11,195 prices on 4,854 listings · last collected 11 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
Model
Claude 
Gemini 
Qwen 
DeepSeek 
GLM 
Kimi 
Mistral 
Llama 
MiniMax 
Nemotron 
Hunyuan Unit price
All 3,235Per second of output 13Per image 6Per million input tokens 1,107Per million output tokens 1,071Per million tokens 5Per million cached input tokens (read) 594Per million cache-write tokens 224Per thousand characters 2Per second of compute time 12Per run (default parameters) 193Other units (see the platform’s wording) 8
Showing 301–400 of 3,235
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterThird-party | MiniMax: MiniMax M2.7via GMICloud · fp8 | $0.21/M in | prompt: 0.00000021 / token (endpoint gmicloud/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash Vision Expvia DeepInfra · fp8 | $0.216/M in | prompt: 0.0000002156 / token (endpoint deepinfra/fp8) | |
| APIMartNot disclosed | minimax-m2.1 | $0.216/M in | Input $0.216 / Output $0.864 · Per 1M tokens | |
| OpenRouterThird-party | MiniMax: MiniMax M3 (batch) | $0.224/M in | prompt: 0.000000224 / token (endpoint deepinfra/fp8) | |
| KIENot disclosed | Gemini 3.6 Flash | $0.225/M in | 45 credits per million tokens ($0.225)Claims official or Fal price $0.75/M in | |
| KIENot disclosed | Gemini 3.7 Flash | $0.225/M in | 45 credits per million tokens ($0.225)Claims official or Fal price $0.75/M in | |
| KIENot disclosed | Gemini 3.8 Flash | $0.225/M in | 45 credits per million tokens ($0.225)Claims official or Fal price $0.75/M in | |
| APIMartNot disclosed | qwen3.6-plus | $0.229/M in | Input $0.2286 / Output $1.3718 · Per 1M tokens | |
| APIMartNot disclosed | qwen3.7-plus | $0.229/M in | Input $0.2286 / Output $0.9146 · Per 1M tokens | |
| AibermNot disclosed | MiniMax M2.1 | $0.23/M in | model_ratio 0.5 × $2/M · group default ×0.23Claims official price $0.3/M in | |
| OpenRouterThird-party | MiniMax: MiniMax M3via CoreWeave · fp4 | $0.23/M in | prompt: 0.00000023 / token (endpoint coreweave/fp4) | |
| OpenRouterOfficial | Qwen: Qwen3.7 Plus (batch) | $0.23/M in | prompt: 0.00000023 / token (endpoint alibaba) | |
| OpenRouterThird-party | MoonshotAI: Kimi K3.1 Provia Relace · fp4 | $0.238/M in | prompt: 0.0000002375 / token (endpoint relace/fp4) | |
| APIMartNot disclosed | gemini-3.5-flash-lite | $0.24/M in | Input $0.24 / Output $1.9992 · Per 1M tokens | |
| APIMartNot disclosed | minimax-m2.5 | $0.24/M in | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMartNot disclosed | minimax-m2.7 | $0.24/M in | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMartNot disclosed | minimax-m3 | $0.24/M in | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMartNot disclosed | qwen-turbo | $0.24/M in | Input $0.24 / Output $2.4 · Per 1M tokens | |
| OpenRouterThird-party | Meta: Muse Glimmer 30B (batch) | $0.24/M in | prompt: 0.00000024 / token (endpoint deepinfra/bf16) | |
| OpenRouterOfficial | Anthropic: Claude Haiku 5.5 (batch)Prompt > 100K | $0.25/M in | prompt: 0.00000025 / token (>100000; endpoint anthropic) | |
