Compare LLM API Prices
Side-by-side per-1M-token rates for every supported model
| Model | Platform | Context | Type | Input /1M | Output /1M |
|---|---|---|---|---|---|
GLM-5.2 glm-5.2 | Z.ai | 1M | chatcoding | — | — |
GLM-5.1 glm-5.1 | Z.ai | 203K | chatcoding | $1.15 | $4.00 |
GLM-5 glm-5.0 | Z.ai | 203K | chatagent | — | — |
GLM-5 glm-5 | Z.ai | 203K | chatagent | $1.00 | $3.20 |
GLM-5-Turbo glm-5-turbo | Z.ai | 203K | chatagent | $1.20 | $4.00 |
GLM-4.7 glm-4.7 | Z.ai | 205K | chat | $0.600 | $2.20 |
GLM-4.6 glm-4.6 | Z.ai | 205K | chat | $0.600 | $2.20 |
Kimi K2.7 Code kimi-k2.7-code | Moonshot | 256K | chatcoding | — | — |
Kimi K2.6 kimi-k2.6 | Moonshot | 256K | chatvision | $0.950 | $4.00 |
Kimi K2.5 kimi-k2.5 | Moonshot | 256K | chatvision | $0.600 | $3.00 |
DeepSeek V4 Pro deepseek-v4-pro | DeepSeek | 128K | chatreasoning | $0.435 | $0.870 |
DeepSeek V4 Flash deepseek-v4-flash | DeepSeek | 128K | chatreasoning | $0.140 | $0.280 |
Qwen3.8 MAX qwen3.8-max | Qwen | 1M | chatreasoning | — | — |
Qwen3.7 MAX qwen3.7-max | Qwen | 1M | chatreasoning | $1.70 | $5.10 |
Qwen3.7 Plus qwen3.7-plus | Qwen | 1M | chatvision | — | — |
Qwen3.6 Flash qwen3.6-flash | Qwen | 1M | chatvision | — | — |
Qwen3.6 35B A3B qwen3.6-35b-a3b | Qwen | 256K | chatcoding | — | — |
Qwen3.5 Plus qwen3.5-plus | Qwen | 1M | chatvision | $0.500 | $3.00 |
Qwen3.5 Flash qwen3.5-flash | Qwen | 1M | chatvision | — | — |
MiniMax M3 minimax-m3 | MiniMax | 1M | chatagent | $0.600 | $2.40 |
MiniMax M2.7 minimax-m2.7 | MiniMax | 200K | chat | $0.300 | $1.20 |
MiniMax M2.7 Highspeed minimax-m2.7-highspeed | MiniMax | 200K | chat | $0.600 | $2.40 |
MiniMax M2.5 Highspeed minimax-m2.5-highspeed | MiniMax | 200K | chatcoding | $0.600 | $2.40 |
MiniMax M2.5 minimax-m2.5 | MiniMax | 200K | chatcoding | $0.300 | $1.20 |
MiniMax M2.1 minimax-m2.1 | MiniMax | 200K | chatcoding | $0.300 | $1.20 |
MiniMax M2 minimax-m2 | MiniMax | 200K | chatcoding | $0.300 | $1.20 |
Prices synced with platform billing (USD per 1M tokens).