11,195 prices on 4,854 listings · last collected 5 h 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 11,195Per second of output 2,701Per minute 34Per video 674Per image 1,827Per 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) 1,784Other units (see the platform’s wording) 228
Showing 101–200 of 1,235
Per million output tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| ReplicatePlatform-hosted | ibm-granite/granite-3.1-8b-instruct | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.2-8b-instruct | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.3-8b-instruct | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-4.0-h-small | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-4.1-8b | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-4.2-8b | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-8b-code-instruct-128k | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-speech-4.1-2b | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-vision-3.3-2b | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-vision-4.1-4b | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | meta/llama-2-7b | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | meta/llama-2-7b-chat | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-8b | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-8b-instruct | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | mistralai/mistral-7b-v0.1 | $0.25/M out | $0.25 per million output tokens | |
| OpenRouterOfficial | Qwen: Qwen3.5-Flash | $0.26/M out | completion: 0.00000026 / token (endpoint alibaba) | |
| OpenRouterThird-party | Qwen: Qwen3 32Bvia DeepInfra · fp8 | $0.28/M out | completion: 0.00000028 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 Coder 30B A3B Instructvia SiliconFlow · fp8 | $0.28/M out | completion: 0.00000028 / token (endpoint siliconflow/fp8) | |
| OpenRouterThird-party | Xiaomi: MiMo-V2.6-Flashvia Darkbloom · fp4 | $0.28/M out | completion: 0.00000028 / token (endpoint darkbloom/fp4) | |
| RunwareNot disclosed | gpt-oss-safeguard-20b | $0.28/M out | $2.8e-7 / outputToken | |
| AibermNot disclosed | MiMo V2.5 | $0.29/M out | model_ratio 0.21 × $2/M · group default ×0.23 · completion_ratio 3Claims official price $2/M out | |
| AibermNot disclosed | MiMo V2 Flash | $0.29/M out | model_ratio 0.21 × $2/M · group default ×0.23 · completion_ratio 3Claims official price $0.3/M out | |
| OpenRouterOfficial | Tencent: Hy-MT2-30B-A3B | $0.295/M out | completion: 0.000000295 / token (endpoint tencent/fp8) | |
| OpenRouterOfficial | Tencent: Hy-MT2-7B | $0.295/M out | completion: 0.000000295 / token (endpoint tencent/fp8) | |
| RunwareNot disclosed | Gemma 4 31B | $0.297/M out | $2.97e-7 / outputToken | |
| KIENot disclosed | claude-haiku-5-5 | $0.3/M out | 60 credits per million tokens ($0.30)Claims official or Fal price $0.5/M out | |
| OpenRouterThird-party | Meta: Llama 4 Scoutvia DeepInfra · fp8 | $0.3/M out | completion: 0.0000003 / token (endpoint deepinfra/fp8) | |
| OpenRouterOfficial | Mistral: Voxtral Small 24B 2507 | $0.3/M out | completion: 0.0000003 / token | |
| OpenRouterOfficial | OpenAI: GPT-4o-mini (batch) | $0.3/M out | completion: 0.0000003 / token (endpoint openai) | |
| OpenRouterThird-party | OpenAI: gpt-oss-safeguard-20b | $0.3/M out | completion: 0.0000003 / token | |
| OpenRouterThird-party | Qwen: Qwen3 30B A3B Instruct 2507via DekaLLM | $0.3/M out | completion: 0.0000003 / token (endpoint dekallm) | |
| OpenRouterThird-party | Ricursive: Ripple 65B Previewvia PrimeIntellect · bf16 | $0.3/M out | completion: 0.0000003 / token (endpoint primeintellect/bf16) | |
| OpenRouterThird-party | StepFun: Step 3.5 Flash | $0.3/M out | completion: 0.0000003 / token (endpoint siliconflow/fp8) | |
| OpenRouterNot disclosed | DeepSeek: DeepSeek V4 Flash Latest | $0.3/M out | completion: 0.0000003 / token | |
| APIMartNot disclosed | deepseek-v3.2 | $0.308/M out | Input $0.2056 / Output $0.3084 · Per 1M tokens | |
| APIMartNot disclosed | deepseek-v3.2-exp | $0.308/M out | Input $0.2056 / Output $0.3084 · Per 1M tokens | |
