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 1801–1900 条，共 2,608 条
每百万缓存读取 token100
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| OpenRouter | OpenAI: GPT-6 Luna Pro | $0.01/百万缓存读 | input_cache_read: 0.00000001 / token | |
| OpenRouter | OpenAI: GPT-6 Luna Pro (batch)提示词超过 272K | $0.01/百万缓存读 | input_cache_read: 0.00000001 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Luna (batch)提示词超过 272K | $0.01/百万缓存读 | input_cache_read: 0.00000001 / token (>272000) | |
| OpenRouter | Z.ai: GLM 5.3 Flash (batch) | $0.01/百万缓存读 | input_cache_read: 0.00000001 / token | |
| OpenRouter | Anthropic: Claude Haiku Latest | $0.01/百万缓存读 | input_cache_read: 0.00000001 / token | |
| OpenRouter | OpenAI: GPT Luna Latest | $0.01/百万缓存读 | input_cache_read: 0.00000001 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Flash 0731 (batch) | $0.012/百万缓存读 | input_cache_read: 0.000000012 / token | |
| OpenRouter | inclusionAI: Ling 3.0 Flash VL | $0.012/百万缓存读 | input_cache_read: 0.000000012 / token | |
| OpenRouter | NVIDIA: Nemotron 3 Nano 30B A3B | $0.012/百万缓存读 | input_cache_read: 0.000000012 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite (batch) | $0.0125/百万缓存读 | input_cache_read: 0.0000000125 / token | |
| OpenRouter | OpenAI: GPT-4.1 Nano (batch) | $0.0125/百万缓存读 | input_cache_read: 0.0000000125 / token | |
| OpenRouter | OpenAI: GPT-5 Mini (batch) | $0.0125/百万缓存读 | input_cache_read: 0.0000000125 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Flash Vision Exp | $0.014/百万缓存读 | input_cache_read: 0.000000014 / token | |
| kie.ai | gpt-6-1-terra | $0.015/百万缓存读 | 3 credits per million tokens ($0.015)平台声称 fal 价 $0.05/百万缓存读 | |
| OpenRouter | Google: Gemini 3.5 Flash Lite (batch) | $0.015/百万缓存读 | input_audio_cache: 0.000000015 / token | |
| OpenRouter | Google: Gemini 3.5 Flash Lite (batch) | $0.015/百万缓存读 | input_cache_read: 0.000000015 / token | |
| OpenRouter | IBM: Granite 4.2 8B | $0.015/百万缓存读 | input_cache_read: 0.000000015 / token | |
| OpenRouter | MiniMax: MiniMax M3.1 Flash | $0.015/百万缓存读 | input_cache_read: 0.000000015 / token | |
| OpenRouter | Mistral: Ministral 3 8B 2512 | $0.015/百万缓存读 | input_cache_read: 0.000000015 / token | |
| OpenRouter | Mistral: Mistral Small 4 | $0.015/百万缓存读 | input_cache_read: 0.000000015 / token | |
| OpenRouter | Nex AGI: Nex-N2.5-Pro | $0.015/百万缓存读 | input_cache_read: 0.000000015 / token | |
| OpenRouter | Qwen: Qwen3.8 Flash | $0.016/百万缓存读 | input_cache_read: 0.000000016 / token | |
| OpenRouter | Qwen: Qwen3.8 Omni Flash | $0.016/百万缓存读 | input_cache_read: 0.000000016 / token | |
| OpenRouter | DeepSeek: DeepSeek V4.1 Flash | $0.018/百万缓存读 | input_cache_read: 0.000000018 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Flash 0423 | $0.0182/百万缓存读 | input_cache_read: 0.0000000182 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Pro 0423 | $0.0192705/百万缓存读 | input_cache_read: 0.0000000192705 / token | |
| OpenRouter | LiquidAI: LFM3-1.7B | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token | |
| OpenRouter | Mistral: Ministral 3 14B 2512 | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token | |
| OpenRouter | Mistral: Saba | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token | |
| OpenRouter | NVIDIA: Nemotron 3.5 Super VL | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token | |
| OpenRouter | OpenAI: GPT-5.4 Nano | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro (batch)提示词超过 272K | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Luna (batch)提示词超过 272K | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Luna提示词超过 272K | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Luna Pro提示词超过 272K | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token (>272000) | |
| OpenRouter | Qwen: Qwen3.7 Flash提示词超过 32K | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token (>32000) | |
| OpenRouter | OpenAI: GPT Luna Latest提示词超过 272K | $0.02/百万缓存读 | input_cache_read: 0.00000002 / token (>272000) | |
| OpenRouter | Tencent: Hy4 | $0.021/百万缓存读 | input_cache_read: 0.000000021 / token | |
| OpenRouter | OpenAI: gpt-oss-120b | $0.023/百万缓存读 | input_cache_read: 0.000000023 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch)提示词超过 100K | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token (>100000) | |
| OpenRouter | Google: Gemini 3.1 Flash Lite | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite Preview | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite (batch) | $0.025/百万缓存读 | input_audio_cache: 0.000000025 / token | |
| OpenRouter | LiquidAI: LFM2.5-24B-A2B | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token | |
| OpenRouter | Meta: Llama 3.1 8B Instruct | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token | |
| OpenRouter | OpenAI: GPT-5 Mini | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token | |
| OpenRouter | OpenAI: GPT-6.1 Terra Pro (batch) | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token | |
