8,429 prices on 4,154 listings · last collected 8 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 
Mistral 
Kimi 
Llama 
MiniMax 
Hunyuan 
Nemotron 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 2001–2100 of 2,608
Per million cached input tokens (read)100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| kie.ai | grok-4-5 | $0.12/M cache read | 24 credits per million tokens ($0.12)Claims fal charges $0.3/M cache read | |
| OpenRouter | NVIDIA: Nemotron 3 Ultra | $0.12/M cache read | input_cache_read: 0.00000012 / token | |
| OpenRouter | Qwen: Qwen3 VL 8B Instruct | $0.12/M cache read | input_cache_read: 0.00000012 / token | |
| OpenRouter | Anthropic: Claude Fable 5.1 (batch) | $0.125/M cache read | input_cache_read: 0.000000125 / token | |
| OpenRouter | Google: Gemini 2.5 Pro | $0.125/M cache read | input_audio_cache: 0.000000125 / token | |
| OpenRouter | Google: Gemini 2.5 Pro | $0.125/M cache read | input_cache_read: 0.000000125 / token | |
| OpenRouter | Google: Gemini 2.5 Pro Preview 06-05 | $0.125/M cache read | input_audio_cache: 0.000000125 / token | |
| OpenRouter | Google: Gemini 2.5 Pro Preview 06-05 | $0.125/M cache read | input_cache_read: 0.000000125 / token | |
| OpenRouter | OpenAI: GPT-5 | $0.125/M cache read | input_cache_read: 0.000000125 / token | |
| OpenRouter | OpenAI: GPT-5.1 | $0.125/M cache read | input_cache_read: 0.000000125 / token | |
| OpenRouter | OpenAI: GPT-5.1-Codex-Max | $0.125/M cache read | input_cache_read: 0.000000125 / token | |
| OpenRouter | OpenAI: GPT-5.4 (batch) | $0.125/M cache read | input_cache_read: 0.000000125 / token | |
| OpenRouter | DeepSeek: DeepSeek V3.1 | $0.13/M cache read | input_cache_read: 0.00000013 / token | |
| OpenRouter | DeepSeek: DeepSeek V3.2 | $0.13/M cache read | input_cache_read: 0.00000013 / token | |
| OpenRouter | OpenAI: GPT-5.1-Codex | $0.13/M cache read | input_cache_read: 0.00000013 / token | |
| OpenRouter | OpenAI: o4 Mini (batch) | $0.1375/M cache read | input_cache_read: 0.0000001375 / token | |
| kie.ai | gpt-5.5 | $0.14/M cache read | 28 credits per million tokens ($0.14)Claims fal charges $0.5/M cache read | |
| kie.ai | gpt-5.6-sol | $0.14/M cache read | 28 credits per million tokens ($0.14)Claims fal charges $0.5/M cache read | |
| OpenRouter | Anthropic: Claude Sonnet 4.5 (batch) | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | Anthropic: Claude Sonnet 4.6 (batch) | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | Cohere: Command A+ | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | Google: Gemini 3.5 Flash | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | Google: Gemini 3.5 Flash (batch) | $0.15/M cache read | input_audio_cache: 0.00000015 / token | |
| OpenRouter | Meta: Muse Spark 1.1 | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | Meta: Muse Spark 1.2 | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | Meta: Muse Spark 1.3 | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | Meta: Muse Spark Open | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | MoonshotAI: Kimi K2 Thinking | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | MoonshotAI: Kimi K2.6 | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | Sakana: Sakana Namazu | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | TheDrummer: Cydonia 24B V4.1 | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | MoonshotAI: Kimi Latest | $0.15/M cache read | input_cache_read: 0.00000015 / token | |
| OpenRouter | Qwen: Qwen-PlusPrompt > 256K | $0.156/M cache read | input_cache_read: 0.000000156 / token (>256000) | |
| OpenRouter | MoonshotAI: Kimi K2.7 Code | $0.16/M cache read | input_cache_read: 0.00000016 / token | |
| OpenRouter | SpaceXAI: Grok 4.3 (batch) | $0.16/M cache read | input_cache_read: 0.00000016 / token | |
| OpenRouter | Meta: Llama 4 Maverick | $0.17/M cache read | input_cache_read: 0.00000017 / token | |
| OpenRouter | Thinking Machines: Inkling | $0.17/M cache read | input_cache_read: 0.00000017 / token | |
| OpenRouter | OpenAI: GPT-5.2 | $0.175/M cache read | input_cache_read: 0.000000175 / token | |
| OpenRouter | OpenAI: GPT-5.2 Chat | $0.175/M cache read | input_cache_read: 0.000000175 / token | |
| OpenRouter | OpenAI: GPT-5.2-Codex | $0.175/M cache read | input_cache_read: 0.000000175 / token | |
| OpenRouter | OpenAI: GPT-5.3-Codex | $0.175/M cache read | input_cache_read: 0.000000175 / token | |
| OpenRouter | AionLabs: Aion-3.0-Mini | $0.18/M cache read | input_cache_read: 0.00000018 / token | |
| OpenRouter | AionLabs: Aion 3.5 Mini | $0.18/M cache read | input_cache_read: 0.00000018 / token | |
| OpenRouter | MoonshotAI: Kimi K3 | $0.182/M cache read | input_cache_read: 0.000000182 / token | |
| OpenRouter | Qwen: Qwen3.7 PlusPrompt > 256K | $0.192/M cache read | input_cache_read: 0.000000192 / token (>256000) | |
| kie.ai | grok-4-6 | $0.2/M cache read | 40 credits per million tokens ($0.20)Claims fal charges $0.5/M cache read | |