| OpenRouterOfficial | ByteDance Seed: Seed-2.0-Lite | $0.25/M in | prompt: 0.00000025 / token (endpoint seed/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3 0324via SiliconFlow · fp8 | $0.25/M in | prompt: 0.00000025 / token (endpoint siliconflow/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3.1via DeepInfra · fp4 | $0.25/M in | prompt: 0.00000025 / token (endpoint deepinfra/fp4) | |
| OpenRouterOfficial | Google: Gemini 3 Flash Preview (batch)Image input | $0.25/M in | image: 0.00000025 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3 Flash Preview (batch) | $0.25/M in | prompt: 0.00000025 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.1 Flash LiteImage inputvia Google AI Studio | $0.25/M in | image: 0.00000025 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.1 Flash Litevia Google AI Studio | $0.25/M in | prompt: 0.00000025 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.1 Flash Lite PreviewImage inputvia Google AI Studio | $0.25/M in | image: 0.00000025 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.1 Flash Lite Previewvia Google AI Studio | $0.25/M in | prompt: 0.00000025 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.1 Flash Lite (batch)Audio input | $0.25/M in | audio: 0.00000025 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-5 Minivia Azure | $0.25/M in | prompt: 0.00000025 / token (endpoint azure) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.1-Codex-Mini | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouterThird-party | Qwen: Qwen3 VL 8B Instruct | $0.25/M in | prompt: 0.00000025 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Qwen: Qwen3.6 27Bvia Chutes · fp8 | $0.25/M in | prompt: 0.00000025 / token (endpoint chutes/fp8) | |
| OpenRouterThird-party | Reflection: Beam 1.0 501B A23Bvia Nebius · fp4 | $0.25/M in | prompt: 0.00000025 / token (endpoint nebius/fp4) | |
| ReplicatePlatform-hosted | meta/llama-4-maverick-instruct | $0.25/M in | $0.25 per million input tokens | |
| ReplicateOfficial partner | openai/gpt-5-mini | $0.25/M in | $0.25 per million input tokens | |
| ReplicateOfficial partner | openai/gpt-5-structuredgpt-5-mini | $0.25/M in | $0.25 per million input tokens (gpt-5-mini) | |
| RunwareNot disclosed | Gemini 3.1 Flash Litetext | $0.25/M in | $2.5e-7 / inputToken · text, image, video | |
| AibermNot disclosed | o3 Mini | $0.253/M in | model_ratio 0.55 × $2/M · group default ×0.23Claims official price $1.1/M in | |
| AibermNot disclosed | MiniMax M2.5 | $0.256/M in | model_ratio 0.5555 × $2/M · group default ×0.23Claims official price $0.3/M in | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3via StreamLake | $0.257/M in | prompt: 0.0000002574 / token (endpoint streamlake) | |
| AibermNot disclosed | GPT-6 Sol | $0.26/M in | model_ratio 0.5652 × $2/M · group default ×0.23Claims official price $2/M in | |
| AibermNot disclosed | GPT-6.1 Sol | $0.26/M in | model_ratio 0.5652 × $2/M · group default ×0.23Claims official price $2/M in | |
| FalOfficial partner | Isaac 0.1 | $0.26/M in | $0.26 per 1M input tokens, $2.17 per 1M output tokens | |
| FalOfficial partner | Isaac 0.1 [OpenAI Compatible Endpoint] | $0.26/M in | $0.26 per 1M input tokens, $2.17 per 1M output tokens | |
| OpenRouterOfficial | Qwen: Qwen-Plus | $0.26/M in | prompt: 0.00000026 / token (endpoint alibaba) | |
