11,195 prices on 4,854 listings · last collected 4 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.
Model
Claude 
Gemini 
Qwen 
DeepSeek 
GLM 
Kimi 
Mistral 
MiniMax 
Hunyuan 
Nemotron 
Llama Version
Showing 1–19 of 19
Per million cached input tokens (read)19
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterThird-party | MoonshotAI: Kimi K2.6via Baidu · fp4 | $0.066/M cache readCheapest | input_cache_read: 0.0000000656 / token (endpoint baidu/fp4) | |
| KIENot disclosed | Kimi K3.1 Pro | $0.08/M cache read | 16 credits per million tokens ($0.08)Claims official or Fal price $0.2/M cache read | |
| AibermNot disclosed | Kimi K2.5 | $0.083/M cache read | model_ratio 0.9 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Kimi K2.6 | $0.083/M cache read | model_ratio 0.9 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Kimi K2.5 | $0.083/M cache read | model_ratio 0.9 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Kimi K2.5 Thinking | $0.083/M cache read | model_ratio 0.9 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Kimi K3 | $0.106/M cache read | model_ratio 2.3 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| OpenRouterThird-party | MoonshotAI: Kimi K2.7 Codevia CoreWeave · int4 | $0.12/M cache read | input_cache_read: 0.00000012 / token (endpoint coreweave/int4) | |
| OpenRouterThird-party | MoonshotAI: Kimi K2 Thinking | $0.15/M cache read | input_cache_read: 0.00000015 / token (endpoint novita/bf16) | |
| AibermNot disclosed | Kimi K2.6 | $0.166/M cache read | model_ratio 1.8 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | Kimi K2.7 Code | $0.166/M cache read | model_ratio 1.8 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| OpenRouterNot disclosed | MoonshotAI: Kimi K3via Relace · fp4 | $0.18/M cache read | input_cache_read: 0.00000018 / token (endpoint relace/fp4) | |
| OpenRouterNot disclosed | MoonshotAI: Kimi Latest | $0.18/M cache read | input_cache_read: 0.00000018 / token | |
| OpenRouterThird-party | MoonshotAI: Kimi K2.5via AtlasCloud · int4 | $0.2/M cache read | input_cache_read: 0.0000002 / token (endpoint atlas-cloud/int4) | |
| OpenRouterThird-party | MoonshotAI: Kimi K3.1 Provia Relace · fp4 | $0.2/M cache read | input_cache_read: 0.0000002 / token (endpoint relace/fp4) | |
| RunwareNot disclosed | Kimi K3.1 ProPer 1M | $0.2/M cache read | $2e-7 / cachedInputToken | |
| OpenRouterThird-party | MoonshotAI: Kimi K3 (batch) | $0.228/M cache read | input_cache_read: 0.000000228 / token (endpoint deepinfra/bf16) | |
| KIENot disclosed | Kimi K3 | $0.24/M cache read | 48 credits per million tokens ($0.24)Claims official or Fal price $0.3/M cache read | |
| RunwareNot disclosed | Kimi K3Per 1M | $0.3/M cache read | $3e-7 / cachedInputToken |