| kie.ai | grok-4-7 | $0.2/M cache read | 40 credits per million tokens ($0.20)Claims fal charges $0.5/M cache read | |
| OpenRouter | AionLabs: Aion-2.0 | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | Anthropic: Claude Opus 5.5 | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | Anthropic: Claude Sonnet 5 | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview | $0.2/M cache read | input_audio_cache: 0.0000002 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview Custom Tools | $0.2/M cache read | input_audio_cache: 0.0000002 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview Custom Tools | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | Meta: Muse Wonder | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | Mistral Large | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | Mistral Large 2407 | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | Mistral: Mixtral 8x22B Instruct | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | MoonshotAI: Kimi K3.1 Pro | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | Nous: Hermes 4 405B | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol Pro (batch) | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol (batch) | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Terra | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Terra Pro | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Terra Pro (batch)Prompt > 272K | $0.2/M cache read | input_cache_read: 0.0000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Terra (batch)Prompt > 272K | $0.2/M cache read | input_cache_read: 0.0000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Sol | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-6 Sol Pro | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-6 Sol Pro (batch)Prompt > 272K | $0.2/M cache read | input_cache_read: 0.0000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Sol (batch)Prompt > 272K | $0.2/M cache read | input_cache_read: 0.0000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6.1 SolPrompt > 272K | $0.2/M cache read | input_cache_read: 0.0000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6.1 Sol ProPrompt > 272K | $0.2/M cache read | input_cache_read: 0.0000002 / token (>272000) | |
| OpenRouter | SpaceXAI: Grok 4.20 | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | SpaceXAI: Grok 4.20 Multi-Agent | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | SpaceXAI: Grok 4.3 | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | SpaceXAI: Grok Build 0.1 | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | Z.ai: GLM 5 | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | Anthropic: Claude Opus Latest | $0.2/M cache read | input_cache_read: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT Sol LatestPrompt > 272K | $0.2/M cache read | input_cache_read: 0.0000002 / token (>272000) | |
| OpenRouter | MoonshotAI: Kimi K2.5 | $0.209/M cache read | input_cache_read: 0.000000209 / token | |
| OpenRouter | MoonshotAI: Kimi K3 (batch) | $0.226/M cache read | input_cache_read: 0.000000226 / token | |
| kie.ai | Kimi K3 | $0.24/M cache read | 48 credits per million tokens ($0.24)Claims fal charges $0.3/M cache read | |
| OpenRouter | Z.ai: GLM 5 Turbo | $0.24/M cache read | input_cache_read: 0.00000024 / token | |
| OpenRouter | Z.ai: GLM 5V Turbo | $0.24/M cache read | input_cache_read: 0.00000024 / token | |
| OpenRouter | Anthropic: Claude Fable 5.1 | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Anthropic: Claude Opus 4.5 (batch) | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Anthropic: Claude Opus 4.6 (batch) | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Anthropic: Claude Opus 4.7 (batch) | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Anthropic: Claude Opus 4.8 (batch) | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Anthropic: Claude Opus 5 (batch) | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Google: Gemini 2.5 ProPrompt > 200K | $0.25/M cache read | input_audio_cache: 0.00000025 / token (>200000) | |
| OpenRouter | Google: Gemini 2.5 ProPrompt > 200K | $0.25/M cache read | input_cache_read: 0.00000025 / token (>200000) | |
| OpenRouter | Google: Gemini 2.5 Pro Preview 06-05Prompt > 200K | $0.25/M cache read | input_audio_cache: 0.00000025 / token (>200000) | |
| OpenRouter | Google: Gemini 2.5 Pro Preview 06-05Prompt > 200K | $0.25/M cache read | input_cache_read: 0.00000025 / token (>200000) | |
| OpenRouter | OpenAI: GPT-4.1 (batch) | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-5.4 | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-5.4 (batch)Prompt > 272K | $0.25/M cache read | input_cache_read: 0.00000025 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.5 (batch) | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | OpenAI: o3 (batch) | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | Qwen: Qwen3.8 2.4T A95B | $0.25/M cache read | input_cache_read: 0.00000025 / token |
