Chat Completions

POST /v1/chat/completions — chat completion, OpenAI-compatible.

Request parameters

Param	Type	Required	Notes
model	string	yes	auto, or a model ID
messages	array	yes	Standard OpenAI message array
stream	bool	no	Defaults to false
temperature	number	no	0–2
max_tokens	int	no	Output cap
tools	array	no	Function calling (on models that support it)

Response

Identical to the OpenAI shape: choices[0].message.content and usage (prompt_tokens, completion_tokens). Streaming returns deltas.

curl https://api.aigateway.ltd/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${AIGATEWAY_API_KEY}" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'