qwen

Qwen: Qwen3 235B A22B

The Qwen3 235B A22B is a text-based AI model developed by qwen. It can handle input modalities limited to text and has a maximum context length of 131,072 tokens. The model also supports tools and reasoning capabilities. Considering its price point, the Qwen3 235B A22B may be a suitable option for those looking for a mid-range AI solution that balances cost with performance. Its benchmark blended score is 48.1 across three independent benchmarks, including Aid-E Polyglot (59.6) and EqBench (59.1). However, its pricing structure, with $0.455 per million input tokens and $1.82 per million output tokens, may deter users who prioritize lower costs.

Open weights 235B parameters, about 131.3 GiB at Q4_K_M: fits comfortably on 0 of 18 consumer graphics cards in the PicksByCard catalog. See which cards run it →
Quality Score
90/100
price + capability + benchmarks
Input Price
$0.46
per 1M tokens · checked 2026-09-23
Output Price
$1.82
per 1M tokens · checked 2026-09-23
Context Window
131,072
tokens

Benchmark results

Independent, published benchmarks. Blended score 47.9 across 3 benchmarks, last refreshed 2026-09-23. How scoring works →

BenchmarkMeasuresScore
Aider Polyglot code editing across languages 59.6
AI Index broad capability composite 13.7
EQ-Bench emotional understanding in dialogue 59.1
Model ID
qwen/qwen3-235b-a22b
Vendor
qwen
Released
April 2025
Tokenizer
Qwen3
Input Modalities
text
Output Modalities
text
Max Output
8,192 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.46/M input and $1.82/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.02
Classify 1,000 customer emails 500k in / 50k out $0.32
A month of a busy support chatbot 5M in / 2M out $5.92

Similar models

Quick answers

How much does Qwen: Qwen3 235B A22B cost?
$0.46 per million input tokens and $1.82 per million output tokens.
What is Qwen: Qwen3 235B A22B's context window?
131,072 tokens, roughly 196 pages of text in a single request.
Does Qwen: Qwen3 235B A22B support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can Qwen: Qwen3 235B A22B process images?
No, it is text-only on the input side.

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.