、API server 目录、日报与历史 review 文件均存在 - - `doc-claimed`：`TASKS.md` 中大量任务标记完成，但对应成果仍未进入 git 历史 -- 本轮背景说明： - - 上一轮（2026-05-11 21:30）报告的 `batch_id` 回填回归与 `scripts/` 编译冲突，本轮未复现，说明此前回归已被修复或环境状态已变化 - - 但仓库依旧存在 14 个 modified、90 个 untracked，且仍停留在 2026-05-08 的最后一次 commit，上述风险没有本质收敛 - -## Evidence - -### Evidence Grades - -- `runtime-verified`：`git status --short`、`git log --oneline -n 8`、`bash scripts/verify_phase1.sh`、`bash scripts/verify_phase2.sh`、`bash scripts/verify_phase6.sh` -- `artifact-present`：`TASKS.md`、`GOALS.md`、`OPENCLAW_EXECUTION.md`、`reports/openclaw/REVIEW_TEMPLATE.md`、`frontend/package.json`、`Makefile`、`.github/`、`reports/daily/` -- `doc-claimed`：`TASKS.md` 中“已完成”状态本身；若未补运行验证，不单独视为完成证据 - -### Verification Commands - -- 命令：`git status --short` - - 结果：14 个 modified，90 个 untracked；核心代码、前端、CI、脚本、文档大量未纳入版本控制。`runtime-verified` -- 命令：`git log --oneline -n 8` - - 结果：最近提交仍停留在 `ba054f0 feat(phase1): OpenRouter采集器接入PostgreSQL，数据链路闭环`；之后无新增 commit。`runtime-verified` -- 命令：`bash scripts/verify_phase1.sh` - - 结果：9/9 PASS，`PHASE_RESULT: PASS`；`batch_id` 空值检查当前为 0。`runtime-verified` -- 命令：`bash scripts/verify_phase2.sh` - - 结果：9/9 PASS，`PHASE_RESULT: PASS`；国内厂商、CNY 定价、多源统计均满足门禁。`runtime-verified` -- 命令：`bash scripts/verify_phase6.sh` - - 结果：14/14 PASS，`PHASE_RESULT: PASS`；全仓 Go 测试、真实采集、API 健康检查、性能门禁均通过。`runtime-verified` - -### Completed - -- 已完成项：Phase 1 基础库表、扩展字段、约束与回填检查当前全部通过 - - 证据：`bash scripts/verify_phase1.sh` PASS。`runtime-verified` -- 已完成项：Phase 2 多源采集、国内厂商覆盖、CNY 定价与审计统计当前全部通过 - - 证据：`bash scripts/verify_phase2.sh` PASS。`runtime-verified` -- 已完成项：Phase 6 综合验收当前可通过，说明 API server、采集、测试与健康检查主链路处于可运行状态 - - 证据：`bash scripts/verify_phase6.sh` PASS。`runtime-verified` -- 已完成项：仓库内已形成项目级执行与审查资产 - - 证据：`TASKS.md`、`GOALS.md`、`OPENCLAW_EXECUTION.md`、`reports/openclaw/REVIEW_TEMPLATE.md` 存在。`artifact-present` - -### Incomplete - -- 未完成项：代码与文档成果仍未进入 git 历史 - - 影响：一旦工作区损坏、误清理或错误覆盖，大量成果不可追溯且可能丢失 - - 当前状态：14 modified + 90 untracked，最后 commit 仍为 2026-05-08。`runtime-verified` -- 未完成项：CI 配置虽已出现，但未见真实触发或提交记录支撑 - - 影响：首次 push 后可能暴露新的集成问题；当前只能认定“配置存在”，不能认定“CI 已验证” - - 当前状态：`.github/` 为 untracked。`artifact-present` -- 未完成项：Phase 6 之后的优先级与收口动作没有被明确冻结 - - 影响：项目容易继续扩散实现面，而不是先收版本管理、提交与发布纪律 - - 当前状态：文档可见 Phase 2/视频等方向，但缺少最新阶段收口决策。`doc-claimed` - -### Inconsistencies - -- 伪进展或文档/实现不一致项：`TASKS.md` 大量任务标记为 ✅，但相当一部分相关文件仍未提交到 git - - 证据：`git status --short` 显示前端、CI、脚本、运行文档、日报等大量成果处于 modified/untracked；因此“已完成”只能说明工作区已有产物，不等价于版本化完成。`runtime-verified` -- 伪进展或文档/实现不一致项：上一轮 review 声称 Phase 1/6 出现回归，本轮未复现 - - 证据：本轮 `verify_phase1.sh` 与 `verify_phase6.sh` 均 PASS；说明回归项至少不是稳定存在的问题，review 需要持续避免把瞬时状态外推成长期结论。