8,429 prices on 4,154 listings · last collected 4 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.
Unit
All 8,429Per second of output 1,919Per minute 34Per video 486Per image 1,521Per megapixel 308Per million input tokens 982Per million output tokens 977Per million tokens 48Per million cached input tokens (read) 458Per million cache-write tokens 191Per thousand characters 64Per second of compute time 93Per run (default parameters) 1,023Other units (see the platform’s wording) 325
Showing 101–200 of 977
Per million output tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| Replicate | ibm-granite/granite-speech-4.1-2b | $0.25/M out | $0.25 per million output tokens | |
| Replicate | ibm-granite/granite-vision-3.3-2b | $0.25/M out | $0.25 per million output tokens | |
| Replicate | ibm-granite/granite-vision-4.1-4b | $0.25/M out | $0.25 per million output tokens | |
| Replicate | meta/llama-2-7b | $0.25/M out | $0.25 per million output tokens | |
| Replicate | meta/llama-2-7b-chat | $0.25/M out | $0.25 per million output tokens | |
| Replicate | meta/meta-llama-3-8b | $0.25/M out | $0.25 per million output tokens | |
| Replicate | meta/meta-llama-3-8b-instruct | $0.25/M out | $0.25 per million output tokens | |
| Replicate | mistralai/mistral-7b-v0.1 | $0.25/M out | $0.25 per million output tokens | |
| OpenRouter | Qwen: Qwen3.5-Flash | $0.26/M out | completion: 0.00000026 / token | |
| OpenRouter | Qwen: Qwen3 32B | $0.28/M out | completion: 0.00000028 / token | |
| OpenRouter | Xiaomi: MiMo-V2.6-Flash | $0.28/M out | completion: 0.00000028 / token | |
| OpenRouter | Tencent: Hy-MT2-30B-A3B | $0.295/M out | completion: 0.000000295 / token | |
| OpenRouter | Tencent: Hy-MT2-7B | $0.295/M out | completion: 0.000000295 / token | |
| kie.ai | claude-haiku-5-5 | $0.3/M out | 60 credits per million tokens ($0.30)Claims fal charges $0.5/M out | |
| OpenRouter | ByteDance Seed: Seed 1.6 Flash | $0.3/M out | completion: 0.0000003 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Flash 0731 | $0.3/M out | completion: 0.0000003 / token | |
| OpenRouter | Meta: Llama 4 Scout | $0.3/M out | completion: 0.0000003 / token | |
| OpenRouter | Mistral: Voxtral Small 24B 2507 | $0.3/M out | completion: 0.0000003 / token | |
| OpenRouter | OpenAI: GPT-4o-mini (batch) | $0.3/M out | completion: 0.0000003 / token | |
| OpenRouter | OpenAI: gpt-oss-safeguard-20b | $0.3/M out | completion: 0.0000003 / token | |
| OpenRouter | Qwen: Qwen3 30B A3B Instruct 2507 | $0.3/M out | completion: 0.0000003 / token | |
| OpenRouter | StepFun: Step 3.5 Flash | $0.3/M out | completion: 0.0000003 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Flash Latest | $0.3/M out | completion: 0.0000003 / token | |
| APIMart | deepseek-v3.2 | $0.3084/M out | Input $0.2056 / Output $0.3084 · Per 1M tokens | |
| APIMart | deepseek-v3.2-exp | $0.3084/M out | Input $0.2056 / Output $0.3084 · Per 1M tokens | |
| APIMart | qwen3.8-flash | $0.3086/M out | Input $0.0914 / Output $0.3086 · Per 1M tokens | |
| APIMart | babbage-002 | $0.32/M out | Input $0.32 / Output $0.32 · Per 1M tokens | |
| APIMart | gpt-4.1-nano | $0.32/M out | Input $0.08 / Output $0.32 · Per 1M tokens | |
| APIMart | gpt-4.1-nano-2025-04-14 | $0.32/M out | Input $0.08 / Output $0.32 · Per 1M tokens | |
| APIMart | gpt-5-nano | $0.32/M out | Input $0.04 / Output $0.32 · Per 1M tokens | |
| APIMart | gpt-5-nano-2025-08-07 | $0.32/M out | Input $0.04 / Output $0.32 · Per 1M tokens | |
| OpenRouter | Meta: Llama 3.2 3B Instruct | $0.33/M out | completion: 0.00000033 / token | |
| kie.ai | gpt-5.6-luna | $0.336/M out | 67.2 credits per million tokens ($0.336)Claims fal charges $1.2/M out | |
| OpenRouter | Google: Gemma 3 27B | $0.35/M out | completion: 0.00000035 / token | |
| Replicate | openai/gpt-oss-20b | $0.36/M out | $0.36 per million output tokens | |
| OpenRouter | OpenAI: GPT-6 Luna Pro (batch)Prompt > 272K | $0.375/M out | completion: 0.000000375 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Luna (batch)Prompt > 272K | $0.375/M out | completion: 0.000000375 / token (>272000) | |
| OpenRouter | DeepSeek: DeepSeek V3.2 | $0.38/M out | completion: 0.00000038 / token | |
| APIMart | claude-haiku-5-5 | $0.4/M out | Input $0.08 / Output $0.4 · Per 1M tokens | |
| APIMart | gpt-6-luna | $0.4/M out | Input $0.08 / Output $0.4 · Per 1M tokens | |
| OpenRouter | ByteDance Seed: Seed-2.0-Mini | $0.4/M out | completion: 0.0000004 / token | |
| OpenRouter | Google: Gemini 2.5 Flash Lite | $0.4/M out | completion: 0.0000004 / token | |
| OpenRouter | Google: Gemini 2.5 Flash LiteReasoning | $0.4/M out | internal_reasoning: 0.0000004 / token | |
| OpenRouter | Google: Gemma 4 31B | $0.4/M out | completion: 0.0000004 / token | |
| OpenRouter | NVIDIA: Nemotron 3 Super | $0.4/M out | completion: 0.0000004 / token | |
