4,154 个模型 · 8,429 个价格 · 最近采集 8 小时前 · 30 天内 36 条需关注的调价
每个平台公布的每一个价格
采集器定时读取 6 个平台公开的全部价格（默认每天一次），并保存读到的原始页面。没有任何手工录入。搜索一个模型，就能看到现在按单位谁最便宜。
模型
Gemini 
Claude 
Qwen 
DeepSeek 
GLM 
Mistral 
Kimi 
Llama 
MiniMax 
Hunyuan 
Nemotron 第 2101–2200 条，共 2,608 条
每百万缓存读取 token92
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| OpenRouter | Qwen: Qwen3.8 Max (0902) | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token | |
| OpenRouter | Sakana: Fugu Max | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token | |
| OpenRouter | TheDrummer: Skyfall 36B V2 | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token | |
| OpenRouter | Pareto 26.9 | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token | |
| OpenRouter | Anthropic: Claude Fable Latest | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token | |
| OpenRouter | Z.ai: GLM 5.1 | $0.26/百万缓存读 | input_cache_read: 0.00000026 / token | |
| OpenRouter | OpenAI: o3 Mini (batch) | $0.275/百万缓存读 | input_cache_read: 0.000000275 / token | |
| kie.ai | gpt-6-astra | $0.28/百万缓存读 | 56 credits per million tokens ($0.28)平台声称 fal 价 $1/百万缓存读 | |
| OpenRouter | Meta: Llama 3.3 70B Instruct | $0.295/百万缓存读 | input_cache_read: 0.000000295 / token | |
| OpenRouter | Qwen: Qwen3.7 Max | $0.295/百万缓存读 | input_cache_read: 0.000000295 / token | |
| OpenRouter | Anthropic: Claude Sonnet 4.5 | $0.3/百万缓存读 | input_cache_read: 0.0000003 / token | |
| OpenRouter | Anthropic: Claude Sonnet 4.5 (batch)提示词超过 200K | $0.3/百万缓存读 | input_cache_read: 0.0000003 / token (>200000) | |
| OpenRouter | Anthropic: Claude Sonnet 4.6 | $0.3/百万缓存读 | input_cache_read: 0.0000003 / token | |
| OpenRouter | Fireworks: Ember-1 | $0.3/百万缓存读 | input_cache_read: 0.0000003 / token | |
| OpenRouter | Google: Gemini 3.5 Flash | $0.3/百万缓存读 | input_audio_cache: 0.0000003 / token | |
| OpenRouter | Qwen: Qwen3.5 397B A17B | $0.3/百万缓存读 | input_cache_read: 0.0000003 / token | |
| OpenRouter | SpaceXAI: Grok 4.5 | $0.3/百万缓存读 | input_cache_read: 0.0000003 / token | |
| OpenRouter | SpaceXAI: Grok 4.3 (batch)提示词超过 200K | $0.32/百万缓存读 | input_cache_read: 0.00000032 / token (>200000) | |
| OpenRouter | DeepSeek: R1 0528 | $0.35/百万缓存读 | input_cache_read: 0.00000035 / token | |
| OpenRouter | ReMM SLERP 13B | $0.35/百万缓存读 | input_cache_read: 0.00000035 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview提示词超过 200K | $0.4/百万缓存读 | input_audio_cache: 0.0000004 / token (>200000) | |
| OpenRouter | Google: Gemini 3.1 Pro Preview提示词超过 200K | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token (>200000) | |
| OpenRouter | Google: Gemini 3.1 Pro Preview Custom Tools提示词超过 200K | $0.4/百万缓存读 | input_audio_cache: 0.0000004 / token (>200000) | |
| OpenRouter | Google: Gemini 3.1 Pro Preview Custom Tools提示词超过 200K | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token (>200000) | |
| OpenRouter | Mancer: Weaver (alpha) | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol Pro | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol Pro (batch)提示词超过 272K | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Sol (batch)提示词超过 272K | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Terra提示词超过 272K | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Terra Pro提示词超过 272K | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Sol提示词超过 272K | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Sol Pro提示词超过 272K | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token (>272000) | |
| OpenRouter | Qwen: Qwen2.5 VL 72B Instruct | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token | |
| OpenRouter | SpaceXAI: Grok 4.20提示词超过 200K | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.20 Multi-Agent提示词超过 200K | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.3提示词超过 200K | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.6 (batch) | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token | |
| OpenRouter | SpaceXAI: Grok 4.7 (batch) | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token | |
| OpenRouter | SpaceXAI: Grok Build 0.1提示词超过 200K | $0.4/百万缓存读 | input_cache_read: 0.0000004 / token (>200000) | |