| OpenRouter | OpenAI: GPT-6.1 Terra (batch) | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token | |
| OpenRouter | Qwen: Qwen3.6 35B A3B | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token | |
| OpenRouter | Z.ai: GLM 4.5 Air | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token | |
| kie.ai | gpt-6-1-sol | $0.03/百万缓存读 | 6 credits per million tokens ($0.03)平台声称 fal 价 $0.1/百万缓存读 | |
| OpenRouter | Google: Gemini 2.5 Flash | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter | Google: Gemini 2.5 Flash Lite | $0.03/百万缓存读 | input_audio_cache: 0.00000003 / token | |
| OpenRouter | Google: Gemini 3.5 Flash Lite | $0.03/百万缓存读 | input_audio_cache: 0.00000003 / token | |
| OpenRouter | Google: Gemini 3.5 Flash Lite | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter | Inference.net: Schematron V2 Turbo | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter | Mistral: Codestral 2508 | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter | OpenAI: GPT-4.1 Nano | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter | OpenAI: GPT-5.1-Codex-Mini | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter | OpenAI: gpt-oss-20b | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter | Pareto 26.10 | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter | Upstage: Solar Pro 4 | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter | Z.ai: GLM 5.3 Flash | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter | Pareto Latest | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter | Z.ai: GLM Flash Latest | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter | Meta: Muse Glimmer 30B (batch) | $0.032/百万缓存读 | input_cache_read: 0.000000032 / token | |
| OpenRouter | Tencent: Hy3 | $0.033/百万缓存读 | input_cache_read: 0.000000033 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Flash 0731 | $0.035/百万缓存读 | input_cache_read: 0.000000035 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Flash Latest | $0.035/百万缓存读 | input_cache_read: 0.000000035 / token | |
| OpenRouter | Xiaomi: MiMo-V2.6-Pro-UltraSpeed | $0.036/百万缓存读 | input_cache_read: 0.000000036 / token | |
| OpenRouter | Google: Gemini 3.6 Flash (batch) | $0.0375/百万缓存读 | input_audio_cache: 0.0000000375 / token | |
| OpenRouter | Google: Gemini 3.6 Flash (batch) | $0.0375/百万缓存读 | input_cache_read: 0.0000000375 / token | |
| OpenRouter | Google: Gemini 3.7 Flash (batch) | $0.0375/百万缓存读 | input_audio_cache: 0.0000000375 / token | |
| OpenRouter | Google: Gemini 3.7 Flash (batch) | $0.0375/百万缓存读 | input_cache_read: 0.0000000375 / token | |
| OpenRouter | Google: Gemini 3.8 Flash (batch) | $0.0375/百万缓存读 | input_audio_cache: 0.0000000375 / token | |
| OpenRouter | Google: Gemini 3.8 Flash (batch) | $0.0375/百万缓存读 | input_cache_read: 0.0000000375 / token | |
| OpenRouter | Google: Gemma 4 26B A4B | $0.0375/百万缓存读 | input_cache_read: 0.0000000375 / token | |
| OpenRouter | OpenAI: GPT-4o-mini (batch) | $0.0375/百万缓存读 | input_cache_read: 0.0000000375 / token | |
| OpenRouter | OpenAI: GPT-5.4 Mini (batch) | $0.0375/百万缓存读 | input_cache_read: 0.0000000375 / token | |
| OpenRouter | OpenAI: gpt-oss-safeguard-20b | $0.0375/百万缓存读 | input_cache_read: 0.0000000375 / token | |
| OpenRouter | PrismML: Ternary Bonsai 2 27B | $0.0375/百万缓存读 | input_cache_read: 0.0000000375 / token | |
| OpenRouter | Qwen: Qwen3.8 27B | $0.0375/百万缓存读 | input_cache_read: 0.0000000375 / token | |
| OpenRouter | Qwen: Qwen3 Coder Flash | $0.039/百万缓存读 | input_cache_read: 0.000000039 / token | |
| OpenRouter | Google: Gemma 3 27B | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token | |
| OpenRouter | LiquidAI: LFM2.5-2.6B | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token | |
| OpenRouter | Meta: Muse Glimmer 30B | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token | |
| OpenRouter | Mistral: Devstral 2 2512 | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token | |
| OpenRouter | Mistral: Mistral Medium 3 | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token | |
| OpenRouter | Mistral: Mistral Medium 3.1 | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token | |
| OpenRouter | NVIDIA: Nemotron 3.5 Lightning | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna提示词超过 272K | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro提示词超过 272K | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (>272000) | |
| OpenRouter | PrismML: Ternary Bonsai 2 9B | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token | |
| OpenRouter | Qwen: Qwen3.7 Flash提示词超过 256K | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (>256000) | |
| OpenRouter | Qwen: Qwen3.8 27B (batch) | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token | |
| OpenRouter | Reflection: Beam 1.0 501B A23B | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token | |
| OpenRouter | StepFun: Step 3.7 Flash | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token | |
| OpenRouter | MiniMax: MiniMax M2.7 | $0.042/百万缓存读 | input_cache_read: 0.000000042 / token |
