Alibaba Cloud: Qwen Max

Flagship Qwen model for complex reasoning, coding, and agentic workflows

qwen-max

AvailableAlibaba CloudChat

Input / Output: $1.60 / $6.40
Context: 31K
Max output: 8K
Modalities: Chat
Capabilities: Prompt Cache

About Qwen Max

Qwen Max is the flagship model of Alibaba's original Qwen commercial line, built for complex reasoning, coding and multi-step analysis. Within the older Qwen names it is the strongest tier, above Qwen Plus and Qwen Flash. Alibaba now lists it as a legacy model and points new projects to the Qwen3 generation, so it fits existing workloads better than fresh builds.

Where it works well

Handles harder multi-step analysis and instruction-heavy prompts better than Qwen Plus and Qwen Flash.
Writes and reviews code, with Alibaba describing coding as one of its target uses.
Follows long, detailed rule sets and keeps to the requested output format.
Prompt caching lowers repeat cost on a long, reused system prompt.

When to choose another model

Its window is much smaller than Qwen Plus and Qwen Flash, which makes whole-document tasks awkward.
It takes text only, so screenshots, charts and scans need a vision-capable model.
It is a legacy name; Qwen3.8 Max is the current top Qwen model for new work.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Text to textMessages API

POST/v1/messages

API format:

curl https://api.tokenlab.sh/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-xxx" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "qwen-max",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Default

per 1M tokens

Official price: Input $1.60 / Output $6.40 / Cache read $0.32 / Text Input $1.60 / Text Output $6.40
Verified price: —
Discount: —

Prompt cache pricing

Cache read

Official price: $0.32
Verified price: —
Discount: —

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Default	Input $1.60 / Output $6.40 / Cache read $0.32 / Text Input $1.60 / Text Output $6.40	—	—
Prompt cache pricing
Cache read	$0.32	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 10:22 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Qwen Max in Console with a prompt ready to edit or send.

Help me try qwen-max with a short message at /v1/messages. Show the reply, latency, and cost.

Use cases

Code review and generation
Ask for a function, a test or a review of a diff, with the code pasted into the prompt.
Structured analysis
Break a business question into steps, weigh options and write the reasoning as a short memo.
Instruction-heavy assistants
Run an assistant with a long, detailed rule set where missing a constraint is costly.
Legacy pipeline upkeep
Keep an existing Qwen Max integration running while you evaluate newer Qwen3 models.

Prompt examples

Review this Python function for bugs and edge cases, then rewrite it with type hints and add three unit tests.

Compare these two vendor proposals on cost structure, risk and lock-in, then recommend one in a paragraph.

Follow these eight formatting rules exactly and produce the weekly report from the notes below.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What is Qwen Max?

The top tier of Alibaba's original Qwen commercial models, aimed at complex reasoning, coding and multi-step analysis. It outranks Qwen Plus and Qwen Flash in capability but has a smaller window than they do.

Is Qwen Max still the best Qwen model?

No. Alibaba lists it under legacy Qwen models and recommends newer Qwen3 generations. Qwen3.8 Max is the current top model; keep Qwen Max for existing prompts that already work well.

When does prompt caching help with Qwen Max?

When a long system prompt or reference text is reused across many requests. Put the stable rules and reference material first and the changing question last, so repeat requests cost less.

Should I use Qwen Max or Qwen Plus?

Use Qwen Max for harder reasoning and coding where answer quality matters most and inputs are short. Use Qwen Plus when you need a much longer input or a balance of quality and speed.

Can Qwen Max read images?

No. Qwen Max is a text model. For screenshots, charts or scanned pages, use a Qwen vision model. If you need a specific output format, ask for it in the prompt and validate the result in code.

How much does Qwen Max cost?

On TokenLab, Qwen Max costs Input $1.60 / Output $6.40 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What are the context window and output limit of Qwen Max?

Qwen Max accepts up to 30,720 tokens of context and returns up to 8,192 tokens in one response.

Which endpoint should Qwen Max use?

Use https://api.tokenlab.sh/v1/messages for Qwen Max. The request example below shows the matching code shape.

Which operations does Qwen Max support?

Qwen Max supports Text to text. Select an operation above to see its endpoint and request example.