11,853 prices on 5,033 listings · last collected 15 min ago · 442 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on eleven platforms, daily by default, and keeps the page it read. Nothing is typed in by hand. Search a model to see who charges least, per unit, right now.
Platform
Model
Claude 
Gemini 
Qwen 
DeepSeek 
GLM 
Kimi 
Mistral 
Llama 
MiniMax 
Nemotron 
Hunyuan Showing 2801–2900 of 3,239
Per million cache-write tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| KIENot disclosed | gpt-6-luna | $0.038/M cache writeCheapest | 7.5 credits per million tokens ($0.0375)Claims official or Fal price $0.125/M cache write | |
| OpenRouterOfficial | Qwen: Qwen3.7 Flash5-min cachevia Alibaba | $0.038/M cache write | input_cache_write: 0.000000038 / token (endpoint alibaba) | |
| OpenRouterOfficial | Google: Gemini 3.6 Flash5-min cachevia Google AI Studio | $0.042/M cache write | input_cache_write: 0.0000000416666666666667 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.6 Flash (batch)5-min cache | $0.042/M cache write | input_cache_write: 0.0000000416666666666667 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.7 Flash5-min cachevia Google AI Studio | $0.042/M cache write | input_cache_write: 0.0000000416666666666667 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.7 Flash (batch)5-min cache | $0.042/M cache write | input_cache_write: 0.0000000416666666666667 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.8 Flash5-min cachevia Google AI Studio | $0.042/M cache write | input_cache_write: 0.0000000416666666666667 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.8 Flash (batch)5-min cache | $0.042/M cache write | input_cache_write: 0.0000000416666666666667 / token (endpoint google-vertex/global) | |
| OpenRouterNot disclosed | Google: Gemini Flash Latest5-min cache | $0.042/M cache write | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouterOfficial | Anthropic: Claude Haiku 5.5 (batch)5-min cache | $0.063/M cache write | input_cache_write: 0.0000000625 / token (endpoint anthropic) | |
| OpenRouterOfficial | OpenAI: GPT-6 Luna Pro (batch)5-min cache | $0.063/M cache write | input_cache_write: 0.0000000625 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6 Luna (batch)5-min cache | $0.063/M cache write | input_cache_write: 0.0000000625 / token (endpoint openai) | |
| KIENot disclosed | gpt-5.6-luna | $0.07/M cache write | 14 credits per million tokens ($0.07)Claims official or Fal price $0.25/M cache write | |
| OpenRouterOfficial | Google: Gemini 2.5 Flash5-min cachevia Google AI Studio | $0.083/M cache write | input_cache_write: 0.0000000833333333333333 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 2.5 Flash Lite5-min cachevia Google AI Studio | $0.083/M cache write | input_cache_write: 0.0000000833333333333333 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3 Flash Preview5-min cachevia Google AI Studio | $0.083/M cache write | input_cache_write: 0.0000000833333333333333 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.1 Flash Lite5-min cachevia Google AI Studio | $0.083/M cache write | input_cache_write: 0.0000000833333333333333 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.1 Flash Lite Preview5-min cachevia Google AI Studio | $0.083/M cache write | input_cache_write: 0.0000000833333333333333 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.5 Flash5-min cachevia Google · global | $0.083/M cache write | input_cache_write: 0.0000000833333333333333 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.5 Flash Lite5-min cachevia Google AI Studio | $0.083/M cache write | input_cache_write: 0.0000000833333333333333 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Anthropic: Claude Haiku 5.5 (batch)1-h cache | $0.1/M cache write | input_cache_write_1h: 0.0000001 / token (endpoint anthropic) | |