| APIMartNot disclosed | qwen3.8-flash | $0.309/M out | Input $0.0914 / Output $0.3086 · Per 1M tokens | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3.2via GMICloud · fp8 | $0.31/M out | completion: 0.0000003096 / token (endpoint gmicloud/fp8) | |
| AibermNot disclosed | DeepSeek V3.2 Exp | $0.311/M out | model_ratio 0.45 × $2/M · group default ×0.23 · completion_ratio 1.5 | |
| AibermNot disclosed | DeepSeek V3.2 | $0.311/M out | model_ratio 0.45 × $2/M · group default ×0.23 · completion_ratio 1.5Claims official price $0.42/M out | |
| AibermNot disclosed | DeepSeek V3.2 Exp | $0.311/M out | model_ratio 0.45 × $2/M · group default ×0.23 · completion_ratio 1.5Claims official price $0.42/M out | |
| AibermNot disclosed | DeepSeek V3.2 Exp Thinking | $0.311/M out | model_ratio 0.45 × $2/M · group default ×0.23 · completion_ratio 1.5Claims official price $0.42/M out | |
| APIMartNot disclosed | babbage-002 | $0.32/M out | Input $0.32 / Output $0.32 · Per 1M tokens | |
| APIMartNot disclosed | gpt-4.1-nano | $0.32/M out | Input $0.08 / Output $0.32 · Per 1M tokens | |
| APIMartNot disclosed | gpt-4.1-nano-2025-04-14 | $0.32/M out | Input $0.08 / Output $0.32 · Per 1M tokens | |
| APIMartNot disclosed | gpt-5-nano | $0.32/M out | Input $0.04 / Output $0.32 · Per 1M tokens | |
| APIMartNot disclosed | gpt-5-nano-2025-08-07 | $0.32/M out | Input $0.04 / Output $0.32 · Per 1M tokens | |
| OpenRouterThird-party | Meta: Llama 3.3 70B InstructTurbovia DeepInfra | $0.32/M out | completion: 0.00000032 / token (endpoint deepinfra/turbo) | |
| OpenRouterThird-party | Meta: Llama 3.2 3B Instructvia Parasail · bf16 | $0.33/M out | completion: 0.00000033 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Tencent: Hy3off-peak 1600–0000 UTC · via Tencent · fp8 | $0.33/M out | completion: 0.00000033 / token (utc_start 1600, utc_end 0; endpoint tencent/fp8) | |
| KIENot disclosed | gpt-5.6-luna | $0.336/M out | 67.2 credits per million tokens ($0.336)Claims official or Fal price $1.2/M out | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4.1 Flash (batch) | $0.336/M out | completion: 0.000000336 / token (endpoint deepinfra/fp8) | |
| OpenRouterNot disclosed | Google: Gemma 4 31Bvia KT | $0.34/M out | completion: 0.00000034 / token (endpoint kt) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3.5 Super VLvia Darkbloom · nvfp4 | $0.35/M out | completion: 0.00000035 / token (endpoint darkbloom/nvfp4) | |
| ReplicateOfficial partner | openai/gpt-oss-20b | $0.36/M out | $0.36 per million output tokens | |
| AibermNot disclosed | Claude Haiku 5.5 | $0.368/M out | model_ratio 0.16 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $0.5/M out | |
| OpenRouterOfficial | OpenAI: GPT-6 Luna Pro (batch)Prompt > 272K | $0.375/M out | completion: 0.000000375 / token (>272000; endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6 Luna (batch)Prompt > 272K | $0.375/M out | completion: 0.000000375 / token (>272000; endpoint openai) | |
| APIMartNot disclosed | claude-haiku-5-5 | $0.4/M out | Input $0.08 / Output $0.4 · Per 1M tokens | |
| APIMartNot disclosed | gpt-6-luna | $0.4/M out | Input $0.08 / Output $0.4 · Per 1M tokens | |
| OpenRouterOfficial | ByteDance Seed: Seed-2.0-Mini | $0.4/M out | completion: 0.0000004 / token (endpoint seed/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4.1 Flashvia Morph · fp8 | $0.4/M out | completion: 0.0000004 / token (endpoint morph/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4.1 Flash 1017via Morph · fp8 | $0.4/M out | completion: 0.0000004 / token (endpoint morph/fp8) | |
| OpenRouterOfficial | Google: Gemini 2.5 Flash Litevia Google AI Studio | $0.4/M out | completion: 0.0000004 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 2.5 Flash LiteReasoningvia Google AI Studio | $0.4/M out | internal_reasoning: 0.0000004 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Nex AGI: Nex-N2.6 | $0.4/M out | completion: 0.0000004 / token (endpoint nex-agi/fp8) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3 Supervia DeepInfra · bf16 | $0.4/M out | completion: 0.0000004 / token (endpoint deepinfra/bf16) | |