`runtime-verified` -- 伪进展或文档/实现不一致项：CI 能力当前只能认定为“文件存在”，不能认定为“流程已跑通” - - 证据：`.github/` 未提交，未见对应 commit/运行痕迹。`artifact-present` - -### Key Gaps - -- Gap：版本控制纪律失效（长期无 commit + 大量 untracked） - - 优先级：P0 - - 影响：真实成果不可追溯、易丢失、难协作、review 成本持续升高 - - 证据：14 modified、90 untracked；最后 commit 为 2026-05-08。`runtime-verified` -- Gap：CI 仍停留在配置存在层，未完成真实验证闭环 - - 优先级：P1 - - 影响：首次提交或 push 时仍可能暴露集成失败 - - 证据：`.github/` 存在但未进入 git 历史。`artifact-present` -- Gap：review 对“回归/恢复”缺少更强的稳定性标注 - - 优先级：P1 - - 影响：可能把短暂故障写成长期问题，或把一次恢复误判为彻底修复 - - 证据：上一轮回归项本轮未复现；需要在 backlog 中补“瞬时回归需二次确认”机制。`runtime-verified` -- Gap：无 delta 审查策略还不够强 - - 优先级：P2 - - 影响：如果只是重复罗列已完成能力，会稀释对老化风险（未提交、未上线、未验证）的关注 - - 证据：最近一次 commit 未变化，但工作区持续积压。`runtime-verified` - -## Outcome - -### Executive Summary - -- 本轮执行摘要：仓库主链路当前是“能跑”的，Phase 1、Phase 2、Phase 6 真实验收都通过；但项目状态依然不是健康交付态，因为大量成果还停留在未提交工作区。 -- 风险判断：短期运行风险中等，版本管理与协作风险高。 -- 阶段结论：当前更像“功能已铺开、工程收口明显滞后”的阶段，而不是可放心宣称稳定收尾的阶段。 - -### Decisions - -- 本轮最重要的落地结论：不要把“验收脚本当前 PASS”误写成“项目已完成收口”；当前最大问题不是主链路不可运行，而是版本化、CI 落地和审查稳定性没有跟上。 -- 是否需要更新 `OPENCLAW_CAPABILITY_BACKLOG.md`：需要；本轮应补充“回归结论稳定性不足”和“无 delta 场景应聚焦老化风险”的能力优化项。 - -## Next - -### Priority Actions - -1. 动作：先收版本控制纪律，按最小安全批次提交核心代码、前端、CI 与验证脚本 - - Owner：集成验收 / 项目主写者 - - 预期证据：`git status --short` 显著收敛，出现新的真实 commit -2. 动作：提交后立即真实触发一次 CI 或等价本地流水线，确认 `.github/workflows` 不是纸面配置 - - Owner：集成验收 - - 预期证据：CI 运行记录或提交后本地等价流水线 PASS -3. 动作：调整 review 规则，对“回归”增加二次确认/恢复标记，避免瞬时状态误导 backlog - - Owner：OpenClaw 执行规范维护者 - - 预期证据：后续 review/backlog 中出现“回归已复现 / 已恢复待观察 / 稳定修复”之类明确状态词 - -### Follow-up Notes - -- 需要人工介入的事项：是否现在就按安全批次提交当前 90 个 untracked 与 14 个 modified；这是本项目最该尽快做的人类决策点 -- 下轮 review 应重点复核的事项：是否出现新 commit、untracked 数量是否下降、CI 是否从 artifact-present 升级为 runtime-verified diff --git a/reports/openclaw/2026-05-13-0015-review.md b/reports/openclaw/2026-05-13-0015-review.md deleted file mode 100644 index ce6e277..0000000 --- a/reports/openclaw/2026-05-13-0015-review.md +++ /dev/null @@ -1,145 +0,0 @@ -# OpenClaw Review — 2026-05-13 00:15 Asia/Shanghai - -> **Review ID**: `llm-intelligence-afternoon-review` -> **Trigger**: `cron 830ba8ca-9863-4d4d-9c45-4e30860ea27a` -> **Reviewer**: 宰相（AI Agent） -> **Scope**: 高频真实状态 review，非破坏性，不改业务代码 - ---- - -## Context - -### Review Frame - -- 本次 review 的时间窗口：2026-05-12 22:46 → 2026-05-13 00:15 Asia/Shanghai -- 与上一次 review 的间隔：约 1 小时 29 分钟 -- 与最后一次真实 commit 的间隔：约 4 天 10 小时（最后提交：`ba054f0 2026-05-08 13:49:12 +0800`） -- 本轮是否存在仓库状态变化：有 delta；工作区仍高度脏，且验证结果相较上一轮出现新的失败 - -### Stage Judgment - -- 当前真实阶段：主实现链路大体可运行，但综合验收当前不是全绿；项目处于“能力已铺开、门禁与工程收口失配”的阶段 -- 主要判断依据： - - `runtime-verified`：`bash scripts/verify_pre_phase6.sh` FAIL、`bash