8,429 prices on 4,154 listings · last collected 6 h ago · 36 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on six 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.
Model
Gemini 
Claude 
Qwen 
DeepSeek 
GLM 
Llama 
Mistral 
Kimi 
MiniMax 
Nemotron 
Hunyuan Unit
All 2,608Per second of output 5Per image 32Per million input tokens 866Per million output tokens 859Per million tokens 5Per million cached input tokens (read) 425Per million cache-write tokens 188Per thousand characters 2Per second of compute time 12Per run (default parameters) 200Other units (see the platform’s wording) 14
Showing 601–700 of 859
Per million output tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | OpenAI: GPT-6.1 TerraPrompt > 272K | $7.5/M out | completion: 0.0000075 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6.1 Terra ProPrompt > 272K | $7.5/M out | completion: 0.0000075 / token (>272000) | |
| OpenRouter | Pareto 26.9 | $7.5/M out | completion: 0.0000075 / token | |
| OpenRouter | OpenAI: GPT Terra LatestPrompt > 272K | $7.5/M out | completion: 0.0000075 / token (>272000) | |
| APIMart | GPT-4o | $8/M out | Input $2 / Output $8 · Per 1M tokens | |
| APIMart | claude-sonnet-5 | $8/M out | Input $1.6 / Output $8 · Per 1M tokens | |
| APIMart | claude-sonnet-5-5 | $8/M out | Input $1.6 / Output $8 · Per 1M tokens | |
| APIMart | gemini-4-argon | $8/M out | Input $1.6 / Output $8 · Per 1M tokens | |
| APIMart | gpt-4-32k | $8/M out | Input $2 / Output $8 · Per 1M tokens | |
| APIMart | gpt-4-32k-0613 | $8/M out | Input $2 / Output $8 · Per 1M tokens | |
| APIMart | gpt-4-vision-preview | $8/M out | Input $2 / Output $8 · Per 1M tokens | |
| APIMart | gpt-4o-2024-11-20 | $8/M out | Input $2 / Output $8 · Per 1M tokens | |
| APIMart | gpt-4o-transcribe | $8/M out | Input $2 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5 | $8/M out | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5-2025-08-07 | $8/M out | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5-chat-latest | $8/M out | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5-codex | $8/M out | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5-search-api | $8/M out | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5-search-api-2025-10-14 | $8/M out | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5.1 | $8/M out | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5.1-2025-11-13 | $8/M out | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5.1-chat-latest | $8/M out | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5.1-codex | $8/M out | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5.1-codex-max | $8/M out | Input $1 / Output $8 · Per 1M tokens | |
| APIMart | gpt-6-sol | $8/M out | Input $1.6 / Output $8 · Per 1M tokens | |
| APIMart | gpt-6.1-sol | $8/M out | Input $1.6 / Output $8 · Per 1M tokens | |
| kie.ai | claude-opus-5-5 | $8/M out | 1600 credits per million tokens ($8.00)Claims fal charges $20/M out | |
| OpenRouter | OpenAI: GPT-4.1 | $8/M out | completion: 0.000008 / token | |
| OpenRouter | OpenAI: o3 | $8/M out | completion: 0.000008 / token | |
| OpenRouter | Perplexity: Sonar Deep Research | $8/M out | completion: 0.000008 / token | |
| OpenRouter | Perplexity: Sonar Reasoning Pro | $8/M out | completion: 0.000008 / token | |
| OpenRouter | DeepSeek: DeepSeek Pro Latest | $8/M out | completion: 0.000008 / token | |
| Replicate | openai/gpt-4.1 | $8/M out | $8 per million output tokens | |
| kie.ai | gpt-5.5 | $8.4/M out | 1680 credits per million tokens ($8.4)Claims fal charges $30/M out | |
| kie.ai | gpt-5.6-sol | $8.4/M out | 1680 credits per million tokens ($8.4)Claims fal charges $30/M out | |
| OpenRouter | Xiaomi: MiMo-V2.6-Pro-UltraSpeed | $8.7/M out | completion: 0.0000087 / token | |
| OpenRouter | Z.ai: GLM 5.3 Prime | $8.8/M out | completion: 0.0000088 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview (batch)Prompt > 200K | $9/M out | completion: 0.000009 / token (>200000) | |
| OpenRouter | Google: Gemini 3.5 Flash | $9/M out | completion: 0.000009 / token | |
| OpenRouter | Google: Gemini 3.5 FlashReasoning | $9/M out | internal_reasoning: 0.000009 / token | |
| OpenRouter | OpenAI: GPT-5.6 Terra Pro (batch)Prompt > 272K | $9/M out | completion: 0.000009 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Terra (batch)Prompt > 272K | $9/M out | completion: 0.000009 / token (>272000) | |
| Replicate | google/gemini-3.5-flash | $9/M out | $9 per million output tokens | |
| Replicate | google/gemini-3.8-flash-tts | $9/M out | $9 per million output tokens | |
| APIMart | gemini-3-pro-preview | $9.6/M out | Input $1.6 / Output $9.6 · Per 1M tokens | |
| APIMart | gemini-3-pro-preview-thinking | $9.6/M out | Input $1.6 / Output $9.6 · Per 1M tokens | |