| OpenRouter | Anthropic: Claude Fable 5 (batch) | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Opus 4.5 | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Opus 4.6 | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Opus 4.7 | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Opus 4.8 | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Opus 5 | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT-4.1 | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT-5.4提示词超过 272K | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.5 | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT-5.5 (batch)提示词超过 272K | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra Pro (batch) | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT-6 Astra (batch) | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT Chat Latest | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | OpenAI: o3 | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | Qwen: Qwen3.8 Max Prime | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | Sakana: Fugu Ultra | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | Sakana: Fugu Ultra v2 | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | SpaceXAI: Grok 4.6 | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | SpaceXAI: Grok 4.7 | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | xAI: Grok Latest | $0.5/百万缓存读 | input_cache_read: 0.0000005 / token | |
| OpenRouter | Z.ai: GLM 5.3 Prime | $0.56/百万缓存读 | input_cache_read: 0.00000056 / token | |
| OpenRouter | Anthropic: Claude Sonnet 4.5提示词超过 200K | $0.6/百万缓存读 | input_cache_read: 0.0000006 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.5提示词超过 200K | $0.6/百万缓存读 | input_cache_read: 0.0000006 / token (>200000) | |
| OpenRouter | Amazon: Nova Premier 1.0 | $0.625/百万缓存读 | input_cache_read: 0.000000625 / token | |
| OpenRouter | OpenAI: GPT-4o (batch) | $0.625/百万缓存读 | input_cache_read: 0.000000625 / token | |
| OpenRouter | AionLabs: Aion-3.0 | $0.75/百万缓存读 | input_cache_read: 0.00000075 / token | |
| OpenRouter | AionLabs: Aion 3.5 | $0.75/百万缓存读 | input_cache_read: 0.00000075 / token | |
| OpenRouter | Anthropic: Claude Opus 4.1 (batch) | $0.75/百万缓存读 | input_cache_read: 0.00000075 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol提示词超过 272K | $0.8/百万缓存读 | input_cache_read: 0.0000008 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Sol Pro提示词超过 272K | $0.8/百万缓存读 | input_cache_read: 0.0000008 / token (>272000) | |
| OpenRouter | SpaceXAI: Grok 4.6 (batch)提示词超过 200K | $0.8/百万缓存读 | input_cache_read: 0.0000008 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.7 (batch)提示词超过 200K | $0.8/百万缓存读 | input_cache_read: 0.0000008 / token (>200000) | |
| OpenRouter | Anthropic: Claude Fable 5 | $1/百万缓存读 | input_cache_read: 0.000001 / token | |
| OpenRouter | OpenAI: GPT-5.5提示词超过 272K | $1/百万缓存读 | input_cache_read: 0.000001 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra | $1/百万缓存读 | input_cache_read: 0.000001 / token | |
| OpenRouter | OpenAI: GPT-6 Astra Pro | $1/百万缓存读 | input_cache_read: 0.000001 / token | |
| OpenRouter | OpenAI: GPT-6 Astra Pro (batch)提示词超过 272K | $1/百万缓存读 | input_cache_read: 0.000001 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra (batch)提示词超过 272K | $1/百万缓存读 | input_cache_read: 0.000001 / token (>272000) | |
| OpenRouter | Sakana: Fugu Ultra提示词超过 272K | $1/百万缓存读 | input_cache_read: 0.000001 / token (>272000) | |
| OpenRouter | Sakana: Fugu Ultra v2提示词超过 272K | $1/百万缓存读 | input_cache_read: 0.000001 / token (>272000) | |
| OpenRouter | SpaceXAI: Grok 4.6提示词超过 200K | $1/百万缓存读 | input_cache_read: 0.000001 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.7提示词超过 200K | $1/百万缓存读 | input_cache_read: 0.000001 / token (>200000) | |
| OpenRouter | OpenAI: GPT Astra Latest | $1/百万缓存读 | input_cache_read: 0.000001 / token | |
| OpenRouter | xAI: Grok Latest提示词超过 200K | $1/百万缓存读 | input_cache_read: 0.000001 / token (>200000) | |
| OpenRouter | OpenAI: GPT-4o | $1.25/百万缓存读 | input_cache_read: 0.00000125 / token | |
| OpenRouter | OpenAI: GPT-4o (2024-08-06) | $1.25/百万缓存读 | input_cache_read: 0.00000125 / token | |
| OpenRouter | OpenAI: GPT-4o (2024-11-20) | $1.25/百万缓存读 | input_cache_read: 0.00000125 / token | |
| OpenRouter | Anthropic: Claude Opus 4.1 | $1.5/百万缓存读 | input_cache_read: 0.0000015 / token | |
| OpenRouter | OpenAI: GPT-6 Astra提示词超过 272K | $2/百万缓存读 | input_cache_read: 0.000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra Pro提示词超过 272K | $2/百万缓存读 | input_cache_read: 0.000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT Astra Latest提示词超过 272K | $2/百万缓存读 | input_cache_read: 0.000002 / token (>272000) | |
| OpenRouter | Magnum v4 72B | $2.5/百万缓存读 | input_cache_read: 0.0000025 / token |
每百万缓存写入 token8
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| kie.ai | gpt-6-luna | $0.0375/百万缓存写最低 | 7.5 credits per million tokens ($0.0375)平台声称 fal 价 $0.125/百万缓存写 | |
| OpenRouter | Qwen: Qwen3.7 Flash缓存 5 分钟 | $0.038/百万缓存写 | input_cache_write: 0.000000038 / token | |
| OpenRouter | Google: Gemini 3.6 Flash缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.6 Flash (batch)缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.7 Flash缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.7 Flash (batch)缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.8 Flash缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.8 Flash (batch)缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token |