Model detail
qwen3.6-max-preview
Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and long-context reasoning, supporting a 262K token context window. The model includes an integrated thinking mode that preserves reasoning traces across multi-turn conversations and supports structured output and function calling. Access is available exclusively through the Alibaba Cloud Model Studio and Qwen Studio APIs; no open weights are provided.
Model specs
- Model ID
-
qwen3.6-max-preview
- Context length
- 262.144K
- Max output
- 65.536K
- I/O modalities
- Released
- 2026-04
02
API endpoints
One MixRoute gateway, OpenAI-compatible
-
OpenAI-compatible
/v1/chat/completionsPOST
03
Tiered pricing
Unit: /1M Tokens
| Tier | Input /1M Tokens | Output /1M Tokens | Cache read /1M Tokens | Cache write /1M Tokens |
|---|---|---|---|---|
| short Length ≤ 128K | $1.3000 | $7.8000 | $0.1300 | $1.6250 |
| long Length > 128K | $2.0000 | $12.0000 | $0.2000 | $2.5000 |
05
Selection summary
Quickly judge whether it fits your workload
What is this model good for?
Proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts
Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters.
What should you check before using it?
262,144 context, 65,536 output tokens
Alibaba model that supports reasoning, tool calling and structured output. Knowledge cutoff: 2025-04. Released 2026-04-14.
Why use it through MixRoute?
qwen3.6-max-preview runs tools and structured output here
Tool calling and structured output run on that route as well. MixRoute serves qwen3.6-max-preview on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID qwen3.6-max-preview and re-run your integration tests.
07
Capabilities & compatibility
Unconfirmed capabilities stay "Unknown," no guesses
Tool calling
qwen3.6-max-preview supports function and tool calls.
tools definition; the response returns tool_calls to execute and feed results back.
Structured output
qwen3.6-max-preview can produce JSON-formatted output on demand.
response_format: { type: "json_schema" } forces valid JSON output.
Streaming
qwen3.6-max-preview supports streamed responses.
stream: true streams tokens incrementally, so chat UIs render as they arrive.
Prompt caching
qwen3.6-max-preview supports prompt caching under supported routing conditions.
OpenAI SDK
Call qwen3.6-max-preview through MixRoute's OpenAI-compatible endpoint.
base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.
08
Token cost estimator
Live estimate from this page's pricing, not an actual bill
Share of the same prefix read repeatedly, up to 100%
09
FAQ
Before switching production traffic to qwen3.6-max-preview, run a pilot on a representative slice of your traffic and check output quality, latency at peak concurrency, and cost per request. Verify the error and retry behaviour, and confirm the request limits you depend on match your plan.
One endpoint, a testable decision
Test this model and alternate routes with the same request format
Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.