10,793 prices on 4,759 listings · last collected 47 min ago · 403 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on eight 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 price
All 10,228Per second of output 2,636Per minute 34Per video 649Per image 1,736Per megapixel 328Per 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) 970Other units (see the platform’s wording) 254
Showing 1–100 of 1,235
Per million output tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterOfficial | Baidu: ERNIE-5.5-Flash-Preview (free) | $0/M outCheapest | completion: 0 / token (endpoint baidu) | |
| OpenRouterOfficial | Cohere: North Mini Code (free) | $0/M outCheapest | completion: 0 / token (endpoint cohere) | |
| OpenRouterThird-party | Dots Studio: Dots3-Note Preview (free) | $0/M outCheapest | completion: 0 / token (endpoint atlas-cloud/fp8) | |
| OpenRouterOfficial | Google: Gemma 4 26B A4B (free) | $0/M outCheapest | completion: 0 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemma 4 31B (free) | $0/M outCheapest | completion: 0 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | LiquidAI: LFM2.5-2.6B (free) | $0/M outCheapest | completion: 0 / token (endpoint liquid/fp8) | |
| OpenRouterOfficial | LiquidAI: LFM3-1.7B (free) | $0/M outCheapest | completion: 0 / token (endpoint liquid/fp8) | |
| OpenRouterOfficial | NVIDIA: Nemotron 3 Nano Omni (free) | $0/M outCheapest | completion: 0 / token (endpoint nvidia) | |
| OpenRouterOfficial | NVIDIA: Nemotron 3 Ultra (free) | $0/M outCheapest | completion: 0 / token (endpoint nvidia) | |
| OpenRouterOfficial | NVIDIA: Nemotron 3.5 Lightning (free) | $0/M outCheapest | completion: 0 / token (endpoint nvidia/nvfp4) | |
| OpenRouterOfficial | NVIDIA: Nemotron 3.5 Super VL (free) | $0/M outCheapest | completion: 0 / token | |
| OpenRouterNot disclosed | Free Models Router | $0/M outCheapest | completion: 0 / token | |
| OpenRouterOfficial | Recursive: Flint (free) | $0/M outCheapest | completion: 0 / token (endpoint recursive/bf16) | |
| OpenRouterOfficial | ScaleDown: Extract | $0/M outCheapest | completion: 0 / token (endpoint scaledown) | |
| OpenRouterOfficial | ScaleDown: Summarize | $0/M outCheapest | completion: 0 / token (endpoint scaledown) | |
| OpenRouterOfficial | Thinking Machines: Inkling 2 Small (free) | $0/M outCheapest | completion: 0 / token (endpoint thinkingmachines/nvfp4) | |
| AibermNot disclosed | Text Embedding 3 Small | $0.0046/M out | model_ratio 0.01 × $2/M · group default ×0.23 · completion_ratio 1 | |
| APIMartNot disclosed | text-embedding-3-small | $0.016/M out | Input $0.016 / Output $0.016 · Per 1M tokens | |
| OpenRouterThird-party | Mistral: Mistral Nemovia Io Net · fp16 | $0.022/M out | completion: 0.0000000216 / token (endpoint io-net/fp16) | |
| AibermNot disclosed | Text Embedding Ada 002 | $0.023/M out | model_ratio 0.05 × $2/M · group default ×0.23 · completion_ratio 1 | |
| AibermNot disclosed | Text Embedding 3 Large | $0.03/M out | model_ratio 0.065 × $2/M · group default ×0.23 · completion_ratio 1 | |
| OpenRouterThird-party | OpenAI: gpt-oss-20bvia PrimeIntellect · fp4 | $0.032/M out | completion: 0.000000032 / token (endpoint primeintellect/fp4) | |
| OpenRouterThird-party | Meta: Llama 3.1 8B Instructvia DeepInfra · fp8 | $0.04/M out | completion: 0.00000004 / token (endpoint deepinfra/fp8) | |
