8,429 prices on 4,154 listings · last collected 7 h ago · 36 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on six 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.
Model
Gemini 
Claude 
Qwen 
DeepSeek 
GLM 
Llama 
Mistral 
Kimi 
MiniMax 
Nemotron 
Hunyuan Unit
All 2,608Per second of output 5Per image 32Per million input tokens 866Per million output tokens 859Per million tokens 5Per million cached input tokens (read) 425Per million cache-write tokens 188Per thousand characters 2Per second of compute time 12Per run (default parameters) 200Other units (see the platform’s wording) 14
Showing 801–866 of 866
Per million input tokens66
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | Anthropic: Claude Sonnet 4.5Prompt > 200K | $6/M in | prompt: 0.000006 / token (>200000) | |
| Replicate | openai/gpt-4o-transcribe | $6/M in | $6 per million input tokens | |
| OpenRouter | Anthropic: Claude Opus 4.1 (batch) | $7.5/M in | prompt: 0.0000075 / token | |
| OpenRouter | OpenAI: GPT-5 Pro (batch) | $7.5/M in | prompt: 0.0000075 / token | |
| APIMart | claude-fable-5 | $8/M in | Input $8 / Output $40 · Per 1M tokens | |
| APIMart | claude-fable-5.1 | $8/M in | Input $8 / Output $40 · Per 1M tokens | |
| APIMart | gpt-4-0125-preview | $8/M in | Input $8 / Output $16 · Per 1M tokens | |
| APIMart | gpt-4-1106-preview | $8/M in | Input $8 / Output $16 · Per 1M tokens | |
| APIMart | gpt-6-astra | $8/M in | Input $8 / Output $40 · Per 1M tokens | |
| APIMart | o3-deep-research | $8/M in | Input $8 / Output $32 · Per 1M tokens | |
| APIMart | o3-deep-research-2025-06-26 | $8/M in | Input $8 / Output $32 · Per 1M tokens | |
| OpenRouter | OpenAI: GPT-5.6 SolPrompt > 272K | $8/M in | prompt: 0.000008 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Sol ProPrompt > 272K | $8/M in | prompt: 0.000008 / token (>272000) | |
| OpenRouter | Anthropic: Claude Fable 5 | $10/M in | prompt: 0.00001 / token | |
| OpenRouter | Anthropic: Claude Fable 5.1 | $10/M in | prompt: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-5.5Prompt > 272K | $10/M in | prompt: 0.00001 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra | $10/M in | prompt: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-6 Astra Pro | $10/M in | prompt: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-6 Astra Pro (batch)Prompt > 272K | $10/M in | prompt: 0.00001 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra (batch)Prompt > 272K | $10/M in | prompt: 0.00001 / token (>272000) | |
| OpenRouter | Sakana: Fugu UltraPrompt > 272K | $10/M in | prompt: 0.00001 / token (>272000) | |
| OpenRouter | Sakana: Fugu Ultra v2Prompt > 272K | $10/M in | prompt: 0.00001 / token (>272000) | |
| OpenRouter | Anthropic: Claude Fable Latest | $10/M in | prompt: 0.00001 / token | |
| OpenRouter | OpenAI: GPT Astra Latest | $10/M in | prompt: 0.00001 / token | |
| Replicate | anthropic/claude-fable-5 | $10/M in | $0.01 per thousand input tokens | |
| OpenRouter | OpenAI: GPT-5.2 Pro (batch) | $10.5/M in | prompt: 0.0000105 / token | |
| APIMart | gpt-5-pro | $12/M in | Input $12 / Output $96 · Per 1M tokens | |
| APIMart | gpt-5-pro-2025-10-06 | $12/M in | Input $12 / Output $96 · Per 1M tokens | |
| APIMart | o1 | $12/M in | Input $12 / Output $48 · Per 1M tokens | |
