This page lists the models available on this gateway together with the price applied to each one. Each entry shows the billing mode in effect for that model and the resulting cost, so you can compare models before sending a request. Prices shown here are the ones this deployment actually applies.
Prices are per this deployment's configuration and can be changed by its operator at any time; the price in effect when a request is handled is the one charged.
Upstream protocol references: OpenAI API reference · Anthropic (Claude) API overview · Google Gemini API docs
| Model | Billing mode | Price |
|---|---|---|
| gpt-6-luna | Per request | $0.002 / request |
| glm-5.3-flash | Usage-based (billing expression) | see the interactive view (computed from usage) |
| deepseek-v4.1-flash-pojia | Per request | $0.003 / request |
| gpt-image-2.5 | Per request | $0.06 / request |
| deepseek-v4.1-flash | Usage-based (billing expression) | see the interactive view (computed from usage) |
| step-5-preview | Per request | $0.0003 / request |