Models and Pricing
Available models
| Model | Model Key | Context Window | Input Modality | Tool Calling | Reasoning | Prompt Caching |
|---|---|---|---|---|---|---|
| DeepSeek-4.1-Flash | deepseek-ai/deepseek-v4.1-flash | 1 million tokens | Text, Image | yes | yes | yes |
| GLM-5.3-Flash | zai-org/glm-5.3-flash | 1 million tokens | Text, Image, Video | yes | yes | yes |
Pricing
Prices are listed in USD per million tokens. Cached input is charged at the cache read rate instead of the regular input rate. Deploy servers are located in the US and unlike many other companies, we do not charge a premium for US based inference.
| Model | Input Tokens | Output Tokens | Cache Read Tokens |
|---|---|---|---|
| DeepSeek | $0.12 / 1M | $0.48 / 1M | $0.0024 / 1M |
| GLM | $0.05 / 1M | $0.17 / 1M | $0.01 / 1M |
Updated 7 days ago