11,195 prices on 4,854 listings · last collected 12 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 701–800 of 3,235
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterThird-party | Nous: Hermes 4 405B | $1/M in | prompt: 0.000001 / token (endpoint nebius/fp8) | |
| OpenRouterOfficial partner | OpenAI: GPT-3.5 Turbo (older v0613) | $1/M in | prompt: 0.000001 / token (endpoint azure) | |
| OpenRouterOfficial | OpenAI: GPT-4.1 (batch) | $1/M in | prompt: 0.000001 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-5.6 Terra Pro (batch) | $1/M in | prompt: 0.000001 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-5.6 Terra (batch) | $1/M in | prompt: 0.000001 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6 Sol Pro (batch) | $1/M in | prompt: 0.000001 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6 Sol (batch) | $1/M in | prompt: 0.000001 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Sol Pro (batch) | $1/M in | prompt: 0.000001 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Sol (batch) | $1/M in | prompt: 0.000001 / token (endpoint openai) | |
| OpenRouterOfficial partner | OpenAI: GPT-6.1 Terravia Azure | $1/M in | prompt: 0.000001 / token (endpoint azure) | |
| OpenRouterOfficial partner | OpenAI: GPT-6.1 Terra Provia Azure | $1/M in | prompt: 0.000001 / token (endpoint azure) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Terra Pro (batch)Prompt > 272K | $1/M in | prompt: 0.000001 / token (>272000; endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6.1 Terra (batch)Prompt > 272K | $1/M in | prompt: 0.000001 / token (>272000; endpoint openai) | |
| OpenRouterOfficial | OpenAI: o3 (batch) | $1/M in | prompt: 0.000001 / token (endpoint openai) | |
| OpenRouterOfficial | Perplexity: Sonar | $1/M in | prompt: 0.000001 / token (endpoint perplexity) | |
| OpenRouterOfficial | Relace: Relace Search | $1/M in | prompt: 0.000001 / token (endpoint relace/bf16) | |
| OpenRouterThird-party | StepFun: Step 5 Previewvia StepFun · fp8 | $1/M in | prompt: 0.000001 / token (endpoint stepfun/fp8) | |
| OpenRouterThird-party | Thinking Machines: Inkling | $1/M in | prompt: 0.000001 / token (endpoint together) | |
| OpenRouterOfficial | SpaceXAI: Grok 4.3 (batch) | $1/M in | prompt: 0.000001 / token (endpoint xai) | |
| OpenRouterOfficial | SpaceXAI: Grok Build 0.1via xAI | $1/M in | prompt: 0.000001 / token (endpoint xai) | |
| OpenRouterNot disclosed | OpenAI: GPT Terra Latest | $1/M in | prompt: 0.000001 / token | |
| ReplicateOfficial partner | anthropic/claude-4.5-haiku | $1/M in | $1 per million input tokens | |
| ReplicateOfficial partner | openai/gpt-5.6-luna | $1/M in | $1 per million input tokens | |
| RunwareNot disclosed | Claude Haiku 4.5 | $1/M in | $0.000001 / inputToken | |
| RunwareNot disclosed | Gemini 3 Flash | $1/M in | $0.000001 / inputToken · audio | |
| RunwareNot disclosed | GPT-6.1 Terra≤ 272K context | $1/M in | $0.000001 / inputToken · ≤ 272K context | |
| AibermNot disclosed | Kimi K3 | $1.058/M in | model_ratio 2.3 × $2/M · group default ×0.23Claims official price $3/M in | |
| AibermNot disclosed | GLM-5.2 | $1.104/M in | model_ratio 2.4 × $2/M · group default ×0.23Claims official price $1.4/M in | |
| AibermNot disclosed | GLM-5.3 | $1.104/M in | model_ratio 2.4 × $2/M · group default ×0.23Claims official price $1.4/M in | |
| APIMartNot disclosed | glm-5.3 | $1.12/M in | Input $1.12 / Output $3.52 · Per 1M tokens | |
| OpenRouterOfficial | Baidu: ERNIE-Light-DT-1.0 | $1.13/M in | prompt: 0.00000113 / token (endpoint baidu) | |
| OpenRouterOfficial | Qwen: Qwen3.8 Max (0902) (batch) | $1.15/M in | prompt: 0.00000115 / token (endpoint alibaba) | |
| APIMartNot disclosed | gemini-3.5-flash | $1.2/M in | Input $1.2 / Output $7.2 · Per 1M tokens | |
