Post Cloud Llm Chat Completions

Changed on

OpenAI-compatible chat-completions proxy over the shared key. Auth accepts a user OR process token (omicos-core calls with the latter). Quota is checked BEFORE proxying so a failed upstream call can't burn budget; tokens are recorded AFTER the call inside cloud_llm.

post/api/llm/cloud/chat/completions

Request

  • Base URL: https://api.omicos.cn (the document declares no server; this is the origin it was published from)
  • URL: https://api.omicos.cn/api/llm/cloud/chat/completions
  • Auth: none declared

Headers

authorizationstring nullable
x-omicos-devicestring nullable
x-omicos-device-kindstring nullable
x-omicos-device-namestring nullable

Response

Successful Response

unknown required

Changes

  • ef3006b6f052Revision changes
    • info

      added the new optional header request parameter x-omicos-device

    • info

      added the new optional header request parameter x-omicos-device-kind

    • info

      added the new optional header request parameter x-omicos-device-name