scripts/verify_phase3.sh` FAIL、`bash scripts/verify_phase5.sh` PASS、`bash scripts/verify_phase6.sh` FAIL - - `artifact-present`：日报文件、归档目录、CI 配置、前端入口、review 模板与 backlog 文件均存在 - - `doc-claimed`：`TASKS.md` 中大量任务标记完成，但当前综合门禁并未全部通过 -- 本轮背景说明： - - 上一轮报告把 Phase 6 判断为 PASS，但本轮真实执行显示 `verify_phase6.sh` 为 FAIL - - 进一步拆解后确认，失败并非 Phase 5 或核心实现回归，而是 Phase 3 的“今日归档报告存在”检查与实际归档路径不一致，进而拖累 `verify_pre_phase6.sh` 与 `verify_phase6.sh` - -## Evidence - -### Evidence Grades - -- `runtime-verified`：`git status --short`、`git log --oneline -8`、`git log -1 --format='%H%n%ci%n%s'`、`bash scripts/verify_pre_phase6.sh`、`bash scripts/verify_phase3.sh`、`bash scripts/verify_phase5.sh`、`bash scripts/verify_phase6.sh`、`ls -la reports/daily/2026`、`find reports/daily -maxdepth 3 -type f | grep '2026-05-12'` -- `artifact-present`：`TASKS.md`、`GOALS.md`、`OPENCLAW_EXECUTION.md`、`reports/openclaw/REVIEW_TEMPLATE.md`、`reports/openclaw/OPENCLAW_CAPABILITY_BACKLOG.md`、`reports/daily/2026/05/daily_report_2026-05-12.md` -- `doc-claimed`：`TASKS.md` 中“已完成”状态本身；若无本轮运行验证，不单独视为完成证据 - -### Verification Commands - -- 命令：`git status --short` - - 结果：14 个 modified，90+ 个 untracked；核心代码、前端、CI、脚本、文档与报告大量未入版本控制。`runtime-verified` -- 命令：`git log --oneline -8` - - 结果：最近提交仍停留在 `ba054f0 feat(phase1): OpenRouter采集器接入PostgreSQL，数据链路闭环`。`runtime-verified` -- 命令：`git log -1 --format='%H%n%ci%n%s'` - - 结果：最后 commit 时间为 `2026-05-08 13:49:12 +0800`。`runtime-verified` -- 命令：`bash scripts/verify_pre_phase6.sh` - - 结果：FAIL；Phase 1 PASS、Phase 2 PASS、Phase 4 PASS、Phase 5 PASS，但 Phase 3 FAIL。`runtime-verified` -- 命令：`bash scripts/verify_phase3.sh` - - 结果：仅 `今日归档报告存在` 失败，其余检查 PASS。`runtime-verified` -- 命令：`bash scripts/verify_phase5.sh` - - 结果：14/14 PASS。`runtime-verified` -- 命令：`bash scripts/verify_phase6.sh` - - 结果：FAIL；顶层第一项 `Phase 1~5 总门禁通过` 失败，实际根因来自 `verify_phase3.sh` 失败。`runtime-verified` -- 命令：`ls -la reports/daily/2026` 与 `find reports/daily -maxdepth 3 -type f | grep '2026-05-12'` - - 结果：实际归档文件存在于 `reports/daily/2026/05/daily_report_2026-05-12.md`，而 `verify_phase3.sh` 期待路径由 `date +%Y/%m` 计算得到，当前检查未与现存结构对齐。`runtime-verified` - -### Completed - -- 已完成项：Phase 1 验收当前通过 - - 证据：`verify_pre_phase6.sh` 中 `verify_phase1.sh PASS`。`runtime-verified` -- 已完成项：Phase 2 验收当前通过 - - 证据：`verify_pre_phase6.sh` 中 `verify_phase2.sh PASS`。`runtime-verified` -- 已完成项：Phase 4 前端门禁当前通过 - - 证据：`verify_pre_phase6.sh` 中 `verify_phase4.sh PASS`。`runtime-verified` -- 已完成项：Phase 5 部署/CI 资产门禁当前通过 - - 证据：`bash scripts/verify_phase5.sh` 14/14 PASS。`runtime-verified` -- 已完成项：今日日报主文件与归档文件都已产出 - - 证据：`reports/daily/daily_report_2026-05-12.md` 与 `reports/daily/2026/05/daily_report_2026-05-12.md` 存在。