Pricing
Per-million-token pricing for serverless models deployed by Cast AI, plus the flat per-token surcharge for requests routed to external providers.
Per 1M token pricing for models available through the Kimchi serverless API. For current plans, billing details, and the latest model availability, see kimchi.dev/pricing.
| Model | Provider | Capabilities | Input / 1M tokens | Cached input / 1M tokens | Output / 1M tokens |
|---|---|---|---|---|---|
| kimi-k3 | Deployed by Cast AI | text, image, video | $3.00 | $0.30 | $15.00 |
| nemotron-3-ultra-fp4 | Deployed by Cast AI | text | $0.60 | — | $3.60 |
| deepseek-v4-flash-0731 | Deployed by Cast AI | text | $0.14 | $0.07 | $0.28 |
| deepseek-v4.1-flash | Deployed by Cast AI | text, image | $0.30 | $0.006 | $1.20 |
| glm-5.3 | Deployed by Cast AI | text | $1.40 | $0.14 | $4.40 |
| glm-5.3-flash | Deployed by Cast AI | text, image | $0.15 | $0.03 | $0.50 |
| minimax-m3 | Deployed by Cast AI | text, image | $0.30 | $0.06 | $1.20 |
| gemma-4-31b | Deployed by Cast AI | text, image | $0.09 | $0.05 | $0.34 |
External providers
Requests routed through Kimchi to external providers incur a flat per-token surcharge regardless of model. This surcharge is added on top of the provider's own token pricing. See Supported Providers for the list of external providers you can connect.
| Input / 1M tokens | Cached input / 1M tokens | Output / 1M tokens |
|---|---|---|
| $0.20 | Free | $0.30 |
Updated 4 days ago
Did this page help you?