Models and pricing

Every model we serve, with the id you pass in your request. Rates are per 1M tokens, in US dollars, and are exactly what your balance is charged.

Swipe the table sideways for all four rate columns.

ModelContextInputOutputCache readCache write
GLM
GLM-5.3glm-5.31M$1.19$3.74$0.221
GLM-5.2glm-5.21M$0.70$2.20$0.13
GLM-5.1glm-5.1202K$0.70$2.20$0.13
Kimi
Kimi K3kimi-k31M$2.55$12.75$0.255
Kimi K2.7 Codekimi-k2.7-code262K$0.475$2.00$0.095
Kimi K2.6kimi-k2.6262K$0.475$2.00$0.08
MiMo
MiMo V2.5 Promimo-v2.5-pro1M$0.36975$0.7395$0.00306
MiMo V2.5mimo-v2.51M$0.07$0.14$0.0014
MiniMax
MiniMax M3minimax-m31M$0.15$0.60$0.03
MiniMax M2.7minimax-m2.7204K$0.15$0.60$0.03$0.1875
MiniMax M2.5minimax-m2.5204K$0.15$0.60$0.03$0.1875
Qwen
Qwen3.8 Maxqwen3.8-max1M$1.70$5.10$0.2125$2.125
Qwen3.7 Plusqwen3.7-plusUp to 200K tokens1M$0.20$0.80$0.02$0.25
Over 200K tokens$0.60$2.40$0.06$0.75
Qwen3.7 Maxqwen3.7-max1M$1.25$3.75$0.25$1.5625
Qwen3.6 Plusqwen3.6-plusUp to 200K tokens1M$0.25$1.50$0.025$0.3125
Over 200K tokens$1.00$3.00$0.10$1.25
DeepSeek
DeepSeek V4 Prodeepseek-v4-pro1M$0.36975$0.7395$0.00306
DeepSeek V4 Flashdeepseek-v4-flash1M$0.07$0.14$0.0014
Hy
Hy3hy3256K$0.07$0.29$0.0175
Grok
Grok 4.5grok-4.5500K$1.70$5.10$0.255
GPT
GPT 5.6 Lunagpt-5.6-lunaUp to 200K tokens1M$0.17$1.02$0.017$0.2125
Over 200K tokens$0.34$1.53$0.034$0.425

Cached input is billed at the cache-read rate automatically: the discount applies itself, with nothing to enable and no separate plan. A model with no cache-write rate does not charge for writing to the cache at all.