`artifact-present` - -### Incomplete - -- 未完成项：Phase 3 归档检查与实际目录结构未收敛 - - 影响：Phase 3 当前 FAIL，并级联拖累 Pre-Phase 6 与 Phase 6 综合验收 - - 当前状态：`verify_phase3.sh` 的 `今日归档报告存在` 失败。`runtime-verified` -- 未完成项：Phase 6 综合验收当前不可宣称通过 - - 影响：任何“Phase 6 当前 PASS”表述都会构成伪进展 - - 当前状态：`verify_phase6.sh` FAIL。`runtime-verified` -- 未完成项：代码与文档成果仍未进入 git 历史 - - 影响：成果不可追溯、易丢失，且 review 会长期围绕脏工作区打转 - - 当前状态：最后 commit 仍为 2026-05-08；大量 modified/untracked 持续存在。`runtime-verified` -- 未完成项：CI 配置仍未升级为真实运行证据 - - 影响：只能证明配置文件存在，不能证明流水线真的能跑 - - 当前状态：`.github/` 仍为 untracked。`artifact-present` - -### Inconsistencies - -- 伪进展或文档/实现不一致项：上一轮 review 把 `verify_phase6.sh` 记为 PASS，但本轮真实执行为 FAIL - - 证据：本轮直接运行 `bash scripts/verify_phase6.sh` 返回 `PHASE_RESULT: FAIL`。`runtime-verified` -- 伪进展或文档/实现不一致项：Phase 6 顶层错误文案容易让人误以为 Phase 5 失败，实际根因是 Phase 3 失败 - - 证据：`verify_pre_phase6.sh` 输出显示仅 `verify_phase3.sh FAIL`；`verify_phase5.sh` 单独执行为 PASS。`runtime-verified` -- 伪进展或文档/实现不一致项：日报归档文件实际存在，但校验规则未正确识别 - - 证据：文件存在于 `reports/daily/2026/05/`，而当前门禁仍报 `今日归档报告存在` FAIL。`runtime-verified` -- 伪进展或文档/实现不一致项：`TASKS.md` 大量标记 ✅，但当前综合门禁并未全部通过 - - 证据：`verify_phase6.sh` FAIL；因此不能把任务表完成态直接等同于当前整体通过。`runtime-verified` - -### Key Gaps - -- Gap：Phase 3 归档路径/门禁规则失配 - - 优先级：P0 - - 影响：直接导致 Phase 3、Pre-Phase 6、Phase 6 连锁失败，掩盖真实实现状态 - - 证据：`verify_phase3.sh` 唯一失败项为 `今日归档报告存在`，但同日日报归档文件实际存在。`runtime-verified` -- Gap：综合验收错误聚合信息可读性差 - - 优先级：P1 - - 影响：顶层 Phase 6 输出会压扁子脚本内容，误导 review 把根因写错到 Phase 5 或其他阶段 - - 证据：`verify_phase6.sh` 首项失败信息混合了 `verify_pre_phase6.sh` 压缩输出。`runtime-verified` -- Gap：版本控制纪律失效（长期无 commit + 大量 untracked） - - 优先级：P0 - - 影响：真实成果不可追溯、风险老化持续扩大 - - 证据：最后 commit 仍为 2026-05-08，工作区高度脏。`runtime-verified` -- Gap：CI 仍停留在 artifact-present - - 优先级：P1 - - 影响：首次提交后仍可能暴露集成问题 - - 证据：`.github/` 存在但未提交，未见运行痕迹。`artifact-present` - -## Outcome - -### Executive Summary - -- 本轮执行摘要：主实现并未整体失效，Phase 1/2/4/5 当前都通过；真正的新问题是 Phase 3 的归档门禁与现有产物结构失配，导致 Pre-Phase 6 和 Phase 6 被级联打红。 -- 风险判断：实现风险中等，验收可信度风险高，版本管理风险高。 -- 阶段结论：当前不是“整体回归”，也不是“综合验收通过”；更准确的结论是“主链路多数可运行，但验收门禁存在规则缺口，导致整体状态被拉低”。 - -### Decisions - -- 本轮最重要的落地结论：需要优先修 Phase 3 归档校验与 Phase 6 错误聚合可读性，否则 review 会持续误判真实阶段状态。 -- 是否需要更新 `OPENCLAW_CAPABILITY_BACKLOG.md`：需要；本轮应新增“归档路径门禁失配”和“综合验收错误聚合误导根因判断”两项。 - -## Next - -### Priority Actions - -1. 动作：修正 `verify_phase3.sh` 对日报归档路径的检查规则，使其与 `reports/daily/2026/05/` 真实结构一致 - - Owner：集成验收 / 数据后端 - - 预期证据：`bash scripts/verify_phase3.sh` PASS -2. 动作：改进 `verify_phase6.sh` 或 `verify_common.sh` 的失败信息聚合，避免顶层输出压扁子阶段结果 - - Owner：集成验收 - - 预期证据：再次制造子阶段失败时，Phase 6 输出可直接定位到具体 phase 和失败项 -3. 