| OpenRouterOfficial | inclusionAI: Ling 3.0 Tiny | $0.045/M out | completion: 0.000000045 / token (endpoint antdigital/fp8) | |
| OpenRouterThird-party | Google: Gemma 4 26B A4B via PrimeIntellect · bf16 | $0.049/M out | completion: 0.000000049 / token (endpoint primeintellect/bf16) | |
| OpenRouterThird-party | Google: Gemma 3 4Bvia Parasail · bf16 | $0.05/M out | completion: 0.00000005 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Sao10K: Llama 3 8B Lunarisvia Parasail · bf16 | $0.05/M out | completion: 0.00000005 / token (endpoint parasail/bf16) | |
| AibermNot disclosed | GPT-4.1 Nano | $0.052/M out | model_ratio 0.028 × $2/M · group default ×0.23 · completion_ratio 4Claims official price $0.4/M out | |
| OpenRouterThird-party | Z.ai: GLM 5.3 Flash (batch)via Morph · fp8 | $0.061/M out | completion: 0.000000061 / token (endpoint morph/fp8) | |
| OpenRouterThird-party | inclusionAI: Ling 3.0 Flashvia Novita | $0.063/M out | completion: 0.000000063 / token (endpoint novita) | |
| OpenRouterThird-party | OpenAI: gpt-oss-120bvia PrimeIntellect · fp4 | $0.076/M out | completion: 0.000000076 / token (endpoint primeintellect/fp4) | |
| OpenRouterNot disclosed | Z.ai: GLM 5.3 Flashvia Relace · fp4 | $0.078/M out | completion: 0.0000000784 / token (endpoint relace/fp4) | |
| OpenRouterNot disclosed | Z.ai: GLM Flash Latest | $0.078/M out | completion: 0.0000000784 / token | |
| APIMartNot disclosed | text-embedding-ada-002 | $0.08/M out | Input $0.08 / Output $0.08 · Per 1M tokens | |
| OpenRouterThird-party | Mistral: Mistral Small 3 | $0.08/M out | completion: 0.00000008 / token (endpoint deepinfra/fp8) | |
| RunwareNot disclosed | Shieldstral 1.0 3B | $0.09/M out | $9e-8 / outputToken | |
| APIMartNot disclosed | qwen3.7-flash | $0.091/M out | Input $0.0229 / Output $0.0914 · Per 1M tokens | |
| AibermNot disclosed | GPT-4o Mini | $0.092/M out | model_ratio 0.05 × $2/M · group default ×0.23 · completion_ratio 4Claims official price $0.6/M out | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash 0423via Baidu · fp8 | $0.1/M out | completion: 0.00000009996 / token (endpoint baidu/fp8) | |
| OpenRouterOfficial | Mistral: Ministral 3 3B 2512via Mistral · zdr | $0.1/M out | completion: 0.0000001 / token (endpoint mistral/zdr) | |
| OpenRouterOfficial | Nex AGI: Nex-N2.5-Mini | $0.1/M out | completion: 0.0000001 / token | |
| OpenRouterOfficial | Reka Edge | $0.1/M out | completion: 0.0000001 / token (endpoint reka) | |
| APIMartNot disclosed | text-embedding-3-large | $0.104/M out | Input $0.104 / Output $0.104 · Per 1M tokens | |
| OpenRouterThird-party | MythoMax 13Bvia Parasail · fp16 | $0.11/M out | completion: 0.00000011 / token (endpoint parasail/fp16) | |
| OpenRouterThird-party | OpenAI: gpt-oss-20b (batch) | $0.112/M out | completion: 0.000000112 / token (endpoint deepinfra/bf16) | |
| AibermNot disclosed | GPT-5 Nano | $0.114/M out | model_ratio 0.031 × $2/M · group default ×0.23 · completion_ratio 8Claims official price $0.4/M out | |
| OpenRouterThird-party | NVIDIA: Nemotron 3.5 Lightningvia Darkbloom · int4 | $0.12/M out | completion: 0.00000012 / token (endpoint darkbloom/int4) | |
| OpenRouterThird-party | PrismML: Ternary Bonsai 2 9B | $0.13/M out | completion: 0.00000013 / token (endpoint darkbloom/int4) | |