| OpenRouterThird-party | Qwen: Qwen3.5-122B-A10Bvia SiliconFlow · fp8 | $0.26/M in | prompt: 0.00000026 / token (endpoint siliconflow/fp8) | |
| OpenRouterOfficial | Qwen: Qwen3.5 Plus 2026-02-15 | $0.26/M in | prompt: 0.00000026 / token (endpoint alibaba) | |
| ReplicatePlatform-hosted | perceptron-ai-inc/isaac-0.1 | $0.26/M in | $0.26 per million input tokens | |
| ReplicatePlatform-hosted | qwen/qwen3-235b-a22b-instruct-2507 | $0.264/M in | $0.264 per million input tokens | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3.1 Terminus | $0.27/M in | prompt: 0.00000027 / token (endpoint siliconflow/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3.2 Exp | $0.27/M in | prompt: 0.00000027 / token (endpoint siliconflow/fp8) | |
| OpenRouterThird-party | MiniMax: MiniMax M2.5via Venice | $0.27/M in | prompt: 0.00000027 / token (endpoint venice) | |
| OpenRouterThird-party | Qwen: Qwen3.5-27Bvia AtlasCloud · fp8 | $0.27/M in | prompt: 0.00000027 / token (endpoint atlas-cloud/fp8) | |
| KIENot disclosed | Claude-Haiku-4-5 | $0.275/M in | 55 credits per million tokens ($0.275)Claims official or Fal price $1/M in | |
| AibermNot disclosed | GPT-5.1 Codex | $0.276/M in | model_ratio 0.6 × $2/M · group default ×0.23Claims official price $1.25/M in | |
| AibermNot disclosed | GPT-5.1 Codex Max | $0.276/M in | model_ratio 0.6 × $2/M · group default ×0.23Claims official price $1.25/M in | |
| AibermNot disclosed | GPT-5.2 Codex | $0.276/M in | model_ratio 0.6 × $2/M · group default ×0.23 | |
| AibermNot disclosed | GPT-5 Codex | $0.276/M in | model_ratio 0.6 × $2/M · group default ×0.23Claims official price $1.25/M in | |
| AibermNot disclosed | GPT-5.1 Codex | $0.276/M in | model_ratio 0.6 × $2/M · group default ×0.23Claims official price $1.25/M in | |
| AibermNot disclosed | GPT-5.1 Codex Max | $0.276/M in | model_ratio 0.6 × $2/M · group default ×0.23Claims official price $1.25/M in | |
| AibermNot disclosed | GPT-5.2 Codex | $0.276/M in | model_ratio 0.6 × $2/M · group default ×0.23Claims official price $1.75/M in | |
| ReplicateOfficial partner | qwen/qwen3-7-plus≤ 256 · 000 | $0.276/M in | $0.276 per million input tokens (input token ≤ 256,000) | |
| OpenRouterThird-party | Qwen: Qwen3 VL 30B A3B Thinking | $0.29/M in | prompt: 0.00000029 / token (endpoint siliconflow/fp8) | |
| AibermNot disclosed | Qwen3.7 Plus | $0.299/M in | model_ratio 0.65 × $2/M · group default ×0.23Claims official price $0.4/M in | |
| KIENot disclosed | gpt-6-1-terra | $0.3/M in | 60 credits per million tokens ($0.3)Claims official or Fal price $1/M in | |
| OpenRouterOfficial | Amazon: Nova 2 Litevia Amazon Bedrock | $0.3/M in | prompt: 0.0000003 / token (endpoint amazon-bedrock) | |
| OpenRouterOfficial | Cohere: Command A+ | $0.3/M in | prompt: 0.0000003 / token (endpoint cohere/fp8) | |
| OpenRouterOfficial | Google: Gemini 2.5 FlashImage inputvia Google AI Studio | $0.3/M in | image: 0.0000003 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 2.5 Flashvia Google AI Studio | $0.3/M in | prompt: 0.0000003 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 2.5 Flash LiteAudio inputvia Google AI Studio | $0.3/M in | audio: 0.0000003 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.5 Flash LiteAudio inputvia Google AI Studio | $0.3/M in | audio: 0.0000003 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.5 Flash LiteImage inputvia Google AI Studio | $0.3/M in | image: 0.0000003 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.5 Flash Litevia Google AI Studio | $0.3/M in | prompt: 0.0000003 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Mancer: Weaver (alpha) | $0.3/M in | prompt: 0.0000003 / token (endpoint mancer/fp8) | |
