Qwen3 235B A22B

Provider: Alibaba (Qwen) CN

No longer listed on OpenRouter since 2026-10-09. The figures below are the last recorded values.
Input price
$0.45
/ 1M tokens
Output price
$1.82
/ 1M tokens
Context
131K tokens
Max output 8K tokens

Overview

Qwen3 235B A22B is a flagship large language model from Alibaba (Qwen) in China, positioned for demanding enterprise workloads. It is designed to handle complex tasks, leveraging advanced reasoning capabilities and structured output features. This model targets applications requiring robust linguistic processing and high accuracy.

Strengths

  • Equipped with advanced 'thinking' capabilities for intricate problem-solving.
  • Supports reliable structured output through function-calling and JSON mode.
  • Features a substantial 131,072-token context window for extensive document analysis.
  • Offers a generous maximum output of 8,192 tokens, suitable for detailed responses.

Best use cases

  • Developing sophisticated AI agents and multi-turn conversational systems.
  • Automating complex analytical tasks requiring deep understanding and reasoning.
  • Processing and summarizing large volumes of text, such as legal documents or codebases.
  • Applications needing reliable structured data extraction and API function calls.

Pricing position

This model is Alibaba's most premium Qwen offering, costing $0.45/M for input and $1.82/M for output tokens. Its input price is comparable to peers like DeepSeek V4 Pro ($0.435/M) and GLM 4.6 ($0.43/M). The output price is competitive with GLM 4.6 ($1.74/M) and Mistral Large 3 ($1.5/M), but notably higher than DeepSeek V4 Pro's $0.87/M output.

Caveats

Qwen3 235B A22B does not explicitly list vision or audio processing capabilities. Given its premium pricing, it is not ideal for high-volume or cost-sensitive tasks where simpler models would suffice. For workloads that do not require its full power, other Qwen models like Qwen3.5-Flash offer a much lower cost per token, even with a larger context window.

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
2026-10-09

Features

Function callingJSON outputReasoning

Price history

  • 2026-10-09 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.14
1M (small app) 1 0.5 $1.36
10M (mid scale) 10 5 $13.65
100M (large) 100 50 $136.50

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API