11,195 prices on 4,854 listings · last collected 2 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
All 29DeepSeek V4.1 Flash 4DeepSeek V4.1 Flash 1017 2DeepSeek V4 Flash 3DeepSeek V4 Flash 0731 1DeepSeek V4 Flash Latest 1DeepSeek V4 Flash Vision Exp 1DeepSeek V4 Pro 3DeepSeek V4 Pro 0813 1DeepSeek V3.2 2DeepSeek V3.2 Exp 1DeepSeek V3.1 1DeepSeek R1 1DeepSeek R1 0528 2DeepSeek Flash Latest 1DeepSeek Pro Latest 1DeepSeek V4.1 Flash 1017 (batch) 1DeepSeek V4.1 Flash (batch) 1DeepSeek V4 Flash 0731 (batch) 1DeepSeek V3.2 Exp Thinking 1
Showing 1–29 of 29
Per million cached input tokens (read)29
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterThird-party | DeepSeek: DeepSeek V4.1 Flash 1017 (batch) | $0.002/M cache readCheapest | input_cache_read: 0.000000002 / token (endpoint morph/fp8) | |
| AibermNot disclosed | DeepSeek V4.1 Flash | $0.0024/M cache read | model_ratio 0.26087 × $2/M · group default ×0.23 · cache_ratio 0.02 | |
| KIENot disclosed | DeepSeek V4.1 Flash | $0.0025/M cache read | 0.5 credits per million tokens ($0.0025) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4.1 Flash (batch) | $0.0034/M cache read | input_cache_read: 0.00000000336 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4.1 Flashvia Morph · fp8 | $0.004/M cache read | input_cache_read: 0.000000004 / token (endpoint morph/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4.1 Flash 1017via Morph · fp8 | $0.004/M cache read | input_cache_read: 0.000000004 / token (endpoint morph/fp8) | |
| OpenRouterNot disclosed | DeepSeek: DeepSeek Flash Latest | $0.005/M cache read | input_cache_read: 0.000000005 / token | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash Vision Expvia DeepInfra · fp8 | $0.0069/M cache read | input_cache_read: 0.00000000686 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash 0423via Baidu · fp8 | $0.01/M cache read | input_cache_read: 0.000000009996 / token (endpoint baidu/fp8) | |
| RunwareNot disclosed | DeepSeek-V4.1-FlashPer 1M | $0.01/M cache read | $1e-8 / cachedInputToken | |
| RunwareNot disclosed | DeepSeek-V4.1-Flash-1017Per 1M | $0.01/M cache read | $1e-8 / cachedInputToken | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash 0731 (batch) | $0.012/M cache read | input_cache_read: 0.000000012 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash 0731via Relace · fp4 | $0.014/M cache read | input_cache_read: 0.000000014 / token (endpoint relace/fp4) | |
| RunwareNot disclosed | DeepSeek-V4-Flash-0731Per 1M | $0.014/M cache read | $1.4e-8 / cachedInputToken | |
| AibermNot disclosed | DeepSeek V3.2 | $0.021/M cache read | model_ratio 0.45 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| AibermNot disclosed | DeepSeek V3.2 Exp | $0.021/M cache read | model_ratio 0.45 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| AibermNot disclosed | DeepSeek V3.2 Exp Thinking | $0.021/M cache read | model_ratio 0.45 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Pro 0813via Baidu · fp8 | $0.021/M cache read | input_cache_read: 0.000000020958 / token (endpoint baidu/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3.2via GMICloud · fp8 | $0.022/M cache read | input_cache_read: 0.0000000216 / token (endpoint gmicloud/fp8) | |
| AibermNot disclosed | DeepSeek V4 Flash | $0.029/M cache read | model_ratio 0.3126 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| OpenRouterNot disclosed | DeepSeek: DeepSeek V4 Flash Latest | $0.035/M cache read | input_cache_read: 0.000000035 / token | |
| RunwareNot disclosed | DeepSeek-V4-Pro-0813Per 1M | $0.079/M cache read | $7.9e-8 / cachedInputToken | |
| OpenRouterNot disclosed | DeepSeek: DeepSeek Pro Latest | $0.1/M cache read | input_cache_read: 0.0000000999 / token | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3.1via DeepInfra · fp4 | $0.13/M cache read | input_cache_read: 0.00000013 / token (endpoint deepinfra/fp4) | |
| AibermNot disclosed | DeepSeek V4 Pro | $0.132/M cache read | model_ratio 1.43478 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| AibermNot disclosed | DeepSeek R1 0528 | $0.198/M cache read | model_ratio 0.86 × $2/M · group default ×0.23 · cache_ratio 0.5 | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Pro 0423via Relace · fp4 | $0.25/M cache read | input_cache_read: 0.00000025 / token (endpoint relace/fp4) | |
| OpenRouterThird-party | DeepSeek: R1 0528via DeepInfra · fp4 | $0.35/M cache read | input_cache_read: 0.00000035 / token (endpoint deepinfra/fp4) | |
| AibermNot disclosed | DeepSeek R1 | $0.359/M cache read | model_ratio 1.56 × $2/M · group default ×0.23 · cache_ratio 0.5 |