← Models

Qwen 3.6 Max Preview

Alibaba · Qwen3

Alibaba's older Qwen 3.6 Max Preview for agentic coding, tool use, and 262K-context reasoning.

Part of Qwen3 family · Other versions: Qwen3.7 Max , Qwen3.6-27B , Qwen3-Max
Type
language
Context
262K tokens
Max Output
66K tokens
Status
preview
Input
$1.3/1M tok
Output
$7.8/1M tok
API Access
Yes
License
proprietary
chinese multilingual reasoning coding agentic long-context tool-use
Released April 2026 · Updated July 10, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on July 10, 2026.

Qwen 3.6 Max Preview is Alibaba Cloud’s older hosted flagship in the Qwen 3.6 generation. It sits above the open-weight Qwen 3.6 27B and Qwen 3.6 35B-A3B variants released earlier in April 2026. Qwen3.7 Max is now the current hosted flagship and official migration target.

Alibaba has scheduled qwen3.6-max-preview for retirement on October 10, 2026. The model remains callable at this snapshot, so the entry keeps status: "preview" rather than marking it deprecated early. New integrations should start with Qwen3.7 Max.

Capabilities

Alibaba’s release materials and Hugging Face cards highlight a specific capability profile:

  • Strong agentic coding behavior, with Qwen 3.6 Max Preview reportedly leading a set of common coding benchmarks at launch.
  • Long-context reasoning across the full 262K context window, designed for retrieval-heavy analysis and multi-turn agent loops.
  • Integrated thinking mode that keeps reasoning traces available across turns, useful for tool-using agents that need to revisit earlier reasoning.
  • Multilingual coverage extending Qwen3’s existing 119-language footprint, with continued strength in Chinese-English bilingual workloads.
  • Tool calling and structured output suitable for production agent orchestration.

The open-weight Qwen 3.6 27B and 35B-A3B variants share the generation’s design philosophy but trade peak intelligence for self-hosted deployability and lower operating cost.

Technical Details

Public anchors at this snapshot:

  • 262K-token context window, with up to 65K max output.
  • Hosted only as a managed Alibaba Cloud Model Studio endpoint at this preview stage, not released as open weights.
  • OpenAI-compatible and Anthropic-compatible API surfaces through Model Studio.

Alibaba does not publish weights or a durable full architecture specification for this proprietary Max preview.

Pricing & Access

Current international Alibaba Cloud Model Studio pricing per 1M tokens is tiered by input length:

  • Through 128K input: 1.30inputand1.30 input and 7.80 output.
  • Above 128K through 256K: 2.00inputand2.00 input and 12.00 output.

Pricing may vary by deployment region and gateway. Teams still using this route should price the migration to Qwen3.7 Max rather than assuming the preview will remain available after October 10.

Access options:

  • Alibaba Cloud Model Studio (DashScope) as the primary hosted route
  • OpenAI-compatible and Anthropic-compatible client SDKs against Model Studio
  • Third-party gateways such as OpenRouter

Best Use Cases

Keep Qwen 3.6 Max Preview for:

  • Existing agentic coding integrations already validated against this snapshot.
  • Tool-using agents that benefit from preserved reasoning traces across turns.
  • Bilingual Chinese-English assistants where Western frontier models still lag on Chinese-language nuance.
  • Long-context document analysis at hosted-API economics rather than self-hosted.

For new hosted work, use Qwen3.7 Max or a current Plus/Flash route. For self-hosted or air-gapped deployments, use open-weight Qwen 3.6 27B or 35B-A3B variants.

Comparisons

  • Qwen3.7 Max (Alibaba): Current 1M-context successor and official migration target.
  • Qwen3.6-27B (Alibaba): Open-weight multimodal sibling for self-managed deployment rather than maximum hosted capability.
  • Kimi K2.7 Code (Moonshot AI): Open-weight coding specialist with multimodal input; Qwen 3.6 Max remains proprietary and scheduled for retirement.