Qwen-Max

Provider: Alibaba (Qwen) CN

No longer listed on OpenRouter since 2026-05-13. The figures below are the last recorded values.
Input price
$1.04
/ 1M tokens
Output price
$4.16
/ 1M tokens
Cache price
$0.21
/ 1M tokens (read)
Context
33K tokens
Max output 8K tokens

Overview

Qwen-Max is a general-purpose model from Alibaba (Qwen) (CN), positioned as a strong mid-tier offering within their lineup. It targets workloads requiring reliable structured outputs and a substantial context window. This model is designed for applications demanding precise control over response formats and integration with external tools.

Strengths

  • Supports robust function calling for complex tool integration workflows.
  • Provides native JSON mode for reliable structured data output generation.
  • Offers a substantial 32,768 token context window for in-depth analysis.
  • Generates comprehensive responses with an 8,192 token maximum output.

Best use cases

  • Automating multi-step workflows requiring external API interactions.
  • Extracting structured data from unstructured text into JSON format.
  • Summarizing lengthy documents or analyzing extensive codebases.
  • Developing applications requiring dependable structured output.

Pricing position

Qwen-Max is positioned as a higher-tier model within the Alibaba (Qwen) lineup, with input costs of $1.04/1M tokens and output costs of $4.16/1M tokens, making it substantially more expensive than its sibling models like Qwen3.5-9B ($0.04/M input). Its pricing is comparable to OpenAI's o4 Mini and o4 Mini High ($1.1/M input, $4.4/M output) and Anthropic's Claude Haiku 4.5 ($1/M input).

Caveats

This model does not offer a free tier, meaning developers must budget for its usage from the start. For tasks not requiring sophisticated function calling or JSON mode, or requiring much larger contexts (e.g., Qwen3.5-Flash's 1M tokens), other Qwen models offer significantly lower pricing. The provided capabilities list does not include vision, suggesting it is a text-only model.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Max output
8K tokens
Tracked since
2026-05-08
Last updated
2026-05-13

Features

Function callingJSON output

Price history

  • 2026-05-13 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.31
1M (small app) 1 0.5 $3.12
10M (mid scale) 10 5 $31.20
100M (large) 100 50 $312.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API