Create model provider config
Create a model provider config, validate the configured credential where the provider exposes a validation endpoint, then probe the provider’s /models endpoint. The result is returned as model_catalog; a failed probe does not fail creation.
Authorizations
An opaque Omnara personal or organization bearer token.
Path Parameters
^org_[a-z2-7]{26}$Body
Connect Omnara to a model API endpoint. Use a preset for built-in providers, or provide api_format and base_url for a custom endpoint. When omitted, endpoint_path and auth settings are filled from api_format.
Human-readable name. Spaces and punctuation are allowed; leading or trailing whitespace and invisible or control characters are not.
1 - 64^sec_[a-z2-7]{26}$openai, openrouter, anthropic openai-responses, openai-chat-completions, anthropic-messages default, openrouter, bedrock Provider endpoint base URL. Normal API mode requires a public HTTPS endpoint; localhost and loopback endpoints are accepted only when the API is running in insecure dev mode.
1URL path under base_url. Defaults to /responses for OpenAI Responses, /chat/completions for Chat Completions, and /messages for Anthropic Messages.
1^/Provider request timeout in milliseconds. Omitted value defaults to 600000.
1 <= x <= 2147483647bearer_token, api_key_header Non-secret API-key placement settings. Use an empty object with bearer_token. With api_key_header, set {"header_name":"..."}; Anthropic Messages defaults to {"header_name":"x-api-key"}.
Response
Route response.