| OpenRouterOfficial partner | Anthropic: Claude Haiku 5.55-min cachevia Google · global | $0.125/M cache write | input_cache_write: 0.000000125 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-6 Luna5-min cachevia Amazon Bedrock · global | $0.125/M cache write | input_cache_write: 0.000000125 / token (endpoint amazon-bedrock/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-6 Luna Pro5-min cachevia OpenAI | $0.125/M cache write | input_cache_write: 0.000000125 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6 Luna Pro (batch)5-min cachePrompt > 272K | $0.125/M cache write | input_cache_write: 0.000000125 / token (>272000; endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6 Luna (batch)5-min cachePrompt > 272K | $0.125/M cache write | input_cache_write: 0.000000125 / token (>272000; endpoint openai) | |
| OpenRouterOfficial | Qwen: Qwen3.7 Flash5-min cachePrompt > 32Kvia Alibaba | $0.125/M cache write | input_cache_write: 0.000000125 / token (>32000; endpoint alibaba) | |
| OpenRouterNot disclosed | Anthropic: Claude Haiku Latest5-min cache | $0.125/M cache write | input_cache_write: 0.000000125 / token | |
| OpenRouterNot disclosed | OpenAI: GPT Luna Latest5-min cache | $0.125/M cache write | input_cache_write: 0.000000125 / token | |
| RunwareNot disclosed | Claude Haiku 5.5≤ 100K context | $0.125/M cache write | $1.25e-7 / cacheWriteToken · ≤ 100K context | |
| RunwareNot disclosed | GPT-6 Luna≤ 272K context | $0.125/M cache write | $1.25e-7 / cacheWriteToken · ≤ 272K context | |
| AibermNot disclosed | Claude Haiku 4.5 20251001 | $0.144/M cache write | model_ratio 0.25 × $2/M · group default ×0.23 · cache_creation_ratio 1.25 | |
| OpenRouterOfficial | Google: Gemini 4 Argon5-min cache | $0.188/M cache write | input_cache_write: 0.0000001875 / token | |
| OpenRouterOfficial | Google: Gemini 4 Argon (batch)5-min cache | $0.188/M cache write | input_cache_write: 0.0000001875 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 4 Carbon5-min cachevia Google AI Studio | $0.188/M cache write | input_cache_write: 0.0000001875 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 4 Carbon (batch)5-min cache | $0.188/M cache write | input_cache_write: 0.0000001875 / token (endpoint google-vertex/global) | |
| OpenRouterNot disclosed | Google: Gemini Pro Latest5-min cache | $0.188/M cache write | input_cache_write: 0.0000001875 / token | |
| OpenRouterOfficial partner | Anthropic: Claude Haiku 5.51-h cachevia Google · global | $0.2/M cache write | input_cache_write_1h: 0.0000002 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Qwen: Qwen3.8 Flash5-min cachevia Alibaba | $0.2/M cache write | input_cache_write: 0.0000002 / token (endpoint alibaba) | |
| OpenRouterNot disclosed | Anthropic: Claude Haiku Latest1-h cache | $0.2/M cache write | input_cache_write_1h: 0.0000002 / token | |
| OpenRouterOfficial | Qwen: Qwen3.6 Flash5-min cache | $0.234/M cache write | input_cache_write: 0.000000234375 / token | |
| OpenRouterOfficial | Qwen: Qwen3 Coder Flash5-min cache | $0.244/M cache write | input_cache_write: 0.00000024375 / token (endpoint alibaba) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.6 Luna5-min cachevia Amazon Bedrock · global | $0.25/M cache write | input_cache_write: 0.00000025 / token (endpoint amazon-bedrock/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.6 Luna Pro5-min cachevia Azure | $0.25/M cache write | input_cache_write: 0.00000025 / token (endpoint azure) | |
| OpenRouterOfficial partner | OpenAI: GPT-6 Luna5-min cachePrompt > 272Kvia Amazon Bedrock · global | $0.25/M cache write | input_cache_write: 0.00000025 / token (>272000; endpoint amazon-bedrock/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-6 Luna Pro5-min cachePrompt > 272Kvia OpenAI | $0.25/M cache write | input_cache_write: 0.00000025 / token (>272000; endpoint openai) | |
| OpenRouterOfficial | Qwen: Qwen3.7 Flash5-min cachePrompt > 256Kvia Alibaba | $0.25/M cache write | input_cache_write: 0.00000025 / token (>256000; endpoint alibaba) | |
| OpenRouterNot disclosed | OpenAI: GPT Luna Latest5-min cachePrompt > 272K | $0.25/M cache write | input_cache_write: 0.00000025 / token (>272000) | |