| APIMartNot disclosed | gemini-3.6-flash | $1.2/M in | Input $1.2 / Output $6 · Per 1M tokens | |
| APIMartNot disclosed | gpt-3.5-turbo-0613 | $1.2/M in | Input $1.2 / Output $2.4 · Per 1M tokens | |
| APIMartNot disclosed | gpt-3.5-turbo-instruct | $1.2/M in | Input $1.2 / Output $1.596 · Per 1M tokens | |
| OpenRouterOfficial | Z.ai: GLM 5 Turbo | $1.2/M in | prompt: 0.0000012 / token (endpoint z-ai) | |
| OpenRouterOfficial | Z.ai: GLM 5V Turbo | $1.2/M in | prompt: 0.0000012 / token (endpoint z-ai/fp8) | |
| RunwareNot disclosed | GLM-5.3 | $1.2/M in | $0.0000012 / inputToken | |
| OpenRouterOfficial | Google: Gemini 2.5 ProAudio inputvia Google AI Studio | $1.25/M in | audio: 0.00000125 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 2.5 ProImage inputvia Google AI Studio | $1.25/M in | image: 0.00000125 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 2.5 Provia Google AI Studio | $1.25/M in | prompt: 0.00000125 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 2.5 Pro Preview 06-05Audio inputvia Google AI Studio | $1.25/M in | audio: 0.00000125 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 2.5 Pro Preview 06-05Image inputvia Google AI Studio | $1.25/M in | image: 0.00000125 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 2.5 Pro Preview 06-05via Google AI Studio | $1.25/M in | prompt: 0.00000125 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Meta: Muse Spark 1.1 | $1.25/M in | prompt: 0.00000125 / token (endpoint meta) | |
| OpenRouterOfficial | Meta: Muse Spark 1.2 | $1.25/M in | prompt: 0.00000125 / token (endpoint meta) | |
| OpenRouterThird-party | Meta: Muse Spark 1.3via Google · global | $1.25/M in | prompt: 0.00000125 / token (endpoint google-vertex/global) | |
| OpenRouterThird-party | Meta: Muse Spark Openvia Modal | $1.25/M in | prompt: 0.00000125 / token (endpoint modal) | |
| OpenRouterOfficial | OpenAI: GPT-4o (batch) | $1.25/M in | prompt: 0.00000125 / token (endpoint openai) | |
| OpenRouterOfficial partner | OpenAI: GPT-5via Azure | $1.25/M in | prompt: 0.00000125 / token (endpoint azure) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.1via Azure | $1.25/M in | prompt: 0.00000125 / token (endpoint azure) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.1-Codex | $1.25/M in | prompt: 0.00000125 / token (endpoint azure) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.1-Codex-Max | $1.25/M in | prompt: 0.00000125 / token (endpoint azure) | |
| OpenRouterOfficial | OpenAI: GPT-5.4 (batch) | $1.25/M in | prompt: 0.00000125 / token (endpoint openai) | |
| OpenRouterOfficial | SpaceXAI: Grok 4.20via xAI · zdr | $1.25/M in | prompt: 0.00000125 / token (endpoint xai/zdr) | |
| OpenRouterOfficial | SpaceXAI: Grok 4.20 Multi-Agentvia xAI · zdr | $1.25/M in | prompt: 0.00000125 / token (endpoint xai/zdr) | |
| OpenRouterOfficial | SpaceXAI: Grok 4.3via xAI · zdr | $1.25/M in | prompt: 0.00000125 / token (endpoint xai/zdr) | |
| ReplicateOfficial partner | openai/gpt-5 | $1.25/M in | $1.25 per million input tokens | |
| ReplicateOfficial partner | openai/gpt-5-structuredgpt-5 | $1.25/M in | $1.25 per million input tokens (gpt-5) | |
| ReplicateOfficial partner | openai/gpt-5.1 | $1.25/M in | $1.25 per million input tokens | |
| RunwareNot disclosed | Grok 4.3 | $1.25/M in | $0.00000125 / inputToken | |
| AibermNot disclosed | GPT-6 Astra | $1.3/M in | model_ratio 2.826 × $2/M · group default ×0.23Claims official price $10/M in | |
| OpenRouterOfficial | Qwen: Qwen3.6 PlusPrompt > 256K | $1.3/M in | prompt: 0.0000013 / token (>256000; endpoint alibaba) | |
| APIMartNot disclosed | qwen3.7-max | $1.371/M in | Input $1.3714 / Output $4.1141 · Per 1M tokens | |
| APIMartNot disclosed | qwen3.8-2.4t-a95b | $1.371/M in | Input $1.3714 / Output $4.1143 · Per 1M tokens | |
