Qwen/Qwen3.6-Plus logo

Qwen/Qwen3.6-Plus

Qwen3.6-Plus is Alibaba's 2026 flagship vision-language model with upgraded perception, document intelligence, and tool-integrated reasoning across multi-image conversational flows.

Alibaba (Cloud) Vision Up to 256K tokens / 10 images
Get API Key
Deposit $5 to get started Unlock API access and start running inference right away. See how many million tokens $5 gets you

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": "qwen3.6-plus",
  "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": 16384,
  "temperature": 0.2,
  "stream": true,
  "top_p": 0.9
}'

Technical Specifications

Model Architecture & Performance

Variant Vision-Language
Model Size Undisclosed (frontier-scale)
Context Length Up to 256K tokens / 10 images
Quantization fp16 / bf16
Architecture Qwen3.6 decoder with ViT-Plus encoder and reasoning adapters
Precision fp16 / bf16 with speculative decoding
License Proprietary
Release Date April 2026
Developers Alibaba Cloud (QwenLM Tongyi Lab)

Pricing

Pay-per-use, no commitments

Input Tokens $0.26/1M Tokens
Output Tokens $1.80/1M Tokens

API Reference

Complete parameter documentation

Parameter Type Default Description
stream boolean true Stream partial tokens for lower-latency responses.
temperature number 0.2 Lower values improve determinism on structured perception tasks.
top_p number 0.9 Nucleus sampling for multimodal decoding. Reduce for more focused outputs.
max_tokens number 16384 Maximum number of tokens the model can generate in a single response.
reasoning_effort select medium Tune chain-of-thought depth. Higher effort improves fine-grained scene QA at the cost of latency.

Explore the full request and response schema in our external API documentation

Performance

Strengths & considerations

Strengths Considerations
Handles up to 10 images per turn with improved multi-image grounding
Enhanced chart/diagram reasoning with upgraded visual parser
Long-context support keeps historical instructions aligned across turns
Supports tool calling for downstream automation workflows
Requires Alibaba Cloud Tongyi (DashScope/Bailian) access in supported regions
High reasoning effort increases latency and cost

Use cases

Recommended applications for this model

Visual question answering over multi-step workflows such as UI flows, dashboards, or scientific plots
Document and chart understanding with table extraction, math reasoning, and structured JSON outputs
Creative assistance where images and prompts are iteratively combined with natural language planning
Retail and e-commerce applications that require attribute tagging, comparison, and compliance auditing

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 helped us turn a collection of AI scripts into structured production workflows. We now have better reliability, visibility, and control over every run."

AI Infrastructure Team

Automation & Orchestration