Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.openserv.ai/llms.txt

Use this file to discover all available pages before exploring further.

SERV exposes three endpoints: /v1/chat/completions, /v1/responses, and /v1/messages. Each supports a different subset of providers.
Provider/v1/chat/completions/v1/responses/v1/messages
OpenAI✅✅✅
Anthropic✅❌✅
Google (Gemini)✅❌⚠️ (not available)
Google (Gemma)✅❌✅
xAI✅❌✅
Qwen✅❌✅
DeepSeek✅❌✅

​
Endpoint behaviors

  1. /v1/chat/completions is universal. It supports every provider in the catalog, including Claude. A single code path through the OpenAI SDK is sufficient for all models.
  2. /v1/responses is OpenAI-only. Non-OpenAI models are not supported on this endpoint and should use /v1/chat/completions.
  3. /v1/messages is multi-provider. It accepts OpenAI, Anthropic, xAI, Qwen, DeepSeek, and Gemma models. Existing Anthropic-SDK integrations can switch providers by changing the model ID alone.

​
Google models

  • Gemini is not available on /v1/messages. Use /v1/chat/completions for Gemini. Gemma is supported on both endpoints.
  • The google-genai SDK is not supported. It uses Gemini’s generateContent format, which SERV does not expose. Use the OpenAI SDK against /v1/chat/completions for any Gemini or Gemma model.

​
See also

  • Models — the full catalog with pricing and context windows.
  • SDK Integration — endpoints and the parameter map.