| OpenRouterThird-party | Meituan: LongCat 2.0 | $0.3/M in | prompt: 0.0000003 / token (endpoint atlas-cloud/fp8) | |
| OpenRouterThird-party | Meta: Muse Glimmer 30B | $0.3/M in | prompt: 0.0000003 / token (endpoint deepinfra/bf16) | |
| OpenRouterOfficial | Mistral: Codestral 2508via Mistral | $0.3/M in | prompt: 0.0000003 / token (endpoint mistral) | |
| OpenRouterThird-party | Moondream: Moondream 3 Preview | $0.3/M in | prompt: 0.0000003 / token (endpoint primeintellect/fp8) | |
| OpenRouterThird-party | Moondream: Moondream 3.1 | $0.3/M in | prompt: 0.0000003 / token (endpoint primeintellect/fp8) | |
| OpenRouterNot disclosed | Motif Technologies: Motif 3 | $0.3/M in | prompt: 0.0000003 / token (endpoint kt) | |
| OpenRouterThird-party | Qwen: Qwen3 Coder 480B A35BTurbovia DeepInfra | $0.3/M in | prompt: 0.0000003 / token (endpoint deepinfra/turbo) | |
| OpenRouterOfficial | Qwen: Qwen3.5 Plus 2026-04-20 | $0.3/M in | prompt: 0.0000003 / token (endpoint alibaba) | |
| OpenRouterThird-party | TheDrummer: Cydonia 24B V4.1 | $0.3/M in | prompt: 0.0000003 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | ReMM SLERP 13B | $0.3/M in | prompt: 0.0000003 / token (endpoint mancer/fp8) | |
| OpenRouterThird-party | Z.ai: GLM 4.6Vvia Novita · bf16 | $0.3/M in | prompt: 0.0000003 / token (endpoint novita/bf16) | |
| ReplicateOfficial partner | google/gemini-2.5-flash | $0.3/M in | $0.30 per million input tokens | |
| RunwareNot disclosed | Gemini 3.5 Flash-Lite | $0.3/M in | $3e-7 / inputToken | |
| RunwareNot disclosed | MiniMax M2.7 | $0.3/M in | $3e-7 / inputToken | |
| RunwareNot disclosed | MiniMax M3≤ 512K context | $0.3/M in | $3e-7 / inputToken · ≤ 512K context | |
| AibermNot disclosed | Claude Sonnet 5 | $0.3/M in | model_ratio 0.6522 × $2/M · group default ×0.23Claims official price $2/M in | |
| AibermNot disclosed | Claude Sonnet 5.5 | $0.3/M in | model_ratio 0.6522 × $2/M · group default ×0.23Claims official price $2/M in | |
| APIMartNot disclosed | babbage-002 | $0.32/M in | Input $0.32 / Output $0.32 · Per 1M tokens | |
| APIMartNot disclosed | gpt-4.1-mini | $0.32/M in | Input $0.32 / Output $1.28 · Per 1M tokens | |
| APIMartNot disclosed | gpt-4.1-mini-2025-04-14 | $0.32/M in | Input $0.32 / Output $1.28 · Per 1M tokens | |
| OpenRouterOfficial | Qwen: Qwen3.7 Plusvia Alibaba | $0.32/M in | prompt: 0.00000032 / token (endpoint alibaba) | |
| AibermNot disclosed | GPT-5.6 Terra | $0.325/M in | model_ratio 0.7065 × $2/M · group default ×0.23Claims official price $2.5/M in | |
| OpenRouterOfficial | Qwen: Qwen3 Coder FlashPrompt > 32K | $0.325/M in | prompt: 0.000000325 / token (>32000; endpoint alibaba) | |
| OpenRouterOfficial | Qwen: Qwen3.5 Plus 2026-02-15Prompt > 256K | $0.325/M in | prompt: 0.000000325 / token (>256000; endpoint alibaba) |
