11,195 prices on 4,854 listings · last collected 14 min ago · 442 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on ten 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
Unit price
All 10,484Per second of output 2,638Per minute 34Per video 649Per image 1,782Per megapixel 326Per million input tokens 1,298Per million output tokens 1,235Per million tokens 47Per million cached input tokens (read) 641Per million cache-write tokens 227Per thousand characters 75Per second of compute time 98Per run (default parameters) 1,216Other units (see the platform’s wording) 218
Showing 1–100 of 1,298
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterOfficial | Baidu: ERNIE-5.5-Flash-Preview (free) | $0/M inCheapest | prompt: 0 / token (endpoint baidu) | |
| OpenRouterOfficial | Cohere: North Mini Code (free) | $0/M inCheapest | prompt: 0 / token (endpoint cohere) | |
| OpenRouterThird-party | Dots Studio: Dots3-Note Preview (free) | $0/M inCheapest | prompt: 0 / token (endpoint atlas-cloud/fp8) | |
| OpenRouterOfficial | Google: Gemma 4 26B A4B (free) | $0/M inCheapest | prompt: 0 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemma 4 31B (free) | $0/M inCheapest | prompt: 0 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | LiquidAI: LFM2.5-2.6B (free) | $0/M inCheapest | prompt: 0 / token (endpoint liquid/fp8) | |
| OpenRouterOfficial | LiquidAI: LFM3-1.7B (free) | $0/M inCheapest | prompt: 0 / token (endpoint liquid/fp8) | |
| OpenRouterOfficial | NVIDIA: Nemotron 3 Nano Omni (free) | $0/M inCheapest | prompt: 0 / token (endpoint nvidia) | |
| OpenRouterOfficial | NVIDIA: Nemotron 3 Ultra (free) | $0/M inCheapest | prompt: 0 / token (endpoint nvidia) | |
| OpenRouterOfficial | NVIDIA: Nemotron 3.5 Lightning (free) | $0/M inCheapest | prompt: 0 / token (endpoint nvidia/nvfp4) | |
| OpenRouterOfficial | NVIDIA: Nemotron 3.5 Super VL (free) | $0/M inCheapest | prompt: 0 / token | |
| OpenRouterNot disclosed | Free Models Router | $0/M inCheapest | prompt: 0 / token | |
| OpenRouterOfficial | Recursive: Flint (free) | $0/M inCheapest | prompt: 0 / token (endpoint recursive/bf16) | |
| OpenRouterOfficial | Thinking Machines: Inkling 2 Small (free) | $0/M inCheapest | prompt: 0 / token (endpoint thinkingmachines/nvfp4) | |
| AibermNot disclosed | Text Embedding 3 Small | $0.0046/M in | model_ratio 0.01 × $2/M · group default ×0.23Claims official price $0.02/M in | |
| OpenRouterNot disclosed | DeepSeek: DeepSeek Flash Latest | $0.006/M in | prompt: 0.000000006 / token | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4.1 Flash 1017 (batch) | $0.011/M in | prompt: 0.000000011 / token (endpoint morph/fp8) | |
| AibermNot disclosed | GPT-4.1 Nano | $0.013/M in | model_ratio 0.028 × $2/M · group default ×0.23Claims official price $0.1/M in | |
| AibermNot disclosed | GPT-5 Nano | $0.014/M in | model_ratio 0.031 × $2/M · group default ×0.23Claims official price $0.05/M in | |
| OpenRouterOfficial | inclusionAI: Ling 3.0 Tiny | $0.015/M in | prompt: 0.000000015 / token (endpoint antdigital/fp8) | |
| APIMartNot disclosed | text-embedding-3-small | $0.016/M in | Input $0.016 / Output $0.016 · Per 1M tokens | |
| OpenRouterThird-party | Google: Gemma 4 26B A4B via PrimeIntellect · bf16 | $0.016/M in | prompt: 0.000000016 / token (endpoint primeintellect/bf16) | |
| OpenRouterThird-party | Mistral: Mistral Nemovia Io Net · fp16 | $0.017/M in | prompt: 0.00000001656 / token (endpoint io-net/fp16) | |
| OpenRouterThird-party | Meta: Llama 3.1 8B Instructvia DeepInfra · fp8 | $0.02/M in | prompt: 0.00000002 / token (endpoint deepinfra/fp8) | |
| RunwareNot disclosed | Laya | $0.02/M in | $2e-8 / inputToken | |
| OpenRouterThird-party | inclusionAI: Ling 3.0 Flashvia Novita | $0.021/M in | prompt: 0.000000021 / token (endpoint novita) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4.1 Flashvia Morph · fp8 | $0.022/M in | prompt: 0.000000022 / token (endpoint morph/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4.1 Flash 1017via Morph · fp8 | $0.022/M in | prompt: 0.000000022 / token (endpoint morph/fp8) | |
