8,429 prices on 4,154 listings · last collected 5 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 501–600 of 859
Per million output tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | Sakana: Sakana Namazu | $4/M out | completion: 0.000004 / token | |
| OpenRouter | SpaceXAI: Grok 4.3 (batch)Prompt > 200K | $4/M out | completion: 0.000004 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok Build 0.1Prompt > 200K | $4/M out | completion: 0.000004 / token (>200000) | |
| OpenRouter | Z.ai: GLM 5 Turbo | $4/M out | completion: 0.000004 / token | |
| OpenRouter | Z.ai: GLM 5V Turbo | $4/M out | completion: 0.000004 / token | |
| Replicate | moonshotai/kimi-k2.6 | $4/M out | $4 per million output tokens | |
| OpenRouter | Thinking Machines: Inkling | $4.05/M out | completion: 0.00000405 / token | |
| APIMart | qwen3.7-max | $4.1141/M out | Input $1.3714 / Output $4.1141 · Per 1M tokens | |
| APIMart | qwen3.8-2.4t-a95b | $4.1143/M out | Input $1.3714 / Output $4.1143 · Per 1M tokens | |
| APIMart | qwen3.8-max | $4.1143/M out | Input $1.3714 / Output $4.1143 · Per 1M tokens | |
| APIMart | qwen3.8-max-0902 | $4.1143/M out | Input $1.3714 / Output $4.1143 · Per 1M tokens | |
| OpenRouter | Google: Gemini 3.8 Flash | $4.125/M out | completion: 0.000004125 / token | |
| OpenRouter | Google: Gemini 3.8 FlashReasoning | $4.125/M out | internal_reasoning: 0.000004125 / token | |
| OpenRouter | Meta: Muse Spark 1.1 | $4.25/M out | completion: 0.00000425 / token | |
| OpenRouter | Meta: Muse Spark 1.2 | $4.25/M out | completion: 0.00000425 / token | |
| OpenRouter | Meta: Muse Spark 1.3 | $4.25/M out | completion: 0.00000425 / token | |
| OpenRouter | Meta: Muse Spark Open | $4.25/M out | completion: 0.00000425 / token | |
| kie.ai | claude-sonnet-4-5 | $4.275/M out | 855 credits per 1M tokens ($4.275)Claims fal charges $15/M out | |
| kie.ai | Claude-Sonnet-4-6 | $4.275/M out | 855 credits per million tokens ($4.275)Claims fal charges $15/M out | |
| kie.ai | claude-sonnet-5 | $4.275/M out | 855 credits per million tokens ($4.275)Claims fal charges $10/M out | |
| OpenRouter | Z.ai: GLM 5.1 | $4.4/M out | completion: 0.0000044 / token | |
| OpenRouter | Qwen: Qwen3.7 Max | $4.425/M out | completion: 0.000004425 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Pro 0813 | $4.44/M out | completion: 0.00000444 / token | |
| OpenRouter | Google: Gemini 3.5 Flash (batch) | $4.5/M out | completion: 0.0000045 / token | |
| OpenRouter | Google: Gemini 3.5 Flash (batch)Reasoning | $4.5/M out | internal_reasoning: 0.0000045 / token | |
| OpenRouter | OpenAI: GPT-5.4 Mini | $4.5/M out | completion: 0.0000045 / token | |
| OpenRouter | OpenAI: GPT Mini Latest | $4.5/M out | completion: 0.0000045 / token | |
| APIMart | grok-4.5 | $4.8/M out | Input $1.6 / Output $4.8 · Per 1M tokens | |
| APIMart | grok-4.6 | $4.8/M out | Input $1.6 / Output $4.8 · Per 1M tokens | |
| APIMart | grok-4.7 | $4.8/M out | Input $1.6 / Output $4.8 · Per 1M tokens | |
| OpenRouter | SpaceXAI: Grok 4.6 (batch) | $4.8/M out | completion: 0.0000048 / token | |
| OpenRouter | SpaceXAI: Grok 4.7 (batch) | $4.8/M out | completion: 0.0000048 / token | |