动作：按最小安全批次提交当前核心变更，先把验证脚本、CI、前端与运行文档纳入版本控制 - - Owner：项目主写者 - - 预期证据：出现新的真实 commit，`git status --short` 显著收敛 - -### Follow-up Notes - -- 需要人工介入的事项：是否立即开始做一轮版本化收口提交；否则后续 review 仍会持续被大量 untracked 噪声包围 -- 下轮 review 应重点复核的事项：`verify_phase3.sh` 是否恢复 PASS、`verify_phase6.sh` 是否恢复 PASS、是否出现新 commit 与 CI 真实运行证据 diff --git a/reports/openclaw/2026-05-13-0930-review.md b/reports/openclaw/2026-05-13-0930-review.md deleted file mode 100644 index 26846e9..0000000 --- a/reports/openclaw/2026-05-13-0930-review.md +++ /dev/null @@ -1,128 +0,0 @@ -# OpenClaw Review — 2026-05-13 09:30 Asia/Shanghai - -> **Review ID**: `llm-intelligence-morning-review` -> **Trigger**: `cron 175a61b2-c2e7-4df4-a994-2fcacdbd24c6` -> **Reviewer**: 宰相（AI Agent） -> **Scope**: 高频真实状态 review，非破坏性，不改业务代码 - ---- - -## Context - -### Review Frame - -- 本次 review 的时间窗口：2026-05-13 00:15 → 2026-05-13 09:30 Asia/Shanghai -- 与上一次 review 的间隔：约 9 小时 15 分钟 -- 与最后一次真实 commit 的间隔：约 4 天 19 小时（最后提交：`ba054f0 feat(phase1): OpenRouter采集器接入PostgreSQL，数据链路闭环`） -- 本轮是否存在仓库状态变化：有部分 delta；上一轮记录为 FAIL 的 `verify_phase6.sh` 本轮实测恢复为 PASS，但工作区仍高度脏且无新增 commit - -### Stage Judgment - -- 当前真实阶段：主实现链路与综合门禁当前可运行，但项目仍处于“功能已铺开、工程收口与版本控制明显滞后”的阶段 -- 主要判断依据： - - `runtime-verified`：`git status --short`、`git log --oneline -8`、`bash scripts/verify_phase6.sh` - - `artifact-present`：`TASKS.md`、`GOALS.md`、`OPENCLAW_EXECUTION.md`、`reports/`、`REVIEW_TEMPLATE.md`、`OPENCLAW_CAPABILITY_BACKLOG.md` - - `doc-claimed`：`TASKS.md` 中大量 ✅ 完成态本身；若无本轮运行验证，不能单独视为当前完成证据 -- 本轮背景说明： - - 上一轮 review 报告判断综合验收被 Phase 3 归档门禁拖累；本轮实际执行 `verify_phase6.sh` 已恢复 PASS，说明上一轮暴露的问题更接近瞬时状态、环境/时间窗口差异，当前未复现 - - 虽然门禁恢复，但最后 commit 仍停留在 2026-05-08，大量 modified/untracked 仍未收敛，工程纪律风险无 delta 改善 - -## Evidence - -### Evidence Grades - -- `runtime-verified`：`git status --short`、`git log --oneline -8`、`find . -maxdepth 2 ...`、`find reports -maxdepth 2 -type f | sort`、`bash scripts/verify_phase6.sh` -- `artifact-present`：`TASKS.md`、`GOALS.md`、`OPENCLAW_EXECUTION.md`、`reports/openclaw/REVIEW_TEMPLATE.md`、`reports/openclaw/OPENCLAW_CAPABILITY_BACKLOG.md`、`reports/verification/phase6_status_2026-05-10.md` -- `doc-claimed`：`TASKS.md` 中各任务完成状态与结果说明；除本轮直接运行命令覆盖到的少数门禁外，其他任务本轮未逐项真实复验 - -### Verification Commands - -- 命令：`git status --short && printf '\n---COMMITS---\n' && git log --oneline -8` - - 结果：工作区仍高度脏；`AGENTS.md`、`TASKS.md`、`OPENCLAW_EXECUTION.md`、前端文件、脚本、报告等大量 modified/untracked 持续存在；最近 commit 仍停留在 `ba054f0`。`runtime-verified` -- 命令：`find reports -maxdepth 2 -type f | sort` - - 结果：日报、历史 review、verification 报告、模板和 backlog 文件均存在；说明 review 与验收产物链路已形成持续输出。