| OpenRouterThird-party | OpenAI: gpt-oss-20bvia PrimeIntellect · fp4 | $0.022/M in | prompt: 0.000000022 / token (endpoint primeintellect/fp4) | |
| APIMartNot disclosed | qwen3.7-flash | $0.023/M in | Input $0.0229 / Output $0.0914 · Per 1M tokens | |
| AibermNot disclosed | GPT-4o Mini | $0.023/M in | model_ratio 0.05 × $2/M · group default ×0.23Claims official price $0.15/M in | |
| AibermNot disclosed | Text Embedding Ada 002 | $0.023/M in | model_ratio 0.05 × $2/M · group default ×0.23Claims official price $0.1/M in | |
| OpenRouterThird-party | Qwen: Qwen3.6 35B A3Bvia PrimeIntellect · fp8 | $0.023/M in | prompt: 0.000000023 / token (endpoint primeintellect/fp8) | |
| OpenRouterThird-party | OpenAI: gpt-oss-20b (batch) | $0.024/M in | prompt: 0.000000024 / token (endpoint deepinfra/bf16) | |
| OpenRouterOfficial | Nex AGI: Nex-N2.5-Mini | $0.025/M in | prompt: 0.000000025 / token | |
| OpenRouterThird-party | NVIDIA: Nemotron 3.5 Lightningvia Darkbloom · int4 | $0.025/M in | prompt: 0.000000025 / token (endpoint darkbloom/int4) | |
| OpenRouterOfficial | OpenAI: GPT-5 Nano (batch) | $0.025/M in | prompt: 0.000000025 / token (endpoint openai) | |
| OpenRouterThird-party | Meta: Llama 3.2 1B Instruct | $0.027/M in | prompt: 0.000000027 / token (endpoint cloudflare) | |
| OpenRouterThird-party | OpenAI: gpt-oss-120b (batch) | $0.03/M in | prompt: 0.0000000296 / token (endpoint deepinfra/bf16) | |
| AibermNot disclosed | Text Embedding 3 Large | $0.03/M in | model_ratio 0.065 × $2/M · group default ×0.23Claims official price $0.13/M in | |
| KIENot disclosed | gpt-6-luna | $0.03/M in | 6 credits per million tokens ($0.03)Claims official or Fal price $0.1/M in | |
| OpenRouterOfficial | Inference.net: Schematron V2 Turbovia InferenceNet · bf16 | $0.03/M in | prompt: 0.00000003 / token (endpoint inference-net/bf16) | |
| OpenRouterOfficial | Qwen: Qwen3.7 Flashvia Alibaba | $0.03/M in | prompt: 0.00000003 / token (endpoint alibaba) | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.0-2b-instruct | $0.03/M in | $0.03 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.1-2b-instruct | $0.03/M in | $0.03 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.1-8b-instruct | $0.03/M in | $0.03 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.2-8b-instruct | $0.03/M in | $0.03 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.3-8b-instruct | $0.03/M in | $0.03 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-speech-4.1-2b | $0.03/M in | $0.03 per million input tokens | |
| OpenRouterOfficial | Amazon: Nova Micro 1.0via Amazon Bedrock | $0.035/M in | prompt: 0.000000035 / token (endpoint amazon-bedrock) | |
| OpenRouterThird-party | OpenAI: gpt-oss-120bvia PrimeIntellect · fp4 | $0.035/M in | prompt: 0.000000035 / token (endpoint primeintellect/fp4) | |
| OpenRouterOfficial | Cohere: Command R7B (12-2024) | $0.038/M in | prompt: 0.0000000375 / token (endpoint cohere) | |
| OpenRouterNot disclosed | Z.ai: GLM 5.3 Flashvia Relace · fp4 | $0.04/M in | prompt: 0.0000000399 / token (endpoint relace/fp4) | |
| OpenRouterNot disclosed | Z.ai: GLM Flash Latest | $0.04/M in | prompt: 0.0000000399 / token | |
| APIMartNot disclosed | gpt-5-nano | $0.04/M in | Input $0.04 / Output $0.32 · Per 1M tokens | |
| APIMartNot disclosed | gpt-5-nano-2025-08-07 | $0.04/M in | Input $0.04 / Output $0.32 · Per 1M tokens | |
| OpenRouterThird-party | Google: Gemma 3 4Bvia Parasail · bf16 | $0.04/M in | prompt: 0.00000004 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Sao10K: Llama 3 8B Lunarisvia Parasail · bf16 | $0.04/M in | prompt: 0.00000004 / token (endpoint parasail/bf16) | |
| OpenRouterOfficial | ScaleDown: Extract | $0.04/M in | prompt: 0.00000004 / token (endpoint scaledown) | |
| OpenRouterOfficial | ScaleDown: Summarize | $0.04/M in | prompt: 0.00000004 / token (endpoint scaledown) | |
| RunwareNot disclosed | Jev 1.13 | $0.042/M in | $4.2e-8 / inputToken | |
| RunwareNot disclosed | Jev 1.14 | $0.042/M in | $4.2e-8 / inputToken | |
| OpenRouterNot disclosed | DeepSeek: DeepSeek V4 Flash Latest | $0.043/M in | prompt: 0.0000000434 / token | |
| OpenRouterOfficial | Tencent: Hy-MT2-1.8B | $0.044/M in | prompt: 0.000000044 / token (endpoint tencent/fp8) | |
