Chat Completions

Generate model responses for a conversation.

Endpoint

POST
$ POST https://api.alltoken.ai/v1/chat/completions

Request body

JSON
1{
2 "model": "deepseek-chat",
3 "messages": [
4 { "role": "system", "content": "You are a helpful assistant." },
5 { "role": "user", "content": "Hello!" }
6 ],
7 "stream": false,
8 "temperature": 0.7,
9 "max_tokens": 1024
10}

Parameters

  • model (required) — model ID (e.g. "deepseek-chat")
  • messages (required) — array of message objects with role and content
  • stream — true for SSE streaming, false for complete response (default: false)
  • temperature — sampling temperature, 0-2 (default: 1)
  • top_p — nucleus sampling, 0-1 (default: 1)
  • max_tokens — maximum tokens to generate
  • frequency_penalty — penalize repeated tokens, -2 to 2 (default: 0)
  • presence_penalty — penalize topic repetition, -2 to 2 (default: 0)
  • tools — array of tool/function definitions for function calling
  • response_format — {"type": "json_object"} for guaranteed JSON output
  • web_search — true to enable web search (model-dependent)

Message roles

  • system — sets the model's behavior and context
  • user — the human's message
  • assistant — the model's previous response (for multi-turn)
  • tool — result of a function call (with tool_call_id)

Response

JSON
1{
2 "id": "chatcmpl-abc123",
3 "object": "chat.completion",
4 "created": 1700000000,
5 "model": "deepseek-chat",
6 "choices": [
7 {
8 "index": 0,
9 "message": {
10 "role": "assistant",
11 "content": "Hello! How can I help you today?"
12 },
13 "finish_reason": "stop"
14 }
15 ],
16 "usage": {
17 "prompt_tokens": 12,
18 "completion_tokens": 10,
19 "total_tokens": 22
20 }
21}