| OpenRouter | OpenAI: GPT-4.1 Nano | $0.4/M out | completion: 0.0000004 / token | |
| OpenRouter | OpenAI: GPT-5 Nano | $0.4/M out | completion: 0.0000004 / token | |
| OpenRouter | Qwen2.5 72B Instruct | $0.4/M out | completion: 0.0000004 / token | |
| OpenRouter | Qwen: Qwen3.7 FlashPrompt > 32K | $0.4/M out | completion: 0.0000004 / token (>32000) | |
| OpenRouter | TheDrummer: UnslopNemo 12B | $0.4/M out | completion: 0.0000004 / token | |
| OpenRouter | Z.ai: GLM 4.7 Flash | $0.4/M out | completion: 0.0000004 / token | |
| Replicate | openai/gpt-5-nano | $0.4/M out | $0.40 per million output tokens | |
| Replicate | openai/gpt-5-structuredgpt-5-nano | $0.4/M out | $0.40 per million output tokens (gpt-5-nano) | |
| OpenRouter | DeepSeek: DeepSeek V3.2 Exp | $0.41/M out | completion: 0.00000041 / token | |
| APIMart | deepseek-v4.1-flash | $0.4571/M out | Input $0.1143 / Output $0.4571 · Per 1M tokens | |
| OpenRouter | DeepSeek: DeepSeek V4 Pro 0423 | $0.462492/M out | completion: 0.000000462492 / token | |
| OpenRouter | Qwen: Qwen3.8 Flash | $0.47/M out | completion: 0.00000047 / token | |
| OpenRouter | Qwen: Qwen3.8 Omni Flash | $0.47/M out | completion: 0.00000047 / token | |
| kie.ai | DeepSeek V4.1 Flash | $0.475/M out | 95 credits per million tokens ($0.475) | |
| APIMart | GPT-4o Mini | $0.48/M out | Input $0.12 / Output $0.48 · Per 1M tokens | |
| OpenRouter | Anthropic: Claude Haiku 5.5 | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouter | DeepSeek: DeepSeek V4.1 Flash 1017 | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouter | LiquidAI: LFM2.5-2.6B | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouter | NVIDIA: Nemotron 3.5 Super VL | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT-6 Luna | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT-6 Luna Pro | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouter | Particle AI: Particle-1 | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouter | PrismML: Ternary Bonsai 2 27B | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouter | Qwen: Qwen3 30B A3B | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouter | TheDrummer: Cydonia 24B V4.1 | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Haiku Latest | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouter | DeepSeek: DeepSeek Flash Latest | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT Luna Latest | $0.5/M out | completion: 0.0000005 / token | |
| Replicate | ibm-granite/granite-20b-code-instruct-8k | $0.5/M out | $0.50 per million output tokens | |
| Replicate | meta/llama-2-13b | $0.5/M out | $0.50 per million output tokens | |
| Replicate | meta/llama-2-13b-chat | $0.5/M out | $0.50 per million output tokens | |
| APIMart | deepseek-v4-flash | $0.5143/M out | Input $0.1714 / Output $0.5143 · Per 1M tokens | |
| OpenRouter | Tencent: Hy3 | $0.528/M out | completion: 0.000000528 / token | |
| OpenRouter | Mistral: Mistral Small 3.1 24B | $0.555/M out | completion: 0.000000555 / token | |
| APIMart | kimi-k2.5 | $0.5551/M out | Input $0.4112 / Output $0.5551 · Per 1M tokens | |
| OpenRouter | DeepSeek: DeepSeek V4.1 Flash | $0.567/M out | completion: 0.000000567 / token | |
| OpenRouter | Tencent: Hunyuan A13B Instruct | $0.57/M out | completion: 0.00000057 / token | |
| OpenRouter | Cohere: Command R (08-2024) | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | MiniMax: MiniMax M3.1 Flash | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | Mistral: Saba | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | Mistral: Mistral Small 4 | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | Morph: Morph V3 Fast (batch) | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | OpenAI: GPT-4o-mini | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | OpenAI: GPT-4o-mini (2024-07-18) | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro (batch) | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna (batch) | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | Qwen: Qwen3 Coder 30B A3B Instruct | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | Qwen: Qwen3 VL 30B A3B Instruct | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | Ricursive: Ripple 65B Preview | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | Tencent: Hy3 preview | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouter | Upstage: Solar Pro 4 | $0.6/M out | completion: 0.0000006 / token | |
| Replicate | openai/gpt-4o-mini | $0.6/M out | $0.60 per million output tokens | |
| Replicate | openai/gpt-image-2.6-flaresvg-gpt-6-luna · gpt-6-luna | $0.6/M out | $0.0000006 gpt-6-luna output tokens (svg-gpt-6-luna) | |
| Replicate | openai/gpt-image-2.6-sunburstsvg-gpt-6-luna · gpt-6-luna | $0.6/M out | $0.0000006 gpt-6-luna output tokens (svg-gpt-6-luna) | |
| OpenRouter | OpenAI: GPT-5.4 Nano (batch) | $0.625/M out | completion: 0.000000625 / token |
