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

​
Key Capabilities

  • OpenAI compatible — Drop-in replacement for the OpenAI SDK with no code changes required
  • 1M token context — Supports large-scale documents and multi-turn conversations, up to 66K output tokens
  • Multimodal input — Supports text, image, and video input
  • Agentic coding — Significant improvement on coding agent benchmarks
  • Reasoning mode — Enable built-in chain-of-thought via the enable_thinking parameter
  • Built-in tools — Supports web search, code interpreter, webpage scraping, and image search via the Responses API

​
Quick Example

curl https://ai.alad.com/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: Both image_url and video_url support remote URLs (https://...) and base64 data URIs (data:image/png;base64,... / data:video/mp4;base64,...). Image tokens and video tokens are reflected in usage.prompt_tokens_details.

​
Parameters

ParameterTypeRequiredDescription
modelstringYesMust be qwen3.6-flash
messagesarrayYesArray of { role, content } objects. Supports image_url and video_url multimodal input
max_completion_tokensintegerNoMaximum number of tokens to generate
temperaturefloatNo0–2, controls randomness, default 1
streambooleanNoEnable SSE streaming, default false
top_pfloatNoNucleus sampling threshold, default 1
stoparrayNoStop sequences. Must be array format, default null
enable_thinkingbooleanNoEnable reasoning mode via extra_body, default false

API Reference

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