Bifrost

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.

ProviderAdapter keyCredentialsDefault transport
OpenAIopenaiapiKeyResponses API
Azure OpenAIazureopenaiapiKey, baseUrlResponses API
Azure FoundryazurefoundryapiKey, baseUrlChat Completions
Google AI StudiogoogleaistudioapiKeygenerateContent
AnthropicanthropicapiKeyMessages API
DeepSeekdeepseekapiKeyChat Completions
MiniMaxminimaxapiKeyChat Completions
MoonshotmoonshotapiKeyChat Completions
Z.AIzaiapiKeyChat Completions
Vercel AI GatewayvercelapiKeyResponses API
OpenAI-compatibleopenaicompatibleapiKey, baseUrlChat 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.

On this page