ODOCK.AI
Models & MCPProviders

Providers

Connect upstream AI providers, store provider keys safely, and create models that use those providers.

Providers

Providers are upstream AI services Odock can call: OpenAI, Anthropic, Google Gemini, Azure OpenAI, vLLM, Mistral, Hugging Face, and custom-compatible providers.

A provider is not a model. The provider defines where and how Odock connects. A model defines what applications request and how that maps to an upstream slug.

Provider Hierarchy

The provider and provider key are setup dependencies. The virtual API key is the application credential. Applications never need upstream provider keys.

Provider Types

The organisation UI supports these provider types:

Provider typeTypical use
OPENAIOpenAI chat, responses, embeddings, image, and compatible OpenAI-style traffic.
ANTHROPICClaude models through Anthropic-compatible endpoints.
GOOGLEGemini models through Gemini-compatible endpoints.
AZURE_OPENAIOpenAI models hosted on Azure OpenAI.
VLLMSelf-hosted vLLM inference endpoints.
MISTRALMistral La Plateforme: chat, Codestral FIM, embeddings, moderation, and OCR.
HUGGINGFACEHugging Face Inference Providers: OpenAI-compatible chat over hundreds of open models and many upstream providers. See Hugging Face.
CUSTOMA custom or compatible upstream where your Odock deployment supports the route shape.

Provider type matters because native endpoints are provider-family aware. For example, an OpenAI-compatible endpoint expects an OpenAI-compatible model. If a request uses the wrong family, the gateway can reject it with a provider mismatch error.

For endpoint behavior, see Endpoints and Native Models call.

Provider Key Security

Odock keeps upstream provider secrets separate from application credentials.

  • The provider key is encrypted before storage.
  • The full provider key is not displayed again in the UI after saving.
  • The gateway resolves and decrypts the provider key only when it needs to call the upstream provider.
  • Plaintext provider keys should not be copied into application code.

For deeper security concepts, see Guardrails. For the runtime encryption flow, see Architecture.

Provider Workflows

For the maintained cross-provider list these workflows use, see Model Catalog.

Troubleshooting

SymptomWhat to check
Provider does not appear activeOpen Providers, clear filters, and confirm the provider card shows Active.
Cannot create modelsConfirm the provider is active and has at least one provider key.
Gateway returns provider mismatchConfirm the requested model belongs to the provider family used by the endpoint.
Upstream authentication failsRotate or replace the provider key, then test again.
Model calls time outReview provider timeout and the upstream provider health.

Continue with Models to configure model records, pricing, policies, and access.

On this page