| APIMartNot disclosed | qwen3.8-max | $1.371/M in | Input $1.3714 / Output $4.1143 · Per 1M tokens | |
| APIMartNot disclosed | qwen3.8-max-0902 | $1.371/M in | Input $1.3714 / Output $4.1143 · Per 1M tokens | |
| APIMartNot disclosed | gpt-5.2 | $1.4/M in | Input $1.4 / Output $11.2 · Per 1M tokens | |
| APIMartNot disclosed | gpt-5.2-chat-latest | $1.4/M in | Input $1.4 / Output $11.2 · Per 1M tokens | |
| APIMartNot disclosed | gpt-5.2-codex | $1.4/M in | Input $1.4 / Output $11.2 · Per 1M tokens | |
| APIMartNot disclosed | gpt-5.3-codex | $1.4/M in | Input $1.4 / Output $11.2 · Per 1M tokens | |
| KIENot disclosed | gpt-5.5 | $1.4/M in | 280 credits per million tokens ($1.4)Claims official or Fal price $5/M in | |
| KIENot disclosed | gpt-5.6-sol | $1.4/M in | 280 credits per million tokens ($1.4)Claims official or Fal price $5/M in | |
| RunwareNot disclosed | GLM-5.1 | $1.4/M in | $0.0000014 / inputToken | |
| KIENot disclosed | claude-opus-4-5 | $1.425/M in | 285 credits per million tokens ($1.425)Claims official or Fal price $5/M in | |
| KIENot disclosed | Claude-Opus-4-6 | $1.425/M in | 285 credits per million tokens ($1.425)Claims official or Fal price $5/M in | |
| KIENot disclosed | Claude-Opus-4-7 | $1.425/M in | 285 credits per million tokens ($1.425)Claims official or Fal price $5/M in | |
| AibermNot disclosed | Claude Sonnet 5 | $1.44/M in | model_ratio 3.1304 × $2/M · group default ×0.23Claims official price $2/M in | |
| AibermNot disclosed | Claude Sonnet 5.5 | $1.44/M in | model_ratio 3.1304 × $2/M · group default ×0.23Claims official price $2/M in | |
| ReplicatePlatform-hosted | deepseek-ai/deepseek-v3 | $1.45/M in | $1.45 per million input tokens | |
| AibermNot disclosed | Claude Opus | $1.467/M in | model_ratio 3.19 × $2/M · group default ×0.23Claims official price $5/M in | |
| OpenRouterOfficial | Qwen: Qwen3.7 Maxvia Alibaba | $1.475/M in | prompt: 0.000001475 / token (endpoint alibaba) | |
| APIMartNot disclosed | kimi-k2.7-code-highspeed | $1.486/M in | Input $1.4858 / Output $6.1659 · Per 1M tokens | |
| OpenRouterOfficial | Anthropic: Claude Sonnet 4.5 (batch) | $1.5/M in | prompt: 0.0000015 / token (endpoint anthropic) | |
| OpenRouterOfficial | Anthropic: Claude Sonnet 4.6 (batch) | $1.5/M in | prompt: 0.0000015 / token (endpoint anthropic) | |
| OpenRouterOfficial | Google: Gemini 3.5 FlashImage inputvia Google · global | $1.5/M in | image: 0.0000015 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.5 Flashvia Google · global | $1.5/M in | prompt: 0.0000015 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.5 Flash (batch)Audio input | $1.5/M in | audio: 0.0000015 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini Omni 1.1 Flash | $1.5/M in | prompt: 0.0000015 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini Omni 1.2 Flash | $1.5/M in | prompt: 0.0000015 / token (endpoint google-ai-studio) | |
| OpenRouterOfficial | Mistral: Mistral Medium 3.5via Mistral · zdr | $1.5/M in | prompt: 0.0000015 / token (endpoint mistral/zdr) | |
| ReplicateOfficial partner | google/gemini-3.5-flash | $1.5/M in | $1.50 per million input tokens | |
| RunwareNot disclosed | Gemini 3.5 Flash | $1.5/M in | $0.0000015 / inputToken | |
| RunwareNot disclosed | Gemini 3.6 Flash | $1.5/M in | $0.0000015 / inputToken | |
| APIMartNot disclosed | claude-sonnet-5 | $1.6/M in | Input $1.6 / Output $8 · Per 1M tokens | |
| APIMartNot disclosed | claude-sonnet-5-5 | $1.6/M in | Input $1.6 / Output $8 · Per 1M tokens | |
| APIMartNot disclosed | davinci-002 | $1.6/M in | Input $1.6 / Output $1.6 · Per 1M tokens | |
| APIMartNot disclosed | gemini-3-pro-preview | $1.6/M in | Input $1.6 / Output $9.6 · Per 1M tokens | |
| APIMartNot disclosed | gemini-3-pro-preview-thinking | $1.6/M in | Input $1.6 / Output $9.6 · Per 1M tokens |
