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 
Mistral 
Kimi 
Llama 
MiniMax 
Hunyuan 
Nemotron 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 1701–1800 of 2,608
Per million output tokens62
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | OpenAI: GPT-6 Astra (batch) | $25/M out | completion: 0.000025 / token | |
| Replicate | anthropic/claude-opus-4.6 | $25/M out | $0.025 per thousand output tokens | |
| Replicate | anthropic/claude-opus-4.7 | $25/M out | $0.025 per thousand output tokens | |
| OpenRouter | OpenAI: GPT-5.5 | $30/M out | completion: 0.00003 / token | |
| OpenRouter | OpenAI: GPT-5.6 SolPrompt > 272K | $30/M out | completion: 0.00003 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Sol ProPrompt > 272K | $30/M out | completion: 0.00003 / token (>272000) | |
| OpenRouter | OpenAI: GPT Chat Latest | $30/M out | completion: 0.00003 / token | |
| OpenRouter | Sakana: Fugu Ultra | $30/M out | completion: 0.00003 / token | |
| OpenRouter | Sakana: Fugu Ultra v2 | $30/M out | completion: 0.00003 / token | |
| APIMart | o3-deep-research | $32/M out | Input $8 / Output $32 · Per 1M tokens | |
| APIMart | o3-deep-research-2025-06-26 | $32/M out | Input $8 / Output $32 · Per 1M tokens | |
| OpenRouter | Anthropic: Claude Opus 4.1 (batch) | $37.5/M out | completion: 0.0000375 / token | |
| OpenRouter | OpenAI: GPT-6 Astra Pro (batch)Prompt > 272K | $37.5/M out | completion: 0.0000375 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra (batch)Prompt > 272K | $37.5/M out | completion: 0.0000375 / token (>272000) | |
| APIMart | claude-fable-5 | $40/M out | Input $8 / Output $40 · Per 1M tokens | |
| APIMart | claude-fable-5.1 | $40/M out | Input $8 / Output $40 · Per 1M tokens | |
| APIMart | gpt-6-astra | $40/M out | Input $8 / Output $40 · Per 1M tokens | |
| Replicate | google/gemini-3.1-flash-tts | $40/M out | $0.04 per thousand output tokens | |
| OpenRouter | OpenAI: GPT-5.5Prompt > 272K | $45/M out | completion: 0.000045 / token (>272000) | |
| OpenRouter | Sakana: Fugu UltraPrompt > 272K | $45/M out | completion: 0.000045 / token (>272000) | |
| OpenRouter | Sakana: Fugu Ultra v2Prompt > 272K | $45/M out | completion: 0.000045 / token (>272000) | |
| APIMart | o1 | $48/M out | Input $12 / Output $48 · Per 1M tokens | |
| APIMart | o1-2024-12-17 | $48/M out | Input $12 / Output $48 · Per 1M tokens | |
| APIMart | o1-preview | $48/M out | Input $12 / Output $48 · Per 1M tokens | |
| APIMart | o1-preview-2024-09-12 | $48/M out | Input $12 / Output $48 · Per 1M tokens | |
| OpenRouter | Anthropic: Claude Fable 5 | $50/M out | completion: 0.00005 / token | |
| OpenRouter | Anthropic: Claude Fable 5.1 | $50/M out | completion: 0.00005 / token | |
| OpenRouter | OpenAI: GPT-6 Astra | $50/M out | completion: 0.00005 / token | |
| OpenRouter | OpenAI: GPT-6 Astra Pro | $50/M out | completion: 0.00005 / token | |
| OpenRouter | Anthropic: Claude Fable Latest | $50/M out | completion: 0.00005 / token | |
| OpenRouter | OpenAI: GPT Astra Latest | $50/M out | completion: 0.00005 / token | |
| Replicate | anthropic/claude-fable-5 | $50/M out | $0.05 per thousand output tokens | |
| OpenRouter | OpenAI: GPT-4 | $60/M out | completion: 0.00006 / token | |
| OpenRouter | OpenAI: GPT-5 Pro (batch) | $60/M out | completion: 0.00006 / token | |