| OpenRouterThird-party | inclusionAI: Ling 3.1 Flash | $0.045/M in | prompt: 0.000000045 / token (endpoint novita) | |
| APIMartNot disclosed | deepseek-ocr | $0.046/M in | Input $0.0456 / Output $0.2052 · Per 1M tokens | |
| OpenRouterThird-party | Z.ai: GLM 5.3 Flash (batch)via Morph · fp8 | $0.047/M in | prompt: 0.000000047 / token (endpoint morph/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash 0731 (batch) | $0.048/M in | prompt: 0.000000048 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash 0423via Baidu · fp8 | $0.05/M in | prompt: 0.00000004998 / token (endpoint baidu/fp8) | |
| OpenRouterOfficial | Anthropic: Claude Haiku 5.5 (batch) | $0.05/M in | prompt: 0.00000005 / token (endpoint anthropic) | |
| OpenRouterOfficial | Inference.net: Schematron V2 Smallvia InferenceNet · bf16 | $0.05/M in | prompt: 0.00000005 / token (endpoint inference-net/bf16) | |
| OpenRouterOfficial | LiquidAI: LFM2.5-24B-A2B | $0.05/M in | prompt: 0.00000005 / token (endpoint liquid/fp8) | |
| OpenRouterThird-party | Meta: Llama 3.2 3B Instructvia Parasail · bf16 | $0.05/M in | prompt: 0.00000005 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Mistral: Mistral Small 3 | $0.05/M in | prompt: 0.00000005 / token (endpoint deepinfra/fp8) | |
| OpenRouterOfficial | OpenAI: GPT-4.1 Nano (batch) | $0.05/M in | prompt: 0.00000005 / token (endpoint openai) | |
| OpenRouterOfficial partner | OpenAI: GPT-5 Nanovia Azure | $0.05/M in | prompt: 0.00000005 / token (endpoint azure) | |
| OpenRouterOfficial | OpenAI: GPT-6 Luna Pro (batch) | $0.05/M in | prompt: 0.00000005 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6 Luna (batch) | $0.05/M in | prompt: 0.00000005 / token (endpoint openai) | |
| OpenRouterOfficial | Particle AI: Particle-1 | $0.05/M in | prompt: 0.00000005 / token | |
| OpenRouterOfficial | Upstage: Solar Mini 4via Upstage · zdr | $0.05/M in | prompt: 0.00000005 / token (endpoint upstage/zdr) | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.0-8b-instruct | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-8b-code-instruct-128k | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | meta/llama-2-7b | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | meta/llama-2-7b-chat | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-8b | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-8b-instruct | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | mistralai/mistral-7b-v0.1 | $0.05/M in | $0.05 per million input tokens | |
| ReplicateOfficial partner | openai/gpt-5-nano | $0.05/M in | $0.05 per million input tokens | |
| ReplicateOfficial partner | openai/gpt-5-structuredgpt-5-nano | $0.05/M in | $0.05 per million input tokens (gpt-5-nano) | |
| KIENot disclosed | gpt-5.6-luna | $0.056/M in | 11.2 credits per million tokens ($0.056)Claims official or Fal price $0.2/M in | |
| AibermNot disclosed | GPT-4.1 Mini | $0.06/M in | model_ratio 0.13 × $2/M · group default ×0.23Claims official price $0.4/M in | |
| APIMartNot disclosed | glm-5.3-flash | $0.06/M in | Input $0.06 / Output $0.2 · Per 1M tokens | |
| KIENot disclosed | claude-haiku-5-5 | $0.06/M in | 12 credits per million tokens ($0.06)Claims official or Fal price $0.1/M in | |
| OpenRouterOfficial | Amazon: Nova Lite 1.0via Amazon Bedrock | $0.06/M in | prompt: 0.00000006 / token (endpoint amazon-bedrock) | |
| OpenRouterThird-party | IBM: Granite 4.2 8Bvia CoreWeave · bf16 | $0.06/M in | prompt: 0.00000006 / token (endpoint coreweave/bf16) | |
| OpenRouterThird-party | inclusionAI: Ling 3.0 Flash VL | $0.06/M in | prompt: 0.00000006 / token (endpoint deepinfra/fp16) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3 Nano 30B A3B | $0.06/M in | prompt: 0.00000006 / token (endpoint nebius/fp8) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3.5 Super VLvia Darkbloom · nvfp4 | $0.06/M in | prompt: 0.00000006 / token (endpoint darkbloom/nvfp4) | |
| ReplicatePlatform-hosted | ibm-granite/granite-4.0-h-small | $0.06/M in | $0.06 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-4.1-8b | $0.06/M in | $0.06 per million input tokens |
