Inference
EN

API pricing

136 ranked models with a price · Providers · Free

Cheapest by index

Blended / 1M
IndexCheapest modelIndexInput / 1MOutput / 1MBlended3 parts input, 1 output.
70+MiMo-V2.6-Pro70.2$0.435$0.87$0.544
65+DeepSeek V4.1 Flash 101768.5$0.022$0.40$0.116
60+GLM-5.3-Flash63.1$0.04$0.078$0.05
55+GLM-5.3-Flash63.1$0.04$0.078$0.05
50+Ling 3.0 Flash50.9$0.021$0.063$0.032
45+Ling 3.0 Flash50.9$0.021$0.063$0.032
40+Ling 3.0 Flash50.9$0.021$0.063$0.032
30+Ling 3.0 Flash50.9$0.021$0.063$0.032

Best value

No model is cheaper and higher
ModelIndexBlended3 parts input, 1 output.1K chats2K tokens in, 500 out, each.1K documents20K tokens in, 1K out, each.1K agent tasks200K tokens in, 20K out, each.
Claude Fable 5.285.6$16.00$36.00$200.00$2,400.00
Gemini 4 Carbon82.7$4.00$9.00$50.00$600.00
GPT-6.1 Terra77.1$2.00$4.50$25.00$300.00
MiMo-V2.6-Pro70.2$0.544$1.31$9.57$104.40
MiniMax M3.1 Flash69.3$0.262$0.60$3.60$42.00
DeepSeek V4.1 Flash 101768.5$0.116$0.244$0.84$12.40
GLM-5.3-Flash63.1$0.05$0.119$0.876$9.55
Ling 3.0 Flash50.9$0.032$0.074$0.483$5.46

Index and price

Blended / 1M
136 of 136 models

Blended price: 3 parts input to 1 part output, US dollars per 1M tokens, from the model's own listing. Ranked models with medium or high confidence. Each model page lists its providers and their prices.