Providers
Every built-in adapter: credentials, default transport, and where to find its catalog.
Each provider is a code adapter (translates the canonical format to/from the provider's wire
format) paired with a catalog (catalog.json, the known models and their capabilities/pricing).
Creating a deployment always names the adapter directly with adapterKey — see
Creating deployments for the full request shape.
| Provider | Adapter key | Credentials | Default transport |
|---|---|---|---|
| OpenAI | openai | apiKey | Responses API |
| Azure OpenAI | azureopenai | apiKey, baseUrl | Responses API |
| Azure Foundry | azurefoundry | apiKey, baseUrl | Chat Completions |
| Google AI Studio | googleaistudio | apiKey | generateContent |
| Anthropic | anthropic | apiKey | Messages API |
| DeepSeek | deepseek | apiKey | Chat Completions |
| MiniMax | minimax | apiKey | Chat Completions |
| Moonshot | moonshot | apiKey | Chat Completions |
| Z.AI | zai | apiKey | Chat Completions |
| Vercel AI Gateway | vercel | apiKey | Responses API |
| OpenAI-compatible | openaicompatible | apiKey, baseUrl | Chat Completions |
Adapters with a built-in upstream host do not require baseUrl. openaicompatible, Azure OpenAI,
and Azure Foundry require baseUrl because the operator chooses the target endpoint.
GET /admin/operations returns this same adapter list live, including required credential keys and
which operations/transports each adapter actually implements.
What to read next
- Creating deployments — the request shape shared by every provider.
- Model catalog — how a provider's models are declared.
- First deployment — the minimal end-to-end example.