| OpenRouterThird-party | Qwen: Qwen3.5-9Bvia Darkbloom · fp4 | $0.13/M out | completion: 0.00000013 / token (endpoint darkbloom/fp4) | |
| OpenRouterOfficial | Qwen: Qwen3.7 Flashvia Alibaba | $0.13/M out | completion: 0.00000013 / token (endpoint alibaba) | |
| OpenRouterThird-party | inclusionAI: Ling 3.1 Flash | $0.135/M out | completion: 0.000000135 / token (endpoint novita) | |
| OpenRouterThird-party | OpenAI: gpt-oss-120b (batch) | $0.136/M out | completion: 0.000000136 / token (endpoint deepinfra/bf16) | |
| OpenRouterOfficial | Amazon: Nova Micro 1.0via Amazon Bedrock | $0.14/M out | completion: 0.00000014 / token (endpoint amazon-bedrock) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash 0731via Relace · fp4 | $0.14/M out | completion: 0.00000014 / token (endpoint relace/fp4) | |
| OpenRouterThird-party | Microsoft: Phi 4via DeepInfra · bf16 | $0.14/M out | completion: 0.00000014 / token (endpoint deepinfra/bf16) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash 0731 (batch) | $0.144/M out | completion: 0.000000144 / token (endpoint deepinfra/fp8) | |
| KIENot disclosed | gpt-6-luna | $0.15/M out | 30 credits per million tokens ($0.15)Claims official or Fal price $0.5/M out | |
| OpenRouterOfficial | Cohere: Command R7B (12-2024) | $0.15/M out | completion: 0.00000015 / token (endpoint cohere) | |
| OpenRouterThird-party | Google: Gemma 3 12Bvia NextBit · int4 | $0.15/M out | completion: 0.00000015 / token (endpoint nextbit/int4) | |
| OpenRouterThird-party | IBM: Granite 4.2 8Bvia CoreWeave · bf16 | $0.15/M out | completion: 0.00000015 / token (endpoint coreweave/bf16) | |
| OpenRouterOfficial | Inference.net: Schematron V2 Turbovia InferenceNet · bf16 | $0.15/M out | completion: 0.00000015 / token (endpoint inference-net/bf16) | |
| OpenRouterOfficial | Mistral: Ministral 3 8B 2512via Mistral · zdr | $0.15/M out | completion: 0.00000015 / token (endpoint mistral/zdr) | |
| RunwareNot disclosed | DeepSeek-V4-Flash-0731 | $0.153/M out | $1.53e-7 / outputToken | |
| APIMartNot disclosed | omni-moderation-latest | $0.16/M out | Input $0.16 / Output $0.16 · Per 1M tokens | |
| APIMartNot disclosed | text-moderation-latest | $0.16/M out | Input $0.16 / Output $0.16 · Per 1M tokens | |
| APIMartNot disclosed | text-moderation-stable | $0.16/M out | Input $0.16 / Output $0.16 · Per 1M tokens | |
| OpenRouterThird-party | Google: Gemma 3 27Bvia DeepInfra · fp8 | $0.16/M out | completion: 0.00000016 / token (endpoint deepinfra/fp8) | |
| OpenRouterOfficial | Tencent: Hy-MT2-1.8B | $0.177/M out | completion: 0.000000177 / token (endpoint tencent/fp8) | |
| OpenRouterThird-party | inclusionAI: Ling 3.0 Flash VL | $0.18/M out | completion: 0.00000018 / token (endpoint deepinfra/fp16) | |
| OpenRouterThird-party | Meta: Llama Guard 4 12Bvia DeepInfra · bf16 | $0.18/M out | completion: 0.00000018 / token (endpoint deepinfra/bf16) | |
| APIMartNot disclosed | glm-5.3-flash | $0.2/M out | Input $0.06 / Output $0.2 · Per 1M tokens | |
| OpenRouterThird-party | ByteDance: UI-TARS 7B | $0.2/M out | completion: 0.0000002 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4.1 Flash 1017 (batch) | $0.2/M out | completion: 0.0000002 / token (endpoint morph/fp8) | |
