Chat Completions

Endpoint (v2 & v3)

POST /v3/chat/completions   # Rust (utama)
POST /v2/chat/completions   # Go (cadangan)
POST /v1/chat/completions   # alias v3

Settings lengkap untuk opencode.json, baseURL v2/v3, dan fallback: lihat Settings API.

Request

{
  "model": "bt/qwen3.8-flash",
  "messages": [
    {"role": "system", "content": "Kamu asisten yang membantu."},
    {"role": "user", "content": "Halo!"}
  ],
  "temperature": 0.7,
  "max_tokens": 2048
}

Response

{
  "id": "chatcmpl-xxx",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Halo! Ada yang bisa saya bantu?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 10,
    "total_tokens": 25
  }
}

Parameter

Parameter	Type	Default	Description
model	string	required	Model ID (prefix bt/)
messages	array	required	Array pesan
temperature	number	0.7	Sampling temperature
max_tokens	integer	2048	Maks token output
stream	boolean	false	Enable streaming