Chat completions
Create OpenAI-compatible chat completions with Capriole AI models.
model and messages. Capriole AI resolves latest aliases to the selected provider model ID before upstream dispatch, forwards compatible fields such as messages, tools, tool_choice, response_format, and stream, and returns the upstream JSON or SSE stream unchanged. For streaming requests, Capriole AI sets stream_options.include_usage=true before forwarding so usage can be recorded.
POST /v1/chat/completions accepts openai-latest, claude-latest, google-latest, and public concrete model IDs returned by GET /v1/models. Use a latest alias to let Capriole AI choose our recommended flagship model for that provider.
Latest aliases are input shortcuts. Usage is recorded against the resolved model, while the response body keeps the model naming behavior of the selected compatible endpoint.
For Capriole-native text generation, use POST /v1/chat. Use POST /v1/chat/completions when OpenAI-compatible wire behavior is required.Authorizations
Use an API key created in the Capriole AI page. Send it as Authorization: Bearer sk-....
Body
Public model identifier or latest alias returned by GET /v1/models
openai-latest, openai/gpt-5.6-terra, openai/gpt-5.6-luna, openai/gpt-5.5, openai/gpt-5.4-mini, claude-latest, anthropic/claude-fable-5, anthropic/claude-opus-4-8, anthropic/claude-opus-4-7, anthropic/claude-opus-4-6, anthropic/claude-sonnet-4-6, google-latest, google/gemini-3.1-pro-preview, google/gemini-3.5-flash, xai/grok-4.5, zai/glm-5.2 OpenAI-compatible conversation messages.
OpenAI-compatible tool definitions.
OpenAI-compatible tool choice.
OpenAI-compatible response format.
Stream the response as OpenAI-compatible server-sent events.
OpenAI-compatible stream options. For streaming requests, Capriole AI sets include_usage=true before upstream dispatch for usage accounting.
Response
OpenAI-compatible Chat Completions response or SSE stream. Response model fields follow the selected compatible endpoint and may differ from the input alias.