| Replicate | ibm-granite/granite-speech-3.3-8b | $4.9/M out | $4.90 per million output tokens | |
| OpenRouter | Magnum v4 72B | $5/M out | completion: 0.000005 / token | |
| OpenRouter | Anthropic: Claude Haiku 4.5 | $5/M out | completion: 0.000005 / token | |
| OpenRouter | Anthropic: Claude Sonnet 5.5 (batch) | $5/M out | completion: 0.000005 / token | |
| OpenRouter | Anthropic: Claude Sonnet 5 (batch) | $5/M out | completion: 0.000005 / token | |
| OpenRouter | Google: Gemini 4 Argon (batch) | $5/M out | completion: 0.000005 / token | |
| OpenRouter | Google: Gemini 4 Argon (batch)Reasoning | $5/M out | internal_reasoning: 0.000005 / token | |
| OpenRouter | OpenAI: GPT-4o (batch) | $5/M out | completion: 0.000005 / token | |
| OpenRouter | OpenAI: GPT-5.1 (batch) | $5/M out | completion: 0.000005 / token | |
| OpenRouter | OpenAI: GPT-5 (batch) | $5/M out | completion: 0.000005 / token | |
| OpenRouter | OpenAI: GPT-6 Sol Pro (batch) | $5/M out | completion: 0.000005 / token | |
| OpenRouter | OpenAI: GPT-6 Sol (batch) | $5/M out | completion: 0.000005 / token | |
| OpenRouter | OpenAI: GPT-6.1 Sol Pro (batch) | $5/M out | completion: 0.000005 / token | |
| OpenRouter | OpenAI: GPT-6.1 Sol (batch) | $5/M out | completion: 0.000005 / token | |
| OpenRouter | OpenAI: GPT-6.1 Terra | $5/M out | completion: 0.000005 / token | |
| OpenRouter | OpenAI: GPT-6.1 Terra Pro | $5/M out | completion: 0.000005 / token | |
| OpenRouter | SpaceXAI: Grok 4.20Prompt > 200K | $5/M out | completion: 0.000005 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.20 Multi-AgentPrompt > 200K | $5/M out | completion: 0.000005 / token (>200000) | |
| OpenRouter | SpaceXAI: Grok 4.3Prompt > 200K | $5/M out | completion: 0.000005 / token (>200000) | |
| OpenRouter | OpenAI: GPT Terra Latest | $5/M out | completion: 0.000005 / token | |
| Replicate | anthropic/claude-3.5-haiku | $5/M out | $5 per million output tokens | |
| Replicate | anthropic/claude-4.5-haiku | $5/M out | $5 per million output tokens | |
| Replicate | openai/gpt-4o-mini-transcribe | $5/M out | $5 per million output tokens | |
| APIMart | gemini-3.6-flash | $6/M out | Input $1.2 / Output $6 · Per 1M tokens | |
| OpenRouter | AionLabs: Aion-3.0 | $6/M out | completion: 0.000006 / token | |
| OpenRouter | AionLabs: Aion 3.5 | $6/M out | completion: 0.000006 / token | |
| OpenRouter | ByteDance Seed: Seed-2.0-CodePrompt > 128K | $6/M out | completion: 0.000006 / token (>128000) | |
| OpenRouter | Google: Gemini 3.1 Pro Preview (batch) | $6/M out | completion: 0.000006 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview (batch)Reasoning | $6/M out | internal_reasoning: 0.000006 / token | |
| OpenRouter | Mistral Large | $6/M out | completion: 0.000006 / token | |
| OpenRouter | Mistral Large 2407 | $6/M out | completion: 0.000006 / token | |
| OpenRouter | Mistral: Mixtral 8x22B Instruct | $6/M out | completion: 0.000006 / token | |
| OpenRouter | MoonshotAI: Kimi K3 (batch) | $6/M out | completion: 0.000006 / token | |
| OpenRouter | OpenAI: GPT-5.6 Terra Pro (batch) | $6/M out | completion: 0.000006 / token | |
