Provider Assets

Provider assets are the main extension surface in AI Providers. Each built-in provider is a concrete LlmProviderDefinitionBase implementation with its own endpoint, auth behavior, and response parser.

Built-in providers

ProviderEndpoint styleNotes
OpenAI/v1/chat/completionsReference shape for OpenAI-compatible providers.
DeepSeekOpenAI-compatible chat completionsSame general transport shape with a different base endpoint.
GeminigenerateContent styleUses Google-style API key header rules.
Ollama/api/chatLocal or remote Ollama endpoint, no remote cloud key by default.
Custom JSONUser-definedGeneric adapter for custom or OpenAI-compatible HTTP+JSON flows.

What provider assets store

  • Display name and description.
  • Base URL and endpoint rules.
  • Default model name.
  • Request header behavior.
  • Provider GUID used for local key lookup.

What provider assets do not store

Local API keys are not serialized into the shared asset file. That boundary is intentional and matters both for version control and for honest public documentation.

Built-in provider surface

AI Providers panel with built-in provider choices

The built-in provider tabs show the supported provider families and the editable asset fields each provider exposes.