LLM

Chat Completions (OpenAI-compatible)

Proxy chat completion requests to configured LLM providers. Supports streaming. Recommended "Single Key + Headers" pattern: send the gateway key as the Bearer token AND set X-Org-Id + X-Tenant-Id. Bearer-only key resolution can fail with 403 "Missing organization context".

post/api/v1/gateway/chat/completions

Request

  • Base URL: http://dobby-ai.com
  • URL: http://dobby-ai.com/api/v1/gateway/chat/completions
  • Auth: HTTP bearer

Headers

X-Org-Idstring

Organization ID. Recommended — Bearer-only requests fall back to resolving the org from the key, which can fail with 403 "Missing organization context".

X-Tenant-Idstring

Tenant workspace ID. Recommended alongside X-Org-Id (Single Key + Headers pattern).

Request body

modelstring required
streamboolean
max_tokensinteger
temperaturenumber

Example request

{
  "model": "claude-sonnet-4-6"
}

Response

Completion response (or SSE stream if stream=true)

idstring
objectstring
modelstring

Example response

{
  "object": "chat.completion"
}

Changes

No recorded changes to this operation across all 1 revision of this API.