Qwen/Qwen3-VL-235B-A22B-Instruct

The Qwen3 series VL models has been comprehensively upgraded in areas such as visual coding and spatial perception. Its visual perception and recognition capabilities have significantly improved, supporting the understanding of ultra-long videos, and its OCR functionality has undergone a major enhancement.

Alibaba Cloud Vision Up to 128K Tokens
Get API Key
Try in Playground
Free Trial Credit No Credit Card Required
$1.00

api_example.sh

curl -X POST "https://platform.qubrid.com/v1/chat/completions" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "Qwen/Qwen3-VL-235B-A22B-Instruct",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image? Describe the main elements."
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
          }
        }
      ]
    }
  ],
  "max_tokens": 8962,
  "temperature": 0.7,
  "stream": true,
  "top_p": 1
}'

Technical Specifications

Model Architecture & Performance

Variant VL Instruct
Model Size 235B params
Context Length Up to 128K Tokens
Quantization fp16
Tokens/Second 386
Architecture Transformer decoder-only (Qwen3-VL with ViT visual encoder)
Precision fp16 / bf16
License Apache 2.0
Release Date 2025
Developers Alibaba Cloud (QwenLM)

Pricing

Pay-per-use, no commitments

Input Tokens $0.0004/1K Tokens
Output Tokens $0.0016/1K Tokens

API Reference

Complete parameter documentation

Parameter Type Default Description
stream boolean true Enable streaming responses for real-time output.
temperature number 0.7 Controls creativity and randomness. Higher values produce more diverse output.
max_tokens number 8962 Maximum number of tokens the model can generate.
top_p number 1 Controls nucleus sampling for more predictable output.
reasoning_effort select medium Adjusts the depth of reasoning and problem-solving effort. Higher settings yield more thorough responses at the cost of latency.

Performance

Strengths & considerations

Strengths Considerations
State-of-the-art multimodal quality
Expensive and slower

Use cases

Recommended applications for this model

Complex visual reasoning
Scientific diagrams
Charts

Enterprise
Platform Integration

Docker

Docker Support

Official Docker images for containerized deployments

Kubernetes

Kubernetes Ready

Production-grade KBS manifests and Helm charts

SDK

SDK Libraries

Official SDKs for Python, Javascript, Go, and Java

Don't let your AI control you. Control your AI the Qubrid way!

Have questions? Want to Partner with us? Looking for larger deployments or custom fine-tuning? Let's collaborate on the right setup for your workloads.

"Qubrid AI reduced our document processing time by over 60% and significantly improved retrieval accuracy across our RAG workflows."

Enterprise AI Team

Document Intelligence Platform