Chat Completions

The Chat Completions API is the primary entry point for text generation, tool calling, and multimodal reasoning. It mirrors OpenAI's chat.completions.create surface so any official OpenAI SDK works out of the box - just point baseURL at https://api.aivene.com/v1.

POST /v1/chat/completions

Send an array of messages representing the conversation so far and the model replies with the next assistant turn. Stream the response with stream: true for token-by-token delivery, or get a single JSON payload otherwise.

What you can do

• Generate text - everything from one-shot completions to multi-turn agentic loops.
• Call tools - register JSON-schema function definitions and let the model decide when to invoke them. See Tool calling.
• Reason over images, audio, and documents - attach multimodal content parts to any user message. See Multimodal.
• Enforce structured output - use response_format: 'json_schema' to get strictly-typed JSON without parsing.

Provider routing

The model id you send determines which upstream provider handles the request. The gateway normalises differences (e.g. rewriting developer roles to system, aligning max_tokens vs max_completion_tokens) so the same request body works across vendors. Browse available models at Models.

Endpoints

Every endpoint expects a bearer token in the Authorization header. Create keys at Manage API Keys.

Errors

All errors follow the OpenAI structured shape:

{ "error": { "type": "invalid_request_error", "message": "..." } }