| OpenRouterOfficial partner | OpenAI: GPT-4.1 Nanovia Azure | $0.4/M out | completion: 0.0000004 / token (endpoint azure) | |
| OpenRouterOfficial partner | OpenAI: GPT-5 Nanovia Azure | $0.4/M out | completion: 0.0000004 / token (endpoint azure) | |
| OpenRouterThird-party | Qwen2.5 72B Instruct | $0.4/M out | completion: 0.0000004 / token (endpoint deepinfra/fp8) | |
| OpenRouterOfficial | Qwen: Qwen3.7 FlashPrompt > 32Kvia Alibaba | $0.4/M out | completion: 0.0000004 / token (>32000; endpoint alibaba) | |
| OpenRouterThird-party | TheDrummer: UnslopNemo 12B | $0.4/M out | completion: 0.0000004 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Z.ai: GLM 4.7 Flashvia Cloudflare | $0.4/M out | completion: 0.0000004 / token (endpoint cloudflare) | |
| ReplicateOfficial partner | openai/gpt-5-nano | $0.4/M out | $0.40 per million output tokens | |
| ReplicateOfficial partner | openai/gpt-5-structuredgpt-5-nano | $0.4/M out | $0.40 per million output tokens (gpt-5-nano) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3.2 Exp | $0.41/M out | completion: 0.00000041 / token (endpoint siliconflow/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3.8 27Bvia PrimeIntellect · fp8 | $0.44/M out | completion: 0.00000044 / token (endpoint primeintellect/fp8) | |
| OpenRouterThird-party | MiniMax: MiniMax M3.1 Flashvia GMICloud · fp8 | $0.45/M out | completion: 0.00000045 / token (endpoint gmicloud/fp8) | |
| APIMartNot disclosed | deepseek-v4.1-flash | $0.457/M out | Input $0.1143 / Output $0.4571 · Per 1M tokens | |
| OpenRouterOfficial | Qwen: Qwen3.8 Flashvia Alibaba | $0.47/M out | completion: 0.00000047 / token (endpoint alibaba) | |
| OpenRouterOfficial | Qwen: Qwen3.8 Omni Flash | $0.47/M out | completion: 0.00000047 / token (endpoint alibaba) | |
| KIENot disclosed | DeepSeek V4.1 Flash | $0.475/M out | 95 credits per million tokens ($0.475) | |
| APIMartNot disclosed | gpt-4o-mini | $0.48/M out | Input $0.12 / Output $0.48 · Per 1M tokens | |
| AibermNot disclosed | DeepSeek V4.1 Flash | $0.48/M out | model_ratio 0.26087 × $2/M · group default ×0.23 · completion_ratio 4Claims official price $0.6/M out | |
| OpenRouterOfficial partner | Anthropic: Claude Haiku 5.5via Google · global | $0.5/M out | completion: 0.0000005 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | LiquidAI: LFM2.5-2.6B | $0.5/M out | completion: 0.0000005 / token (endpoint liquid/fp8) | |
| OpenRouterOfficial | Mancer: Weaver (alpha) | $0.5/M out | completion: 0.0000005 / token (endpoint mancer/fp8) | |
| OpenRouterThird-party | Meta: Muse Embervia Google · global | $0.5/M out | completion: 0.0000005 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-6 Lunavia Amazon Bedrock · global | $0.5/M out | completion: 0.0000005 / token (endpoint amazon-bedrock/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-6 Luna Provia OpenAI | $0.5/M out | completion: 0.0000005 / token (endpoint openai) | |
| OpenRouterOfficial | Particle AI: Particle-1 | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouterThird-party | PrismML: Ternary Bonsai 2 27B | $0.5/M out | completion: 0.0000005 / token (endpoint darkbloom/int4) | |
| OpenRouterThird-party | Qwen: Qwen3 30B A3B | $0.5/M out | completion: 0.0000005 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | TheDrummer: Cydonia 24B V4.1 | $0.5/M out | completion: 0.0000005 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | ReMM SLERP 13B | $0.5/M out | completion: 0.0000005 / token (endpoint mancer/fp8) | |
| OpenRouterNot disclosed | Anthropic: Claude Haiku Latest | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouterNot disclosed | DeepSeek: DeepSeek Flash Latest | $0.5/M out | completion: 0.0000005 / token | |
| OpenRouterNot disclosed | OpenAI: GPT Luna Latest | $0.5/M out | completion: 0.0000005 / token | |
| ReplicatePlatform-hosted | ibm-granite/granite-20b-code-instruct-8k | $0.5/M out | $0.50 per million output tokens | |
| ReplicatePlatform-hosted | meta/llama-2-13b | $0.5/M out | $0.50 per million output tokens |
