Create a chat completion | AssemblyAI

1 curl -X POST https://llm-gateway.assemblyai.com/v1/chat/completions \ 2 -H "Authorization: <apiKey>" \ 3 -H "Content-Type: application/json" \ 4 -d '{ 5 "model": "claude-sonnet-4-5-20250929", 6 "prompt": "Write a haiku about coding", 7 "max_tokens": 50, 8 "temperature": 0.5 9 }'

1 { 2 "request_id": "string", 3 "choices": [ 4 { 5 "message": { 6 "role": "string", 7 "content": "string" 8 }, 9 "finish_reason": "stop", 10 "tool_calls": [ 11 { 12 "id": "string", 13 "type": "function", 14 "function": { 15 "name": "string", 16 "arguments": "string" 17 } 18 } 19 ] 20 } 21 ], 22 "request": { 23 "model": "string", 24 "max_tokens": 1, 25 "temperature": 1.1, 26 "tools": [ 27 { 28 "type": "function", 29 "function": { 30 "name": "string", 31 "parameters": {}, 32 "description": "string" 33 } 34 } 35 ], 36 "tool_choice": "none" 37 }, 38 "usage": { 39 "prompt_tokens": 1, 40 "completion_tokens": 1, 41 "total_tokens": 1 42 } 43 }

Generates a response from a model given a prompt or a series of messages.

Authentication

Authorizationstring

API Key authentication via header

Request

Request body for creating a chat completion.

modelstringRequired

The ID of the model to use for this request.

messageslist of objectsOptional

A list of messages comprising the conversation so far.

promptstringOptional

A simple string prompt. The API will automatically convert this into a user message.

max_tokensintegerOptional>=1

The maximum number of tokens to generate in the completion.

temperaturedoubleOptional

Controls randomness. Lower values produce more deterministic results.

toolslist of objectsOptional

A list of tools the model may call.

tool_choiceenum or objectOptional

Controls which (if any) function is called by the model.

Response

Successful response containing the model's choices.

request_idstring or nullformat: "uuid"

choiceslist of objects or null

requestobject or null

A copy of the original request, excluding prompt and messages.

usageobject or null