| APIMart | o3-pro | $64/M out | Input $16 / Output $64 · Per 1M tokens | |
| APIMart | o3-pro-2025-06-10 | $64/M out | Input $16 / Output $64 · Per 1M tokens | |
| OpenRouter | OpenAI: GPT Audio | $64/M out | audio_output: 0.000064 / token | |
| OpenRouter | Anthropic: Claude Opus 4.1 | $75/M out | completion: 0.000075 / token | |
| OpenRouter | OpenAI: GPT-6 AstraPrompt > 272K | $75/M out | completion: 0.000075 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra ProPrompt > 272K | $75/M out | completion: 0.000075 / token (>272000) | |
| OpenRouter | OpenAI: GPT Astra LatestPrompt > 272K | $75/M out | completion: 0.000075 / token (>272000) | |
| OpenRouter | OpenAI: o3 Pro | $80/M out | completion: 0.00008 / token | |
| OpenRouter | OpenAI: GPT-5.2 Pro (batch) | $84/M out | completion: 0.000084 / token | |
| OpenRouter | OpenAI: GPT-5.4 Pro (batch) | $90/M out | completion: 0.00009 / token | |
| OpenRouter | OpenAI: GPT-5.5 Pro (batch) | $90/M out | completion: 0.00009 / token | |
| APIMart | gpt-5-pro | $96/M out | Input $12 / Output $96 · Per 1M tokens | |
| APIMart | gpt-5-pro-2025-10-06 | $96/M out | Input $12 / Output $96 · Per 1M tokens | |
| APIMart | gpt-4.5-preview | $120/M out | Input $60 / Output $120 · Per 1M tokens | |
| APIMart | gpt-4.5-preview-2025-02-27 | $120/M out | Input $60 / Output $120 · Per 1M tokens | |
| OpenRouter | OpenAI: GPT-5 Pro | $120/M out | completion: 0.00012 / token | |
| Replicate | openai/gpt-5-pro | $120/M out | $0.12 per thousand output tokens | |
| APIMart | gpt-5.2-pro | $134.4/M out | Input $16.8 / Output $134.4 · Per 1M tokens | |
| OpenRouter | OpenAI: GPT-5.4 Pro (batch)Prompt > 272K | $135/M out | completion: 0.000135 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.5 Pro (batch)Prompt > 272K | $135/M out | completion: 0.000135 / token (>272000) | |
| APIMart | gpt-5.4-pro | $144/M out | Input $24 / Output $144 · Per 1M tokens | |
| OpenRouter | OpenAI: GPT-5.2 Pro | $168/M out | completion: 0.000168 / token | |
| OpenRouter | OpenAI: GPT-5.4 Pro | $180/M out | completion: 0.00018 / token | |
| OpenRouter | OpenAI: GPT-5.5 Pro | $180/M out | completion: 0.00018 / token | |
| OpenRouter | OpenAI: GPT-5.4 ProPrompt > 272K | $270/M out | completion: 0.00027 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.5 ProPrompt > 272K | $270/M out | completion: 0.00027 / token (>272000) | |
| APIMart | o1-pro | $480/M out | Input $120 / Output $480 · Per 1M tokens | |
| APIMart | o1-pro-2025-03-19 | $480/M out | Input $120 / Output $480 · Per 1M tokens |
Per million tokens5
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| fal | Bytedance Seed V2 Mini | $0.1/M tokCheapest | $0.0001 / 1000 tokens | |
| fal | NVIDIA Nemotron 3.5 Super Text | $10/M tok | $0.01 / 1000 tokens | |
| fal | Nemotron 3 Nano Omni | $10/M tok | $0.01 / 1000 tokens | |
| fal | Marlin | $15/M tok | $0.015 / 1000 tokens | |
| fal | Marlin Find | $15/M tok | $0.015 / 1000 tokens |
Per million cached input tokens (read)33
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | DeepSeek: DeepSeek V4.1 Flash 1017 (batch) | $0.002/M cache readCheapest | input_cache_read: 0.000000002 / token | |
| OpenRouter | DeepSeek: DeepSeek V4.1 Flash (batch) | $0.002/M cache readCheapest | input_cache_read: 0.000000002 / token | |
