---
title: "Chat Completions qwen"
method: POST
path: "/vu/chat/completions"
---

# Chat Completions qwen

`POST /vu/chat/completions`

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

## Request body

- object
  - `model` string, required — The model to use (e.g., qwen:qwen3-vl-plus)
  - `messages` object[], required — Array of message objects
    - `role` 'system' | 'user', required
    - `content` union, required
      - string
      - union[]
        - union
          - object
            - `image` string — URL or base64 encoded image
          - object
            - `video` string — URL only (video does not support base64)
          - object
            - `text` string, required
  - `temperature` number — Controls randomness: 0.0-2.0, higher = more random
  - `max_tokens` integer — Maximum number of tokens to generate
  - `top_p` number — Nucleus sampling: 0.0-1.0
  - `frequency_penalty` number — Reduces repetition of frequent tokens: -2.0 to 2.0
  - `presence_penalty` number — Increases likelihood of new topics: -2.0 to 2.0
  - `n` integer — Number of completions to generate
  - `stream` boolean — Whether to stream the response
  - `stop` union — Stop sequences
    - string
    - string[]
  - `extra_body` object
    - `metadata` object
      - `enable_thinking` boolean
      - `thinking_budget` integer
      - `response_format` object
        - `type` 'json_schema'
        - `json_schema` object
          - `name` string
          - `schema` object
            - `type` 'object'
            - `properties` object
            - `required` string[]

## Response `200`

Chat completion response with structured output

- object
  - `id` string, required — Unique identifier for the completion
  - `object` string, required — Object type, always 'completion'
  - `model` string, required — The model used for the completion
  - `created_at` integer, required — Unix timestamp of when the completion was created
  - `status` string, required — Status of the completion
  - `choices` object[], required
    - `text` string, required — Text content of the completion
    - `index` integer, required — Index of the choice in the choices array
  - `usage` object, required
    - `input_tokens` integer, required — Number of input tokens used
    - `output_tokens` integer, required — Number of output tokens generated
    - `total_tokens` integer, required — Total number of tokens used
  - `meta` object, required
    - `provider` string, required — Provider name
    - `provider_model` string, required — Provider-specific model name

---

[API](https://skmtc.net/memories/apis/screenplay-extraction-api.md) · [All operations](https://skmtc.net/memories/apis/screenplay-extraction-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/memories/screenplay-extraction-api/versions/720c8c144ddc/schema)