| APIMart | gemini-3.1-pro-preview | $9.6/M out | Input $1.6 / Output $9.6 · Per 1M tokens | |
| APIMart | gemini-3.1-pro-preview-thinking | $9.6/M out | Input $1.6 / Output $9.6 · Per 1M tokens | |
| APIMart | gpt-5.6-terra | $9.6/M out | Input $1.6 / Output $9.6 · Per 1M tokens | |
| OpenRouter | SpaceXAI: Grok 4.6 (batch)Prompt > 200K | $9.6/M out | completion: 0.0000096 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.7 (batch)Prompt > 200K | $9.6/M out | completion: 0.0000096 / token (>200000) | |
| kie.ai | Claude-Opus-4-8 | $10/M out | 2000 credits per 1M tokens ($10)Claims fal charges $25/M out | |
| kie.ai | claude-opus-5 | $10/M out | 2000 credits per million tokens ($10)Claims fal charges $25/M out | |
| OpenRouter | Anthropic: Claude Opus 5.5 (batch) | $10/M out | completion: 0.00001 / token | |
| OpenRouter | Anthropic: Claude Sonnet 5 | $10/M out | completion: 0.00001 / token | |
| OpenRouter | Anthropic: Claude Sonnet 5.5 | $10/M out | completion: 0.00001 / token | |
| OpenRouter | Cohere: Command A | $10/M out | completion: 0.00001 / token | |
| OpenRouter | Cohere: Command R+ (08-2024) | $10/M out | completion: 0.00001 / token | |
| OpenRouter | Google: Gemini 2.5 Pro | $10/M out | completion: 0.00001 / token | |
| OpenRouter | Google: Gemini 2.5 ProReasoning | $10/M out | internal_reasoning: 0.00001 / token | |
| OpenRouter | Google: Gemini 2.5 Pro Preview 06-05 | $10/M out | completion: 0.00001 / token | |
| OpenRouter | Google: Gemini 2.5 Pro Preview 06-05Reasoning | $10/M out | internal_reasoning: 0.00001 / token | |
| OpenRouter | Google: Gemini 4 Argon | $10/M out | completion: 0.00001 / token | |
| OpenRouter | Google: Gemini 4 ArgonReasoning | $10/M out | internal_reasoning: 0.00001 / token | |
| OpenRouter | MoonshotAI: Kimi K3.1 Pro | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-4o | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-4o (2024-08-06) | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-4o (2024-11-20) | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-5 | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-5.1 | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-5.1-Codex | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-5.1-Codex-Max | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol Pro (batch) | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol (batch) | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-6 Sol | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-6 Sol Pro | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-6.1 Sol | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT-6.1 Sol Pro | $10/M out | completion: 0.00001 / token | |
| OpenRouter | OpenAI: GPT Audio | $10/M out | completion: 0.00001 / token | |
| OpenRouter | Anthropic: Claude Sonnet Latest | $10/M out | completion: 0.00001 / token | |
| OpenRouter | Google: Gemini Pro Latest | $10/M out | completion: 0.00001 / token | |
| OpenRouter | Google: Gemini Pro LatestReasoning | $10/M out | internal_reasoning: 0.00001 / token | |
| OpenRouter | OpenAI: GPT Sol Latest | $10/M out | completion: 0.00001 / token | |
| Replicate | anthropic/claude-sonnet-5 | $10/M out | $0.01 per thousand output tokens | |
| Replicate | deepseek-ai/deepseek-r1 | $10/M out | $0.01 per thousand output tokens | |
| Replicate | openai/gpt-4o | $10/M out | $0.01 per thousand output tokens | |
| Replicate | openai/gpt-4o-transcribe | $10/M out | $0.01 per thousand output tokens | |
| Replicate | openai/gpt-5 | $10/M out | $0.01 per thousand output tokens | |
| Replicate | openai/gpt-5-structuredgpt-5 | $10/M out | $0.01 per thousand output tokens (gpt-5) | |
| Replicate | openai/gpt-5.1 | $10/M out | $0.01 per thousand output tokens | |
| Replicate | openai/gpt-5.6-sol | $10/M out | $0.01 per thousand output tokens | |
| Replicate | sourceful/riverflow-v2.5-fast | $10/M out | $0.01 per thousand output tokens | |
| Replicate | sourceful/riverflow-v2.5-pro | $10/M out | $0.01 per thousand output tokens | |
| OpenRouter | MoonshotAI: Kimi Latest | $10.5634/M out | completion: 0.0000105634 / token | |
| APIMart | gpt-5.2 | $11.2/M out | Input $1.4 / Output $11.2 · Per 1M tokens | |
| APIMart | gpt-5.2-chat-latest | $11.2/M out | Input $1.4 / Output $11.2 · Per 1M tokens | |
| APIMart | gpt-5.2-codex | $11.2/M out | Input $1.4 / Output $11.2 · Per 1M tokens | |
| APIMart | gpt-5.3-codex | $11.2/M out | Input $1.4 / Output $11.2 · Per 1M tokens | |
| OpenRouter | Anthropic: Claude Sonnet 4.5 (batch)Prompt > 200K | $11.25/M out | completion: 0.00001125 / token (>200000) | |
| OpenRouter | OpenAI: GPT-5.4 (batch)Prompt > 272K | $11.25/M out | completion: 0.00001125 / token (>272000) |
