ZMIME
Alibaba (Qwen) · Released Apr 28, 2025

Qwen3 235B-A22B

Large open Qwen MoE for multilingual reasoning, coding, and tool use.

  • Open weights
  • Reasoning
  • Tool calling
  • Deprecated
Capability
138.4ECI · #119 of 158
Input
$0.70per 1M tokens
Output
$2.80per 1M tokens
Context
131K16K max output
Pricing

What it costs

Input
$0.70per million tokens
Output
$2.80per million tokens
Blended (3:1)
$1.23pricier than 62% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$2.80
Team assistant25M input + 5M output tokens$31.50
Production app250M input + 50M output tokens$315.00

Official Alibaba API price, as listed on models.dev.

Capability

Independent benchmarks

138.4Epoch Capabilities Index
#119 of 158 scored models
68Median 147174

The shaded band is Epoch AI’s confidence range (136.1–140.7); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions70.7%

Scores from Epoch AI, run independently of Alibaba (Qwen).

Specifications

The details

Lab
Alibaba (Qwen)
Released
Apr 28, 2025
Knowledge cutoff
Apr 2025
Context window
131,072 tokens
Max output
16,384 tokens
Inputs
Text
Output
Text
Reasoning
Thinking budget
Tool calling
Yes
Structured output
No
API model ID
qwen3-235b-a22bon Alibaba
Availability
7 API providerslisted on models.dev
Status
Deprecated by the provider

Alibaba model documentation

Lab-reported

What Alibaba (Qwen) claims

Published by the lab at launch. Settings vary, so compare these only with care.

BenchmarkScoreSettingSource
Aider Polyglot59.6 percent correct—Source
SWE-Bench Pro21.41 resolve rate—Source
Same lab

More from Alibaba (Qwen)

Questions

About Qwen3 235B-A22B

How much does Qwen3 235B-A22B cost?

Qwen3 235B-A22B costs $0.70 input / $2.80 output per million tokens (official Alibaba API price). At a 3:1 input-to-output mix that is $1.23 per million tokens, more expensive than 62% of the 469 priced models we track.

What is the context window of Qwen3 235B-A22B?

Qwen3 235B-A22B accepts up to 131,072 tokens per request and can write up to 16,384 tokens in one response.

How good is Qwen3 235B-A22B?

Epoch AI gives Qwen3 235B-A22B a Capabilities Index score of 138.4 (likely range 136.1–140.7), ranking it #119 of 158 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 70.7%.

Is Qwen3 235B-A22B open source?

Yes. Alibaba (Qwen) publishes the weights, so it can be downloaded and self-hosted.

What inputs does Qwen3 235B-A22B support?

Qwen3 235B-A22B accepts text and replies in text. It is a reasoning model, supports tool calling.

When was Qwen3 235B-A22B released?

Alibaba (Qwen) released Qwen3 235B-A22B on Apr 28, 2025. Its training data runs to Apr 2025.

What are the best alternatives to Qwen3 235B-A22B?

The closest current models from other labs on capability, price and release date are DeepSeek R1 0528 (DeepSeek, ECI 140.8, $0.512 / $2.19), Gemini 2.5 Flash Preview 05-20 (Google, ECI 141.6, $0.142 / $3.33), Kimi K2 Instruct (Moonshot AI, ECI 141.3, $0.57 / $2.30) and GPT-4.1 mini (OpenAI, ECI 134.3, $0.40 / $1.60).