Qwen3 Max

Provider: Alibaba (Qwen) CN

No longer listed on OpenRouter since 2026-10-09. The figures below are the last recorded values.
Input price
$0.78
/ 1M tokens
Output price
$3.90
/ 1M tokens
Cache price
$0.16
/ 1M tokens (read)
Context
262K tokens
Max output 66K tokens

Overview

Qwen3 Max is a flagship offering from Alibaba (Qwen), positioned for advanced general-purpose workloads that demand extensive context and structured outputs. This model from the Chinese provider targets complex reasoning and comprehensive data processing tasks within the Qwen family.

Strengths

  • Extremely large 262,144 token context window for processing extensive documents and conversations.
  • Robust support for function-calling, enabling complex tool integration and automation.
  • Reliable JSON-mode output for structured data extraction and programmatic interaction.
  • Substantial 32,768 token maximum output length for generating detailed responses.

Best use cases

  • In-depth analysis of lengthy legal documents, academic papers, or technical manuals.
  • Developing advanced AI agents that require tool use and structured communication.
  • Generating detailed reports or comprehensive summaries from vast amounts of input data.
  • Automating data extraction and transformation tasks using JSON-mode output.

Pricing position

Qwen3 Max is positioned as a higher-cost model within the Alibaba (Qwen) family, significantly more expensive than models like Qwen3.5-9B (input $0.04/M, output $0.15/M) or Qwen3.5-Flash (input $0.065/M, output $0.26/M). Among its similarly-priced peers, Qwen3 Max's input price of $0.78/1M tokens and output price of $3.9/1M tokens are competitive, closely matching Claude 3.5 Haiku ($0.799/M in, $4/M out) and GPT-5.4 Mini ($0.75/M in, $4.5/M out), while being slightly more expensive on output than Kimi K2.6 ($3.49/M out) or Deepseek R1 ($2.5/M out).

Caveats

This model lacks a free tier, meaning all usage incurs costs from the outset. For tasks that do not require its expansive 262,144 token context window or advanced capabilities like function-calling, significantly more cost-effective Alibaba (Qwen) models such as Qwen3.5-9B or Qwen3.5-Flash are available. The data does not indicate support for multimodal inputs like vision, which might be a limitation for certain applications.

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

Key facts

Max output
66K tokens
Tracked since
2026-05-08
Last updated
2026-10-09

Features

Function callingJSON output

Price history

  • 2026-10-09 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.27
1M (small app) 1 0.5 $2.73
10M (mid scale) 10 5 $27.30
100M (large) 100 50 $273.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API