Skip to main content
Qwen3.6-Flash is Alibaba’s native vision-language Flash model, available through Anyfast via an OpenAI-compatible interface. It delivers significant improvements in agentic coding, math/code reasoning, and spatial intelligence compared to Qwen3.5-Flash.

​
Key capabilities

  • OpenAI-compatible — Works as a drop-in replacement with the OpenAI SDK
  • 1M token context — Handles massive documents and conversations with up to 66K output tokens
  • Multi-modal input — Supports text, image, and video inputs
  • Agentic coding — Substantially improved coding agent benchmarks
  • Reasoning — Built-in thinking support via enable_thinking parameter
  • Built-in tools — Web search, code interpreter, web scraping, image search via Responses API

​
Quick example

curl https://www.anyfast.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.6-flash",
    "messages": [
      { "role": "user", "content": "Explain quantum entanglement in simple terms." }
    ]
  }'
Note: image_url and video_url support both remote URLs (https://...) and base64 data URIs (data:image/png;base64,... / data:video/mp4;base64,...). Image tokens and video tokens are counted in usage.prompt_tokens_details.

​
Parameters

ParameterTypeRequiredDescription
modelstringYesMust be qwen3.6-flash
messagesarrayYesList of { role, content } objects. Supports image_url and video_url for multi-modal
max_completion_tokensintegerNoMaximum tokens to generate
temperaturefloatNo0–2. Controls randomness. Default: 1
streambooleanNoEnable SSE streaming. Default: false
top_pfloatNoNucleus sampling threshold. Default: 1
stoparrayNoStop sequences. Must be an array. Default: null
enable_thinkingbooleanNoEnable reasoning via extra_body. Default: false

API Reference

View the interactive API playground for Qwen3.6-Flash.