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 2,592Per 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) 184Other units (see the platform’s wording) 14
Showing 1–100 of 859
Per million output tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | Cohere: North Mini Code (free) | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | Dots Studio: Dots3-Note Preview (free) | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | Google: Gemma 4 26B A4B (free) | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | Google: Gemma 4 31B (free) | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | Google: Lyria 3 Clip Preview | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | Google: Lyria 3 Pro Preview | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | LiquidAI: LFM2.5-2.6B (free) | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | LiquidAI: LFM3-1.7B (free) | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | NVIDIA: Nemotron 3 Nano Omni (free) | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | NVIDIA: Nemotron 3 Ultra (free) | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | NVIDIA: Nemotron 3.5 Lightning (free) | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | NVIDIA: Nemotron 3.5 Super VL (free) | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | Free Models Router | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | Recursive: Flint (free) | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | ScaleDown: Extract | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | ScaleDown: Summarize | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | Crouton Alpha | $0/M outCheapest | completion: 0 / token | |
| OpenRouter | XingChen: Xing4.0 29B A4B (free) | $0/M outCheapest | completion: 0 / token | |
| APIMart | text-embedding-3-small | $0.016/M out | Input $0.016 / Output $0.016 · Per 1M tokens | |
| OpenRouter | Mistral: Mistral Nemo | $0.03/M out | completion: 0.00000003 / token | |
| OpenRouter | inclusionAI: Ling 3.0 Tiny | $0.045/M out | completion: 0.000000045 / token | |
| OpenRouter | Sao10K: Llama 3 8B Lunaris | $0.05/M out | completion: 0.00000005 / token | |
| OpenRouter | inclusionAI: Ling 3.0 Flash | $0.063/M out | completion: 0.000000063 / token | |
| APIMart | text-embedding-ada-002 | $0.08/M out | Input $0.08 / Output $0.08 · Per 1M tokens | |
| OpenRouter | Meta: Llama 3.1 8B Instruct | $0.08/M out | completion: 0.00000008 / token | |
| OpenRouter | Mistral: Mistral Small 3 | $0.08/M out | completion: 0.00000008 / token | |
| OpenRouter | Z.ai: GLM 5.3 Flash | $0.083/M out | completion: 0.000000083 / token | |
| OpenRouter | Z.ai: GLM Flash Latest | $0.083/M out | completion: 0.000000083 / token | |
| APIMart | qwen3.7-flash | $0.0914/M out | Input $0.0229 / Output $0.0914 · Per 1M tokens | |
| OpenRouter | OpenAI: gpt-oss-120b | $0.094/M out | completion: 0.000000094 / token | |
| OpenRouter | Google: Gemma 3 4B | $0.1/M out | completion: 0.0000001 / token | |
| OpenRouter | Mistral: Ministral 3 3B 2512 | $0.1/M out | completion: 0.0000001 / token | |
| OpenRouter | Nex AGI: Nex-N2.5-Mini | $0.1/M out | completion: 0.0000001 / token | |
| OpenRouter | Reka Edge | $0.1/M out | completion: 0.0000001 / token | |
| APIMart | text-embedding-3-large | $0.104/M out | Input $0.104 / Output $0.104 · Per 1M tokens | |
| OpenRouter | MythoMax 13B | $0.11/M out | completion: 0.00000011 / token | |
| OpenRouter | OpenAI: gpt-oss-20b (batch) | $0.112/M out | completion: 0.000000112 / token | |
| OpenRouter | OpenAI: gpt-oss-20b | $0.13/M out | completion: 0.00000013 / token | |
| OpenRouter | PrismML: Ternary Bonsai 2 9B | $0.13/M out | completion: 0.00000013 / token | |
| OpenRouter | Qwen: Qwen3.7 Flash | $0.13/M out | completion: 0.00000013 / token | |
| OpenRouter | inclusionAI: Ling 3.1 Flash | $0.135/M out | completion: 0.000000135 / token | |
| OpenRouter | OpenAI: gpt-oss-120b (batch) | $0.136/M out | completion: 0.000000136 / token | |
| OpenRouter | Amazon: Nova Micro 1.0 | $0.14/M out | completion: 0.00000014 / token | |
| OpenRouter | Microsoft: Phi 4 | $0.14/M out | completion: 0.00000014 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Flash 0731 (batch) | $0.144/M out | completion: 0.000000144 / token | |
| kie.ai | gpt-6-luna | $0.15/M out | 30 credits per million tokens ($0.15)Claims fal charges $0.5/M out | |
| OpenRouter | Cohere: Command R7B (12-2024) | $0.15/M out | completion: 0.00000015 / token | |
| OpenRouter | Google: Gemma 3 12B | $0.15/M out | completion: 0.00000015 / token | |
| OpenRouter | Inference.net: Schematron V2 Turbo | $0.15/M out | completion: 0.00000015 / token | |