| OpenRouter | OpenAI: GPT-5.6 Terra (batch) | $6/M out | completion: 0.000006 / token | |
| OpenRouter | Qwen: Qwen3.8 2.4T A95B | $6/M out | completion: 0.000006 / token | |
| OpenRouter | Qwen: Qwen3.8 Max (0902) | $6/M out | completion: 0.000006 / token | |
| OpenRouter | Sakana: Fugu Max | $6/M out | completion: 0.000006 / token | |
| OpenRouter | Writer: Palmyra X5 | $6/M out | completion: 0.000006 / token | |
| OpenRouter | SpaceXAI: Grok 4.5 | $6/M out | completion: 0.000006 / token | |
| OpenRouter | SpaceXAI: Grok 4.6 | $6/M out | completion: 0.000006 / token | |
| OpenRouter | SpaceXAI: Grok 4.7 | $6/M out | completion: 0.000006 / token | |
| OpenRouter | xAI: Grok Latest | $6/M out | completion: 0.000006 / token | |
| Replicate | google/gemini-3.8-flash-lite-tts | $6/M out | $6 per million output tokens | |
| Replicate | openai/gpt-5.6-luna | $6/M out | $6 per million output tokens | |
| APIMart | kimi-k2.7-code-highspeed | $6.1659/M out | Input $1.4858 / Output $6.1659 · Per 1M tokens | |
| APIMart | gpt-4.1 | $6.4/M out | Input $1.6 / Output $6.4 · Per 1M tokens | |
| APIMart | gpt-4.1-2025-04-14 | $6.4/M out | Input $1.6 / Output $6.4 · Per 1M tokens | |
| APIMart | o3 | $6.4/M out | Input $1.6 / Output $6.4 · Per 1M tokens | |
| APIMart | o3-2025-04-16 | $6.4/M out | Input $1.6 / Output $6.4 · Per 1M tokens | |
| APIMart | o4-mini-deep-research | $6.4/M out | Input $1.6 / Output $6.4 · Per 1M tokens | |
| APIMart | o4-mini-deep-research-2025-06-26 | $6.4/M out | Input $1.6 / Output $6.4 · Per 1M tokens | |
| OpenRouter | Z.ai: GLM 5.2 | $6.8/M out | completion: 0.0000068 / token | |
| OpenRouter | OpenAI: GPT-5.2 (batch) | $7/M out | completion: 0.000007 / token | |
| kie.ai | claude-opus-4-5 | $7.15/M out | 1430 credits per million tokens ($7.150)Claims fal charges $25/M out | |
| kie.ai | Claude-Opus-4-6 | $7.15/M out | 1430 credits per million tokens ($7.150)Claims fal charges $25/M out | |
| kie.ai | Claude-Opus-4-7 | $7.15/M out | 1430 credits per million tokens ($7.150)Claims fal charges $25/M out | |
| APIMart | gemini-3.5-flash | $7.2/M out | Input $1.2 / Output $7.2 · Per 1M tokens | |
| APIMart | gpt-3.5-turbo-16k | $7.2/M out | Input $2.4 / Output $7.2 · Per 1M tokens | |
| APIMart | gpt-3.5-turbo-16k-0613 | $7.2/M out | Input $2.4 / Output $7.2 · Per 1M tokens | |
| OpenRouter | Anthropic: Claude Sonnet 4.5 (batch) | $7.5/M out | completion: 0.0000075 / token | |
| OpenRouter | Anthropic: Claude Sonnet 4.6 (batch) | $7.5/M out | completion: 0.0000075 / token | |
| OpenRouter | Mistral: Mistral Medium 3.5 | $7.5/M out | completion: 0.0000075 / token | |
| OpenRouter | OpenAI: GPT-5.4 (batch) | $7.5/M out | completion: 0.0000075 / token | |
| OpenRouter | OpenAI: GPT-6 Sol Pro (batch)Prompt > 272K | $7.5/M out | completion: 0.0000075 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Sol (batch)Prompt > 272K | $7.5/M out | completion: 0.0000075 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6.1 Sol Pro (batch)Prompt > 272K | $7.5/M out | completion: 0.0000075 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6.1 Sol (batch)Prompt > 272K | $7.5/M out | completion: 0.0000075 / token (>272000) |
