Skip to main content

Messages API v3

Messages API v3 is Funtimes's OpenAI-compatible generation endpoint for text and images.

Base URL:

https://msg.funtimes.technology

Use this API when you want synchronous chat or Responses API generations with Funtimes quota tracking, character prompts, configured knowledge context, streaming, fallback models, and usage attribution.

The older Messages API v2 docs cover the legacy /v2/completions text/audio flow. Use Messages API v3 for new OpenAI-compatible integrations.

Typical Flow​

  1. Send an OpenAI-compatible request with a quota API key.
  2. Funtimes validates the API key, quota, and character access.
  3. Messages API v3 applies character prompts and configured knowledge context when available.
  4. The model response is returned directly or streamed.
  5. Usage is recorded automatically.

Features​

  • Chat Completions: POST /v3/chat/completions
  • Responses API: POST /v3/responses
  • Authentication: Authorization: Bearer <quota_api_key> or X-API-Key: <quota_api_key>
  • Characters: Optional GitHub or inline characters under metadata.funtimes.character
  • Knowledge context: Configured through GitHub or inline character settings
  • Knowledge visibility: Responses API calls can include status messages and source items when knowledge context is used
  • Fallback models: Optional top-level fallback_model for supported requests
  • Reasoning controls: Optional reasoning settings for supported models
  • Streaming: Standard streaming responses for supported models
  • Images: Send images to vision models, or generate them with an image model. See Images.

Important Considerations​

important
  • metadata.funtimes may contain only character and character_params.
  • metadata.funtimes.routing, metadata.funtimes.request_id, and unknown metadata.funtimes fields are rejected.
  • metadata.funtimes is Funtimes-only request metadata and is not part of the model conversation.
  • Knowledge context is configured in character settings, either in GitHub or inline.
  • Request bodies are limited to 20 MB, including base64 images. Larger requests return 413.
  • Character max_new_tokens, when present in old character schemas, is not used as the output-token limit. Use request-level token fields such as max_completion_tokens, max_tokens, or max_output_tokens.