| RunwareNot disclosed | GPT-6 Luna> 272K context | $0.25/M cache write | $2.5e-7 / cacheWriteToken · > 272K context | |
| OpenRouterOfficial | Anthropic: Claude Haiku 5.5 (batch)5-min cachePrompt > 100K | $0.313/M cache write | input_cache_write: 0.0000003125 / token (>100000; endpoint anthropic) | |
| OpenRouterOfficial | Qwen: Qwen-Plus5-min cache | $0.325/M cache write | input_cache_write: 0.000000325 / token (endpoint alibaba) | |
| KIENot disclosed | gpt-6-1-terra | $0.375/M cache write | 75 credits per million tokens ($0.375)Claims official or Fal price $1.25/M cache write | |
| OpenRouterOfficial | Google: Gemini 2.5 Pro5-min cachevia Google AI Studio | $0.375/M cache write | input_cache_write: 0.000000375 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 2.5 Pro Preview 06-055-min cachevia Google AI Studio | $0.375/M cache write | input_cache_write: 0.000000375 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.1 Pro Preview5-min cachevia Google · global | $0.375/M cache write | input_cache_write: 0.000000375 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.1 Pro Preview Custom Tools5-min cache | $0.375/M cache write | input_cache_write: 0.000000375 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Qwen: Qwen3.5 Plus 2026-04-205-min cache | $0.375/M cache write | input_cache_write: 0.000000375 / token (endpoint alibaba) | |
| OpenRouterOfficial | Qwen: Qwen3.7 Plus5-min cachevia Alibaba | $0.4/M cache write | input_cache_write: 0.0000004 / token (endpoint alibaba) | |
| OpenRouterOfficial | Qwen: Qwen3 Coder Flash5-min cachePrompt > 32K | $0.406/M cache write | input_cache_write: 0.00000040625 / token (>32000; endpoint alibaba) | |
| OpenRouterOfficial | Qwen: Qwen3.6 Plus5-min cache | $0.406/M cache write | input_cache_write: 0.00000040625 / token (endpoint alibaba) | |
| OpenRouterOfficial | Qwen: Qwen3.5 Plus 2026-04-205-min cachePrompt > 256K | $0.469/M cache write | input_cache_write: 0.00000046875 / token (>256000; endpoint alibaba) | |
| OpenRouterOfficial | Anthropic: Claude Haiku 5.5 (batch)1-h cachePrompt > 100K | $0.5/M cache write | input_cache_write_1h: 0.0000005 / token (>100000; endpoint anthropic) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.6 Luna5-min cachePrompt > 272Kvia Amazon Bedrock · global | $0.5/M cache write | input_cache_write: 0.0000005 / token (>272000; endpoint amazon-bedrock/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.6 Luna Pro5-min cachePrompt > 272Kvia Azure | $0.5/M cache write | input_cache_write: 0.0000005 / token (>272000; endpoint azure) | |
| AibermNot disclosed | Claude Sonnet 4.5 20250929 | $0.562/M cache write | model_ratio 0.9775 × $2/M · group default ×0.23 · cache_creation_ratio 1.25 | |
| AibermNot disclosed | Claude Sonnet 4.5 20250929 Thinking | $0.562/M cache write | model_ratio 0.9775 × $2/M · group default ×0.23 · cache_creation_ratio 1.25 | |
| OpenRouterOfficial | Anthropic: Claude Haiku 4.5 (batch)5-min cache | $0.625/M cache write | input_cache_write: 0.000000625 / token (endpoint anthropic) | |
| OpenRouterOfficial partner | Anthropic: Claude Haiku 5.55-min cachePrompt > 100Kvia Google · global | $0.625/M cache write | input_cache_write: 0.000000625 / token (>100000; endpoint google-vertex/global) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Terra Pro (batch)5-min cache | $0.625/M cache write | input_cache_write: 0.000000625 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Terra (batch)5-min cache | $0.625/M cache write | input_cache_write: 0.000000625 / token (endpoint openai) | |
| OpenRouterNot disclosed | Anthropic: Claude Haiku Latest5-min cachePrompt > 100K | $0.625/M cache write | input_cache_write: 0.000000625 / token (>100000) | |
| RunwareNot disclosed | Claude Haiku 5.5> 100K context | $0.625/M cache write | $6.25e-7 / cacheWriteToken · > 100K context | |
| OpenRouterOfficial | Qwen: Qwen3 Coder Flash5-min cachePrompt > 128K | $0.65/M cache write | input_cache_write: 0.00000065 / token (>128000; endpoint alibaba) | |
| KIENot disclosed | gpt-5.6-terra | $0.7/M cache write | 140 credits per million tokens ($0.70)Claims official or Fal price $2.5/M cache write | |