| APIMart | o1-2024-12-17 | $12/M in | Input $12 / Output $48 · Per 1M tokens | |
| APIMart | o1-preview | $12/M in | Input $12 / Output $48 · Per 1M tokens | |
| APIMart | o1-preview-2024-09-12 | $12/M in | Input $12 / Output $48 · Per 1M tokens | |
| OpenRouter | Anthropic: Claude Opus 4.1 | $15/M in | prompt: 0.000015 / token | |
| OpenRouter | OpenAI: GPT-5 Pro | $15/M in | prompt: 0.000015 / token | |
| OpenRouter | OpenAI: GPT-5.4 Pro (batch) | $15/M in | prompt: 0.000015 / token | |
| OpenRouter | OpenAI: GPT-5.5 Pro (batch) | $15/M in | prompt: 0.000015 / token | |
| Replicate | openai/gpt-5-pro | $15/M in | $0.015 per thousand input tokens | |
| APIMart | o3-pro | $16/M in | Input $16 / Output $64 · Per 1M tokens | |
| APIMart | o3-pro-2025-06-10 | $16/M in | Input $16 / Output $64 · Per 1M tokens | |
| APIMart | gpt-5.2-pro | $16.8/M in | Input $16.8 / Output $134.4 · Per 1M tokens | |
| OpenRouter | OpenAI: GPT-6 AstraPrompt > 272K | $20/M in | prompt: 0.00002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra ProPrompt > 272K | $20/M in | prompt: 0.00002 / token (>272000) | |
| OpenRouter | OpenAI: o3 Pro | $20/M in | prompt: 0.00002 / token | |
| OpenRouter | OpenAI: GPT Astra LatestPrompt > 272K | $20/M in | prompt: 0.00002 / token (>272000) | |
| Replicate | snowflake/snowflake-arctic-instruct | $20/M in | $0.02 per thousand input tokens | |
| OpenRouter | OpenAI: GPT-5.2 Pro | $21/M in | prompt: 0.000021 / token | |
| APIMart | gpt-5.4-pro | $24/M in | Input $24 / Output $144 · Per 1M tokens | |
| OpenRouter | OpenAI: GPT-4 | $30/M in | prompt: 0.00003 / token | |
| OpenRouter | OpenAI: GPT-5.4 Pro | $30/M in | prompt: 0.00003 / token | |
| OpenRouter | OpenAI: GPT-5.4 Pro (batch)Prompt > 272K | $30/M in | prompt: 0.00003 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.5 Pro | $30/M in | prompt: 0.00003 / token | |
| OpenRouter | OpenAI: GPT-5.5 Pro (batch)Prompt > 272K | $30/M in | prompt: 0.00003 / token (>272000) | |
| OpenRouter | OpenAI: GPT AudioAudio input | $32/M in | audio: 0.000032 / token | |
| APIMart | gpt-4.5-preview | $60/M in | Input $60 / Output $120 · Per 1M tokens | |
| APIMart | gpt-4.5-preview-2025-02-27 | $60/M in | Input $60 / Output $120 · Per 1M tokens | |
| OpenRouter | OpenAI: GPT-5.4 ProPrompt > 272K | $60/M in | prompt: 0.00006 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.5 ProPrompt > 272K | $60/M in | prompt: 0.00006 / token (>272000) | |
| Replicate | minimax/speech-02-turbo | $60/M in | $0.06 per thousand input tokens | |
| Replicate | minimax/speech-2.6-turbo | $60/M in | $0.06 per thousand input tokens | |
| Replicate | minimax/speech-2.8-turbo | $60/M in | $0.06 per thousand input tokens | |
| OpenRouter | Mistral: Voxtral Small 24B 2507Audio input | $100/M in | audio: 0.0001 / token | |
| Replicate | minimax/speech-02-hd | $100/M in | $0.10 per thousand input tokens | |
| Replicate | minimax/speech-2.6-hd | $100/M in | $0.10 per thousand input tokens | |
| Replicate | minimax/speech-2.8-hd | $100/M in | $0.10 per thousand input tokens | |
| APIMart | o1-pro | $120/M in | Input $120 / Output $480 · Per 1M tokens | |
| APIMart | o1-pro-2025-03-19 | $120/M in | Input $120 / Output $480 · Per 1M tokens |