| OpenRouter | Mistral: Ministral 3 8B 2512 | $0.15/M out | completion: 0.00000015 / token | |
| APIMart | omni-moderation-latest | $0.16/M out | Input $0.16 / Output $0.16 · Per 1M tokens | |
| APIMart | text-moderation-latest | $0.16/M out | Input $0.16 / Output $0.16 · Per 1M tokens | |
| APIMart | text-moderation-stable | $0.16/M out | Input $0.16 / Output $0.16 · Per 1M tokens | |
| OpenRouter | Tencent: Hy-MT2-1.8B | $0.177/M out | completion: 0.000000177 / token | |
| OpenRouter | inclusionAI: Ling 3.0 Flash VL | $0.18/M out | completion: 0.00000018 / token | |
| OpenRouter | Meta: Llama Guard 4 12B | $0.18/M out | completion: 0.00000018 / token | |
| OpenRouter | Z.ai: GLM 5.3 Flash (batch) | $0.18/M out | completion: 0.00000018 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Flash 0423 | $0.182/M out | completion: 0.000000182 / token | |
| APIMart | glm-5.3-flash | $0.2/M out | Input $0.06 / Output $0.2 · Per 1M tokens | |
| OpenRouter | ByteDance: UI-TARS 7B | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | DeepSeek: DeepSeek V4.1 Flash 1017 (batch) | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | DeepSeek: DeepSeek V4.1 Flash (batch) | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | LiquidAI: LFM3-1.7B | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | Meta: Muse Spark 1.2 Contributor | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | Meta: Muse Spark 1.3 Contributor | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | Mistral: Ministral 3 14B 2512 | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | Mistral: Mistral Small 3.2 24B | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | NVIDIA: Nemotron 3.5 Content Safety | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | NVIDIA: Nemotron 3.5 Lightning | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-4.1 Nano (batch) | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5 Nano (batch) | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | Qwen: Qwen2.5 7B Instruct | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | Reka Flash 3 | $0.2/M out | completion: 0.0000002 / token | |
| OpenRouter | Upstage: Solar Mini 4 | $0.2/M out | completion: 0.0000002 / token | |
| Replicate | meta/llama-guard-4-12b | $0.2/M out | $0.20 per million output tokens | |
| OpenRouter | Meta: Llama 3.2 1B Instruct | $0.201/M out | completion: 0.000000201 / token | |
| APIMart | deepseek-ocr | $0.2052/M out | Input $0.0456 / Output $0.2052 · Per 1M tokens | |
| OpenRouter | Google: Gemma 4 26B A4B | $0.225/M out | completion: 0.000000225 / token | |
| OpenRouter | Inference.net: Schematron V2 Small | $0.23/M out | completion: 0.00000023 / token | |
| OpenRouter | Amazon: Nova Lite 1.0 | $0.24/M out | completion: 0.00000024 / token | |
| OpenRouter | NVIDIA: Nemotron 3 Nano 30B A3B | $0.24/M out | completion: 0.00000024 / token | |
| OpenRouter | Qwen: Qwen3 14B | $0.24/M out | completion: 0.00000024 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch) | $0.25/M out | completion: 0.00000025 / token | |
| OpenRouter | IBM: Granite 4.2 8B | $0.25/M out | completion: 0.00000025 / token | |
| OpenRouter | Nex AGI: Nex-N2.5-Pro | $0.25/M out | completion: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-6 Luna Pro (batch) | $0.25/M out | completion: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-6 Luna (batch) | $0.25/M out | completion: 0.00000025 / token | |
| OpenRouter | Qwen: Qwen3.5-9B | $0.25/M out | completion: 0.00000025 / token | |
| Replicate | ibm-granite/granite-3.0-2b-instruct | $0.25/M out | $0.25 per million output tokens | |
| Replicate | ibm-granite/granite-3.0-8b-instruct | $0.25/M out | $0.25 per million output tokens | |
| Replicate | ibm-granite/granite-3.1-2b-instruct | $0.25/M out | $0.25 per million output tokens | |
| Replicate | ibm-granite/granite-3.1-8b-instruct | $0.25/M out | $0.25 per million output tokens | |
| Replicate | ibm-granite/granite-3.2-8b-instruct | $0.25/M out | $0.25 per million output tokens | |
| Replicate | ibm-granite/granite-3.3-8b-instruct | $0.25/M out | $0.25 per million output tokens | |
| Replicate | ibm-granite/granite-4.0-h-small | $0.25/M out | $0.25 per million output tokens | |
| Replicate | ibm-granite/granite-4.1-8b | $0.25/M out | $0.25 per million output tokens | |
| Replicate | ibm-granite/granite-4.2-8b | $0.25/M out | $0.25 per million output tokens | |
| Replicate | ibm-granite/granite-8b-code-instruct-128k | $0.25/M out | $0.25 per million output tokens | |
| 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 |
