v1

latestOpenAPI 3.1.02026-07-266827131.9 KB

Chat Completions qwen ilm

Generate chat completions using Qwen ILM or VLM models with image and video inputs.

post/iu/chat/completions

Request body

modelstring required

The model to use (e.g., qwen:qwen3-vl-plus)

temperaturenumber

Controls randomness: 0.0-2.0, higher = more random

max_tokensinteger

Maximum number of tokens to generate

top_pnumber

Nucleus sampling: 0.0-1.0

frequency_penaltynumber

Reduces repetition of frequent tokens: -2.0 to 2.0

presence_penaltynumber

Increases likelihood of new topics: -2.0 to 2.0

ninteger

Number of completions to generate

streamboolean

Whether to stream the response

Example request

{
  "model": "qwen:qwen3-vl-plus"
}

Response

Chat completion response with structured output

idstring required

Unique identifier for the completion

objectstring required

Object type, always 'completion'

modelstring required

The model used for the completion

created_atinteger required

Unix timestamp of when the completion was created

statusstring required

Status of the completion

Example response

{
  "id": "6612267a-d08f-9ea0-a254-7bcea6339f49",
  "object": "completion",
  "model": "qwen3-vl-plus",
  "created_at": 1767094289,
  "status": "completed",
  "choices": [
    {
      "text": "This image is from the game Half-Life 2, showing a game scene from a first-person perspective."
    }
  ],
  "usage": {
    "input_tokens": 235,
    "output_tokens": 229,
    "total_tokens": 464
  },
  "meta": {
    "provider": "qwen",
    "provider_model": "qwen3-vl-plus"
  }
}