Qwen: Qwen3 235B A22B
qwen/qwen3-235b-a22b
ReasoningToolsJSON
Intelligence
—
Design Elo
1055
Website
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.455
167th cheapest
Context
131K
8K max out
How it compares
Cheaper than50%
of all ranked models
Overview
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...
Benchmarks
independent · Artificial Analysis & Design ArenaDesign Arena · Elo3,811 tournaments
Website
1055
Data Viz
1030
3D
916
Providers & pricing (1)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Alibabafp8 | $0.455 | $1.82 | 131K | 100% |
Specifications
Context window131K
Max output8K
Knowledge cutoffMar 2025
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsQwen/Qwen3-235B-A22B ↗
Qwen3 235B A22B FAQ
How much does Qwen3 235B A22B cost?
Qwen3 235B A22B costs $0.455 per million input tokens and $1.82 per million output tokens via OpenRouter, making it 167th cheapest of 335 paid models.
What is Qwen3 235B A22B's context window?
Qwen3 235B A22B supports a 131K-token context window and can output up to 8K tokens. It accepts text input.