AI Observatory / Model Radar
Qwen / qwen/qwen3-235b-a22b
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...
131,072
Context
8,192
Max output
$0.45 / 1M
Prompt price
2025-04-28
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Qwen | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.45 / 1M |
| Completion price | $1.82 / 1M | Request price | N/A |
| Context length | 131,072 | Max completion tokens | 8,192 |
| Supported parameters | include_reasoning, max_tokens, presence_penalty, reasoning, response_format, seed, temperature, tool_choice, tools, top_p | ||
Best for
qwen/qwen3-235b-a22b
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...
Deep analysis
High-volume usage
Coding workflows
tool-capable
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.