| OpenRouter | Meta: Muse Spark 1.2 Contributor | $0.002/M cache readCheapest | input_cache_read: 0.000000002 / token | |
| OpenRouter | Meta: Muse Spark 1.3 Contributor | $0.002/M cache readCheapest | input_cache_read: 0.000000002 / token | |
| kie.ai | DeepSeek V4.1 Flash | $0.0025/M cache read | 0.5 credits per million tokens ($0.0025) | |
| OpenRouter | Nex AGI: Nex-N2.5-Mini | $0.0025/M cache read | input_cache_read: 0.0000000025 / token | |
| OpenRouter | OpenAI: GPT-5 Nano (batch) | $0.0025/M cache read | input_cache_read: 0.0000000025 / token | |
| OpenRouter | Xiaomi: MiMo-V2.6-Flash | $0.0028/M cache read | input_cache_read: 0.0000000028 / token | |
| kie.ai | gpt-6-luna | $0.003/M cache read | 0.6 credits per million tokens ($0.003)Claims fal charges $0.01/M cache read | |
| OpenRouter | inclusionAI: Ling 3.0 Tiny | $0.003/M cache read | input_cache_read: 0.000000003 / token | |
| OpenRouter | Particle AI: Particle-1 | $0.003/M cache read | input_cache_read: 0.000000003 / token | |
| OpenRouter | Xiaomi: MiMo-V2.6-Pro | $0.0036/M cache read | input_cache_read: 0.0000000036 / token | |
| OpenRouter | inclusionAI: Ling 3.0 Flash | $0.0042/M cache read | input_cache_read: 0.0000000042 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch) | $0.005/M cache read | input_cache_read: 0.000000005 / token | |
| OpenRouter | DeepSeek: DeepSeek V4.1 Flash 1017 | $0.005/M cache read | input_cache_read: 0.000000005 / token | |
| OpenRouter | OpenAI: GPT-5 Nano | $0.005/M cache read | input_cache_read: 0.000000005 / token | |
| OpenRouter | OpenAI: GPT-6 Luna Pro (batch) | $0.005/M cache read | input_cache_read: 0.000000005 / token | |
| OpenRouter | OpenAI: GPT-6 Luna (batch) | $0.005/M cache read | input_cache_read: 0.000000005 / token | |
| OpenRouter | Upstage: Solar Mini 4 | $0.005/M cache read | input_cache_read: 0.000000005 / token | |
| OpenRouter | Z.ai: GLM 5.2 | $0.005/M cache read | input_cache_read: 0.000000005 / token | |
| OpenRouter | DeepSeek: DeepSeek Flash Latest | $0.005/M cache read | input_cache_read: 0.000000005 / token | |
| kie.ai | gpt-5.6-luna | $0.0056/M cache read | 1.12 credits per million tokens ($0.0056)Claims fal charges $0.02/M cache read | |
| OpenRouter | Meituan: LongCat 2.0 | $0.006/M cache read | input_cache_read: 0.000000006 / token | |
| OpenRouter | Qwen: Qwen3.7 Flash | $0.006/M cache read | input_cache_read: 0.000000006 / token | |
| OpenRouter | inclusionAI: Ling 3.1 Flash | $0.009/M cache read | input_cache_read: 0.000000009 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5 | $0.01/M cache read | input_cache_read: 0.00000001 / token | |
| OpenRouter | Google: Gemini 2.5 Flash Lite | $0.01/M cache read | input_cache_read: 0.00000001 / token | |
| OpenRouter | Mistral: Ministral 3 3B 2512 | $0.01/M cache read | input_cache_read: 0.00000001 / token | |
| OpenRouter | Mistral: Voxtral Small 24B 2507 | $0.01/M cache read | input_cache_read: 0.00000001 / token | |
| OpenRouter | OpenAI: GPT-5.4 Nano (batch) | $0.01/M cache read | input_cache_read: 0.00000001 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro (batch) | $0.01/M cache read | input_cache_read: 0.00000001 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna (batch) | $0.01/M cache read | input_cache_read: 0.00000001 / token | |
| OpenRouter | OpenAI: GPT-6 Luna | $0.01/M cache read | input_cache_read: 0.00000001 / token |
