Qwen-VL-Chat

Model IntroductionText

Qwen-VL-Chat: Early vision dialogue, multi-turn interaction

Qwen-VL-Chat is part of the Qwen lineup from Qwen, designed for production workloads that need reliable quality at scale. Early vision dialogue, multi-turn interaction.

It accepts Image, Text inputs and produces Text outputs, with a context window of up to 32,000 input / 2,048 output tokens. The model is tuned for chat, analysis, and tool use in enterprise pipelines.

Native vision understanding supports charts, screenshots, UI mockups, and short video clips alongside text prompts.

Benchmarks

Benchmark (Area)Score*
MMMU (Vision)49.3% accuracy (Max)
DocVQA (Document)92.1 ANLS (Max)
ChartQA (Charts)60.7 Acc (Max)
MMLU-Pro (Knowledge)62.1 EM (Max)
MathVista (Math+Vision)51.7% (Max)
OCRBench (OCR)82.4 score (Max)

API request example

Endpoint /v1/chat/completions. Replace <API_KEY> with a key from the console.

Standard OpenAI Chat Completions. Swap `model` for the target slug.

curl https://api.ravenrouter.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
  "model": "Qwen-VL-Chat",
  "messages": [
    {
      "role": "user",
      "content": "Hello! Introduce yourself in one sentence."
    }
  ],
  "max_tokens": 64
}'

More models: API Reference → Examples by model

Qwen-VL-Chat API — $0.05/1M input, $0.10/1M output | RavenRouter AI