Skip to contentATP Token

Qwen 3.6 Max

Qwen (Alibaba)All Qwen (Alibaba) models

Input

$1.29

USD / 1M tokens

Output

$7.71

USD / 1M tokens

Released

2026-04-20

Positioning: Flagship. Price level 3 of 4 among text models.

Qwen 3.6 Max is Alibaba's Max-tier Qwen 3.6 model, released as Qwen3.6-Max-Preview, a hosted proprietary model without open weights. Alibaba reports gains over Qwen3.6-Plus in agentic coding, world knowledge, and instruction following, including tool-call formatting. Model Studio now lists it among legacy models with a 256K context, after newer Qwen 3.7 and 3.8 releases.

Tools
Get started freeAll model pricesCompare

Pricing

Pay for what you use: credits are deducted only when a request succeeds.
Prices in USD · $1 = 100 credits
Input
$1.29
Output
$7.71
USD / 1M tokens

Qwen (Alibaba) · Family · USD / 1M tokens

Text models from the same vendor on ATP. Bars fill up to the family's highest price.
All Qwen (Alibaba) models
ModelInputOutput
Qwen 3.6 Max This pageqwen-3-6-max$1.29$7.71
Qwen 3.7 Maxqwen-3-7-max$2.50$7.50
Qwen 3.8 Maxqwen-3-8-max$2.00$6.00
Qwen 3.6 Plusqwen-3-6-plus$0.276$1.651
Qwen 3.7 Plusqwen-3-7-plus$0.40$1.60
Qwen 3.6 Flashqwen-3-6-flash$0.165$0.99
Qwen Plus Characterqwen-plus-character$0.115$0.287
Qwen 3.7 Flashqwen-3-7-flash$0.03$0.13

Cost per 1,000 typical requests

A quick estimate with fixed token counts per request. No caching, no retries. Try the estimator with your own numbers.
WorkloadUSD / 1,000
Short chat turn800 / 400$4.12
RAG answer4,000 / 500$9.02
Agent step with tools20,000 / 1,500$37.37

Where it fits

Good fit
  • Agentic software engineering and terminal / CLI automation
  • Workloads that depend on strict tool-call format adherence
  • Chinese–English bilingual assistants and content pipelines
Usually not ideal
  • Image, audio, or PDF inputs — ATP's catalog lists this id as text-only
  • Deployments that require open weights for self-hosting

Benchmarks

Vendor-reported
  • SWE-bench Pro57.3%

    Preview (Qwen3.6-Max-Preview); value read from vendor's score chart image on the page

    Alibaba Cloud / Qwen
  • Terminal-Bench 2.0 (Terminus-2)65.4%

    Preview (Qwen3.6-Max-Preview); Terminus-2 harness; value read from vendor's score chart image

    Alibaba Cloud / Qwen
  • SkillsBench55.6%

    Preview (Qwen3.6-Max-Preview); value read from vendor's score chart image

    Alibaba Cloud / Qwen
  • SuperGPQA73.9%

    Preview (Qwen3.6-Max-Preview); value read from vendor's score chart image

    Alibaba Cloud / Qwen

Scores as published by each vendor, not measured by ATP. Test conditions vary, so they are not directly comparable across vendors.

Same controls on every model: project keys, per-project model access, credit budgets, and a log of every request.Set up your organization

Cost estimator

Plug in your usage to see roughly what a month costs.
0200
0100
ESTIMATE
$28.32
USD / month
2,832 credits / month
  • Input$12.90
  • Output$15.42

$28.32 USD / month · 2,832 credits / month

An estimate at our USD prices (USD 1 = 100 credits). What each request actually cost shows up in your console's request log.

Quickstart

Keep your SDK. Point it at ATP and use a project key. Read the docs
quickstart.py · OpenAI SDK
from openai import OpenAI

client = OpenAI(
  base_url="https://api.atptoken.ai/v1",
  api_key="atp-•••"
)

r = client.chat.completions.create(
  model="qwen-3-6-max",
  messages=[{"role":"user","content":"hi"}],
)

Compare with similar models

Same type and positioning, from other vendors, closest in price first.
Compare side by side

Related models

All Qwen (Alibaba) models
Qwen 3.7 Maxqwen-3-7-max$2.50 / $7.50In / out · per 1M tokensQwen 3.8 Maxqwen-3-8-max$2.00 / $6.00In / out · per 1M tokensQwen 3.6 Plusqwen-3-6-plus$0.276 / $1.651In / out · per 1M tokensQwen 3.7 Plusqwen-3-7-plus$0.40 / $1.60In / out · per 1M tokensQwen 3.6 Flashqwen-3-6-flash$0.165 / $0.99In / out · per 1M tokensQwen Plus Characterqwen-plus-character$0.115 / $0.287In / out · per 1M tokens

FAQ

4
Can Qwen 3.6 Max use tools, read images, or think before answering?
Qwen 3.6 Max supports tool calling, but not vision input, extended thinking or audio.
How is Qwen 3.6 Max priced?
You pay per 1M input tokens and per 1M output tokens. You only pay when a request succeeds. $1 = 100 credits. See pricing
Is there a newer Qwen (Alibaba) model than Qwen 3.6 Max on ATP?
Yes. Qwen 3.8 Max (qwen-3-8-max) came out on Aug 2, 2026, after Qwen 3.6 Max (Apr 20, 2026), and is the newer Qwen (Alibaba) text option on ATP. Both stay available: compare family prices on this page, then turn on the id you want for your project.
How do I call Qwen 3.6 Max on ATP?
Create a project API key and point any OpenAI-compatible SDK at https://api.atptoken.ai/v1. Set model to "qwen-3-6-max" (the API id, not the display name). Make sure the model is turned on for your project.

Sources

The model description on this page cites these sources. Prices come from ATP.
Get started

Start with $5. Credits never expire.

Create a project key, turn this model on, and pay only for what you use.

Get started freeTalk to enterprise