`runtime-verified` -- 命令：`find . -maxdepth 2 \( -name 'Makefile' -o -name 'package.json' -o -name 'pyproject.toml' -o -name 'requirements.txt' -o -path './scripts/*' \) | sort` - - 结果：当前可执行入口以 `Makefile`、`frontend/package.json`、`scripts/verify_phase1~6.sh`、`scripts/run_real_pipeline.sh`、多组 Go 脚本为主，验证入口完整。`runtime-verified` -- 命令：`bash scripts/verify_phase6.sh` - - 结果：14/14 PASS，`PHASE_RESULT: PASS`；包括 Phase 1~5 总门禁、全仓 Go 测试、真实采集并输出今日日报、API server build、healthcheck、API `/health` 与 `/api/v1/models`、最近 7 次采集成功率、前端测试入口均通过。`runtime-verified` - -### Completed - -- 已完成项：综合验收当前恢复为 PASS - - 证据：`bash scripts/verify_phase6.sh` 返回 `SUMMARY pass=14 fail=0 warn=0` 与 `PHASE_RESULT: PASS`。`runtime-verified` -- 已完成项：项目具备持续输出 review 与 verification 产物的基础设施 - - 证据：`reports/openclaw/` 存在连续多份 review，`reports/verification/` 存在阶段验收状态文件。`artifact-present` -- 已完成项：当前验证入口齐全 - - 证据：存在 `Makefile`、前端 `package.json`、Phase 1~6 验证脚本、真实 pipeline 与多源采集相关脚本。`runtime-verified` - -### Incomplete - -- 未完成项：版本控制收口长期停滞 - - 影响：真实成果不可追溯，review 长期被 modified/untracked 噪声包围，回滚与协作成本高 - - 当前状态：最后 commit 仍停留在 `2026-05-08`，且当前存在大量 modified/untracked。`runtime-verified` -- 未完成项：CI 仍缺少“真实运行成功”证据 - - 影响：只能确认配置/文件存在，不能确认远端流水线在真实仓库中可执行 - - 当前状态：`.github/` 处于 untracked；本轮未见任何 CI run 结果。`artifact-present` -- 未完成项：`TASKS.md` 完成态未与本轮 delta 审查自动对齐 - - 影响：容易把历史完成态误读为“当前整体已持续稳定通过” - - 当前状态：本轮只验证了综合门禁，没有逐项复验所有 ✅ 任务。`doc-claimed` - -### Inconsistencies - -- 伪进展或文档/实现不一致项：上一轮将 `verify_phase6.sh` 记录为 FAIL，但本轮实际执行恢复 PASS - - 证据：本轮直接运行 `bash scripts/verify_phase6.sh` 返回 `PHASE_RESULT: PASS`。`runtime-verified` -- 伪进展或文档/实现不一致项：`reports/verification/phase6_status_2026-05-10.md` 记录 05-10 Phase 6 已 PASS，但此类静态报告不能替代当前状态验证 - - 证据：该文件存在且内容为历史快照；本轮已用真实命令重新验证。`artifact-present` -- 伪进展或文档/实现不一致项：大量任务、文档、CI 与前端资产已存在，但仍未进入 git 历史 - - 证据：`git status --short` 显示大量关键文件 untracked 或 modified。`runtime-verified` - -### Key Gaps - -- Gap：版本控制纪律失效（长期无 commit + 大量 untracked） - - 优先级：P0 - - 影响：成果不可追溯，review 噪声持续扩大，任何“已完成”都缺少稳定版本锚点 - - 证据：最后 commit 仍为 `ba054f0`；工作区高度脏。`runtime-verified` -- Gap：CI 缺少 runtime 级证据 - - 优先级：P1 - - 影响：首轮提交后仍可能暴露集成问题；当前只能说“配置存在”，不能说“流水线已验证可运行” - - 证据：`.github/` 未入版本控制，本轮未看到任何实际 CI run 结果。`artifact-present` -- Gap：review 对瞬时失败缺少稳定性标记 - - 优先级：P1 - - 影响：单次瞬时 FAIL 容易被写成结构性问题，下一轮恢复后又要回滚判断，增加 backlog 噪声 - - 证据：上一轮 Phase 3/6 失败本轮未复现；当前更像短时状态而非稳定回归。`runtime-verified` -- Gap：无 delta 场景下 review 仍主要围绕脏工作区重复报警 - - 优先级：P2 - - 影响：高频 review 价值递减，难以把注意力集中到“风险老化”和“未提交但高价值变更” - - 证据：最近 commit 无变化，主要重复风险仍是未提交变更与未验证 CI。`runtime-verified` - -## Outcome - -### Executive Summary - -- 本轮执行摘要：综合验收当前为 PASS，说明主实现链路可运行；但项目最突出的真实问题已经不是功能缺口，而是版本控制与工程收口滞后。 -- 风险判断：实现风险中等偏低，工程纪律风险高，状态判断噪声风险中等。 -- 阶段结论：项目不应再被描述为“仅差主链路打通”；更准确的判断是“主链路已能通过综合门禁，但尚未完成版本化收口、CI 实跑与 review 降噪治理”。 - -### Decisions - -- 本轮最重要的落地结论：本轮无必要回写 `TASKS.md` / `GOALS.md`；下一步最值得推进的是最小安全批次提交，把当前已存在的核心资产纳入版本控制，并为 CI 争取首次真实运行证据。 -- 是否需要更新 `OPENCLAW_CAPABILITY_BACKLOG.md`：需要；应补充“瞬时失败缺少稳定性标记”本轮复现证据，并更新“日报归档路径门禁失配”从结构性故障降级为待复核的瞬时问题。 - -## Next - -### Priority Actions - -1. 动作：按最小安全批次提交当前核心变更（至少覆盖验证脚本、前端基础、运行文档、CI 配置） - - Owner：项目主写者 - - 预期证据：出现新的真实 commit，`git status --short` 明显收敛 -2. 动作：让 `.github/` 进入版本控制并触发一次真实 CI 运行 - - Owner：集成验收 / 项目主写者 - - 预期证据：仓库出现可引用的 workflow run 结果，review 可引用 `runtime-verified` CI 证据 -3. 动作：为 review / phase 验收增加“瞬时失败 vs 稳定回归”标记规则 - - Owner：集成验收 - - 预期证据：下一次单轮 FAIL 不会直接被 backlog 记录为结构性问题，除非连续复现或可稳定复现 - -### Follow-up Notes - -- 需要人工介入的事项：是否现在安排一轮正式提交与远端推送；这已经比继续扩文档更值钱 -- 下轮 review 应重点复核的事项：是否出现新 commit、CI 是否有真实 run 结果、Phase 6 是否继续保持 PASS、工作区脏状态是否收敛 diff --git a/reports/verification/phase6_status_2026-05-10.md b/reports/verification/phase6_status_2026-05-10.md deleted file mode 100644 index 002a676..0000000 --- a/reports/verification/phase6_status_2026-05-10.md +++ /dev/null @@ -1,53 +0,0 @@ -# Phase 6 综合验收结果 - -日期：2026-05-10 -项目：`llm-intelligence` - -## 总结 - -- `Phase 1~5`: PASS -- `Phase 6`: PASS - -结论：当前仓库在现有 Phase 6 综合门禁定义下已通过验收。 - -## 本次新增/修复的验证能力 - -- 修复了 `verify_common.sh` 中 SQL 检查失败时直接异常退出的问题，改为明确输出 `FAIL` 证据。 -- 为 `scripts/` 下多个 Go 可执行入口补充了 build tag，恢复 `go test ./...` 的可用性。 -- 新增 `scripts/verify_phase6.sh`，将综合验收固化为可重复执行的门禁。 -- 将 `bash scripts/run_real_pipeline.sh` 纳入 Phase 6 综合门禁，要求真实 OpenRouter 采集、PostgreSQL 写库和今日日报生成全链路通过。 -- 为前端补充了共享模型归一化模块与 `vitest` 测试，不再是“有 test 命令但无测试文件”。 -- `Dashboard` 已改为基于真实模型数据/回退数据计算统计与厂商分布，不再写死示例数字。 - -## 本次执行的关键检查 - -- `bash scripts/verify_pre_phase6.sh` -- `go test ./...` -- `bash scripts/test.sh` -- `go build -o /dev/null ./cmd/server` -- `bash healthcheck.sh` -- `bash scripts/verify_phase6.sh` -- `bash scripts/run_real_pipeline.sh` -- `cd frontend && npm run test -- --run` -- `cd frontend && npm run build` - -## 关键结果 - -- `verify_pre_phase6.sh`: `PRE_PHASE6_RESULT: PASS` -- `verify_phase6.sh`: `PHASE_RESULT: PASS` -- `run_real_pipeline.sh`: PASS -- `2026-05-10 23:02` 真实采集 `367` 条，日报重新生成，当前 `models=377`、`report_runs=3` -- `go test ./...`: PASS -- `frontend vitest`: `3 passed` -- `API /health`: 200 -- `API /api/v1/models`: 200 -- `API latency`: `< 500ms` -- `最近 7 次采集成功率`: `100%` - -## 入口 - -- 总门禁：`bash scripts/verify_pre_phase6.sh` -- Phase 6 综合门禁：`bash scripts/verify_phase6.sh` -- Makefile： - - `make verify-pre-phase6` - - `make verify-phase6` diff --git a/reports/verification/pre_phase6_status_2026-05-10.md b/reports/verification/pre_phase6_status_2026-05-10.md deleted file mode 100644 index cc11dff..0000000 --- a/reports/verification/pre_phase6_status_2026-05-10.md +++ /dev/null @@ -1,92 +0,0 @@ -# Pre-Phase 6 验收结果 - -日期：2026-05-10 -项目：`llm-intelligence` - -## 总结 - -- `Phase 1`: PASS -- `Phase 2`: PASS -- `Phase 3`: PASS -- `Phase 4`: PASS -- `Phase 5`: PASS -- `Pre-Phase 6`: PASS - -结论：`Phase 1` 到 `Phase 5` 当前已全部通过验收，项目现在可以进入 `Phase 6`。 - -## 明细 - -### Phase 1 - -已通过： -- 核心三表与 Sprint 1 扩展迁移文件存在 -- `model_provider`、`operator`、`region_pricing`、`pricing_history`、`free_tier`、`daily_report`、`user_subscription`、`audit_log` 全部存在 -- `models` 扩展字段已落库 -- 关键 `CHECK` 约束已存在 -- `updated_at` 触发器已挂载 -- `model_provider` 种子数据和 `region_pricing` 初始数据已存在 -- `models.batch_id` 已完成回填 - -### Phase 2 - -已通过： -- `internal/collectors` 和 `internal/retry` 单测通过 -- `scripts/fetch_openrouter.go` 可独立构建 -- 国内厂商种子数、国内模型数、CNY 定价数、采集成功统计均已达到最低门槛 -- `2026-05-10 21:22` 的真实采集已跑通，OpenRouter API 实际拉取 `367` 条 -- 当前 `models` 总量已达到 `377` -- `audit_log` 中 `models` 审计记录已达到 `383` - -### Phase 3 - -已通过： -- `scripts/run_daily.sh`、`scripts/feishu_alert.sh` 可执行 -- 日报生成器可独立构建 -- 降级逻辑与飞书告警逻辑已接入 -- 今日日报、归档文件、`daily_report` 生成记录都已存在 -- `crontab` 已配置每日调度 -- 真实采集 `OPENROUTER_API_KEY` 已配置 -- 真实链路 `bash scripts/run_real_pipeline.sh` 已验证通过 -- 当前 `report_runs` 已达到 `2` - -### Phase 4 - -已通过： -- 前端构建入口与 TypeScript/Vite 配置存在 -- `npm run build` 可通过 -- `App` 已接入 `Dashboard` 与 `Explorer` -- `Explorer` 已具备分页、排序、筛选和本地 JSON 回退 -- `Dashboard` 已集成 `ECharts` -- `Explorer` 已实现 `stale` 状态显示 -- `Explorer` 已实现 `pricing unavailable` 显示 - -未通过： -- 无 - -### Phase 5 - -已通过： -- `Dockerfile`、`docker-compose.yml`、`nginx.conf`、`.env.example`、GitHub Actions CI 文件已存在 -- CI 中已包含 Go 测试、前端构建、Docker 构建 -- `scripts/backup.sh` 已可执行 -- `healthcheck.sh` 已落地，且本机验证通过 -- `scripts/restore.sh` 已落地 -- CI 已配置覆盖率门禁与构建产物上传 -- 日志轮转配置已落地 - -未通过： -- 无 - -## 本次关键证据 - -- 真实链路：`bash scripts/run_real_pipeline.sh` - - OpenRouter API 返回 `367` 条 - - PostgreSQL 写库完成 - - 今日日报与 HTML 已重新生成 -- 总门禁：`bash scripts/verify_pre_phase6.sh` - - 最新结果：`PRE_PHASE6_RESULT: PASS` - -## 入口 - -- 总门禁：`bash scripts/verify_pre_phase6.sh` -- Makefile：`make verify-pre-phase6` diff --git a/reports/verification/tencent_subscription_import_latest.txt b/reports/verification/tencent_subscription_import_latest.txt deleted file mode 100644 index f075098..0000000 --- a/reports/verification/tencent_subscription_import_latest.txt +++ /dev/null @@ -1 +0,0 @@ -source=tencent-subscription-import updated_at=2026-04-27 17:18:02 plans=8 provider=Tencent operator=Tencent Cloud table_rows=8 dry_run=false diff --git a/test.md b/test.md deleted file mode 100644 index 08cf610..0000000 --- a/test.md +++ /dev/null @@ -1 +0,0 @@ -test content \ No newline at end of file