| KIENot disclosed | gpt-6-1-sol | $0.75/M cache write | 150 credits per million tokens ($0.75)Claims official or Fal price $2.5/M cache write | |
| KIENot disclosed | gpt-6-sol | $0.75/M cache write | 150 credits per million tokens ($0.75)Claims official or Fal price $2.5/M cache write | |
| AibermNot disclosed | Claude Opus 4.5 20251101 | $0.937/M cache write | model_ratio 1.629 × $2/M · group default ×0.23 · cache_creation_ratio 1.25 | |
| AibermNot disclosed | Claude Opus 4.5 20251101 Thinking | $0.937/M cache write | model_ratio 1.629 × $2/M · group default ×0.23 · cache_creation_ratio 1.25 | |
| OpenRouterOfficial | Qwen: Qwen3.6 Flash5-min cachePrompt > 256K | $0.938/M cache write | input_cache_write: 0.0000009375 / token (>256000) | |
| OpenRouterOfficial | Qwen: Qwen-Plus5-min cachePrompt > 256K | $0.975/M cache write | input_cache_write: 0.000000975 / token (>256000; endpoint alibaba) | |
| OpenRouterOfficial | Anthropic: Claude Haiku 4.5 (batch)1-h cache | $1/M cache write | input_cache_write_1h: 0.000001 / token (endpoint anthropic) | |
| OpenRouterOfficial partner | Anthropic: Claude Haiku 5.51-h cachePrompt > 100Kvia Google · global | $1/M cache write | input_cache_write_1h: 0.000001 / token (>100000; endpoint google-vertex/global) | |
| OpenRouterNot disclosed | Anthropic: Claude Haiku Latest1-h cachePrompt > 100K | $1/M cache write | input_cache_write_1h: 0.000001 / token (>100000) | |
| OpenRouterOfficial | Qwen: Qwen3.7 Plus5-min cachePrompt > 256Kvia Alibaba | $1.2/M cache write | input_cache_write: 0.0000012 / token (>256000; endpoint alibaba) | |
| OpenRouterOfficial partner | Anthropic: Claude Haiku 4.55-min cachevia Azure · global | $1.25/M cache write | input_cache_write: 0.00000125 / token (endpoint azure/global) | |
| OpenRouterOfficial | Anthropic: Claude Sonnet 5.5 (batch)5-min cache | $1.25/M cache write | input_cache_write: 0.00000125 / token (endpoint anthropic) | |
| OpenRouterOfficial | Anthropic: Claude Sonnet 5 (batch)5-min cache | $1.25/M cache write | input_cache_write: 0.00000125 / token (endpoint anthropic) | |
| OpenRouterOfficial | OpenAI: GPT-6 Sol Pro (batch)5-min cache | $1.25/M cache write | input_cache_write: 0.00000125 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6 Sol (batch)5-min cache | $1.25/M cache write | input_cache_write: 0.00000125 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Sol Pro (batch)5-min cache | $1.25/M cache write | input_cache_write: 0.00000125 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Sol (batch)5-min cache | $1.25/M cache write | input_cache_write: 0.00000125 / token (endpoint openai) | |
| OpenRouterOfficial partner | OpenAI: GPT-6.1 Terra5-min cachevia Azure | $1.25/M cache write | input_cache_write: 0.00000125 / token (endpoint azure) | |
| OpenRouterOfficial partner | OpenAI: GPT-6.1 Terra Pro5-min cachevia Azure | $1.25/M cache write | input_cache_write: 0.00000125 / token (endpoint azure) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Terra Pro (batch)5-min cachePrompt > 272K | $1.25/M cache write | input_cache_write: 0.00000125 / token (>272000; endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Terra (batch)5-min cachePrompt > 272K | $1.25/M cache write | input_cache_write: 0.00000125 / token (>272000; endpoint openai) | |
| OpenRouterNot disclosed | OpenAI: GPT Terra Latest5-min cache | $1.25/M cache write | input_cache_write: 0.00000125 / token | |
| RunwareNot disclosed | Claude Haiku 4.5Per 1M | $1.25/M cache write | $0.00000125 / cacheWriteToken | |
| RunwareNot disclosed | GPT-6.1 Terra≤ 272K context | $1.25/M cache write | $0.00000125 / cacheWriteToken · ≤ 272K context | |
| OpenRouterOfficial | Qwen: Qwen3.6 Plus5-min cachePrompt > 256K | $1.625/M cache write | input_cache_write: 0.000001625 / token (>256000; endpoint alibaba) | |
| KIENot disclosed | gpt-5.6-sol | $1.75/M cache write | 350 credits per million tokens ($1.75)Claims official or Fal price $6.25/M cache write |