| OpenRouterOfficial | LiquidAI: LFM3-1.7B | $0.2/M out | completion: 0.0000002 / token (endpoint liquid/fp8) | |
| OpenRouterOfficial | Meta: Muse Spark 1.2 Contributor | $0.2/M out | completion: 0.0000002 / token (endpoint meta) | |
| OpenRouterOfficial | Meta: Muse Spark 1.3 Contributor | $0.2/M out | completion: 0.0000002 / token (endpoint meta) | |
| OpenRouterOfficial | Mistral: Ministral 3 14B 2512via Mistral · zdr | $0.2/M out | completion: 0.0000002 / token (endpoint mistral/zdr) | |
| OpenRouterThird-party | Mistral: Mistral Small 3.2 24Bvia DeepInfra · fp8 | $0.2/M out | completion: 0.0000002 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3.5 Content Safety | $0.2/M out | completion: 0.0000002 / token (endpoint deepinfra/bf16) | |
| OpenRouterOfficial | OpenAI: GPT-4.1 Nano (batch) | $0.2/M out | completion: 0.0000002 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-5 Nano (batch) | $0.2/M out | completion: 0.0000002 / token (endpoint openai) | |
| OpenRouterOfficial | Reka Flash 3 | $0.2/M out | completion: 0.0000002 / token (endpoint reka) | |
| OpenRouterOfficial | Upstage: Solar Mini 4via Upstage · zdr | $0.2/M out | completion: 0.0000002 / token (endpoint upstage/zdr) | |
| ReplicatePlatform-hosted | meta/llama-guard-4-12b | $0.2/M out | $0.20 per million output tokens | |
| OpenRouterThird-party | Meta: Llama 3.2 1B Instruct | $0.201/M out | completion: 0.000000201 / token (endpoint cloudflare) | |
| APIMartNot disclosed | deepseek-ocr | $0.205/M out | Input $0.0456 / Output $0.2052 · Per 1M tokens | |
| OpenRouterThird-party | Qwen: Qwen3.6 35B A3Bvia PrimeIntellect · fp8 | $0.213/M out | completion: 0.000000213 / token (endpoint primeintellect/fp8) | |
| AibermNot disclosed | DeepSeek V4 Flash | $0.216/M out | model_ratio 0.3126 × $2/M · group default ×0.23 · completion_ratio 1.5Claims official price $0.28/M out | |
| OpenRouterThird-party | Qwen: Qwen3 14Bvia NextBit · int4 | $0.22/M out | completion: 0.00000022 / token (endpoint nextbit/int4) | |
| OpenRouterOfficial | Inference.net: Schematron V2 Smallvia InferenceNet · bf16 | $0.23/M out | completion: 0.00000023 / token (endpoint inference-net/bf16) | |
| AibermNot disclosed | GPT-4.1 Mini | $0.239/M out | model_ratio 0.13 × $2/M · group default ×0.23 · completion_ratio 4Claims official price $1.6/M out | |
| OpenRouterOfficial | Amazon: Nova Lite 1.0via Amazon Bedrock | $0.24/M out | completion: 0.00000024 / token (endpoint amazon-bedrock) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3 Nano 30B A3B | $0.24/M out | completion: 0.00000024 / token (endpoint nebius/fp8) | |
| OpenRouterOfficial | Anthropic: Claude Haiku 5.5 (batch) | $0.25/M out | completion: 0.00000025 / token (endpoint anthropic) | |
| OpenRouterOfficial | Nex AGI: Nex-N2.5-Pro | $0.25/M out | completion: 0.00000025 / token (endpoint nex-agi/fp8) | |
| OpenRouterOfficial | OpenAI: GPT-6 Luna Pro (batch) | $0.25/M out | completion: 0.00000025 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6 Luna (batch) | $0.25/M out | completion: 0.00000025 / token (endpoint openai) | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.0-2b-instruct | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.0-8b-instruct | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.1-2b-instruct | $0.25/M out | $0.25 per million output tokens |
