Qwen: Qwen3 235B A22B
Analysis Summary
Qwen3 235B A22B is Alibaba's largest Qwen3 model, using a mixture-of-experts architecture that activates 22B parameters per forward pass. It supports tool use and function calling across a 128K context window. Despite its large parameter count, benchmark scores are broadly similar to the Qwen3 32B, with a slightly higher intelligence index of 10.9 but a lower math score.
For businesses, the value proposition is less clear than for smaller Qwen3 siblings. The coding and agentic indices are comparable to the 32B, and the higher pricing at $0.455/1M input reduces its cost advantage. It does not support vision, limiting multimodal applications.
Teams that specifically need the MoE architecture for self-hosting or have workloads that benefit from the larger parameter count may find it useful. For most cloud API use cases, the Qwen3 32B offers similar performance at lower cost, making the 235B a harder sell for typical business deployments.
Assessed June 17, 2026
Editorial notes
Qwen3 235B A22B is a large MoE model from Alibaba with tool use and competitive coding scores, but its pricing is higher than smaller Qwen3 siblings that match or exceed it on most benchmarks.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen: Qwen3 235B A22B compares
Qwen: Qwen3 235B A22B ranks #209 of 380 AI models we track for overall intelligence, #193 of 317 for coding, #208 of 292 for agentic tasks. Its 131K-token context window is larger than 59% of the models we list. At $0.46 per million input tokens it is cheaper than 35% of comparable models.
About Qwen: Qwen3 235B A22B
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and..
Capabilities
Architecture Detail
| Instruct Type | qwen3 |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen: Qwen3 235B A22B stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
qwen/qwen3-235b-a22b
|
| Provider | qwen |
| Release Date | April 28, 2025 |
| Context Length | 131,072 tokens |
| Max Completion | 8,192 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.46 | $0.000455 |
| Output | $1.82 | $0.001820 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Qwen: Qwen3 235B A22B
How much does Qwen: Qwen3 235B A22B cost?
Qwen: Qwen3 235B A22B costs $0.46 per million input tokens and $1.82 per million output tokens.
What is the context window of Qwen: Qwen3 235B A22B?
Qwen: Qwen3 235B A22B has a context window of 131,072 tokens (131K).
Is Qwen: Qwen3 235B A22B good for coding?
On our coding benchmark index, Qwen: Qwen3 235B A22B ranks #193 of 317 models, placing it in the broader range of the field for code generation and debugging.
What can Qwen: Qwen3 235B A22B do?
Qwen: Qwen3 235B A22B supports tool use and function calling.
Who created Qwen: Qwen3 235B A22B?
Qwen: Qwen3 235B A22B is developed by Qwen and was released on April 28, 2025.
