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
| Provider | Endpoint style | Notes |
|---|---|---|
| OpenAI | /v1/chat/completions | Reference shape for OpenAI-compatible providers. |
| DeepSeek | OpenAI-compatible chat completions | Same general transport shape with a different base endpoint. |
| Gemini | generateContent style | Uses Google-style API key header rules. |
| Ollama | /api/chat | Local or remote Ollama endpoint, no remote cloud key by default. |
| Custom JSON | User-defined | Generic 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
The built-in provider tabs show the supported provider families and the editable asset fields each provider exposes.