All Models
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 code tasks, and a "non-thinking" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling.
Available Providers (8)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Nvidia | qwen/qwen3-235b-a22b | $0.00/MTok | $0.00/MTok | 131.1K | 8.2K | |
 iFlow | qwen3-235b | $0.00/MTok | $0.00/MTok | 128K | 32K | |
 NovitaAI | qwen/qwen3-235b-a22b-fp8 | $0.20/MTok | $0.80/MTok | 41.0K | 20K | |
 Jiekou.AI | qwen/qwen3-235b-a22b-fp8 | $0.20/MTok | $0.80/MTok | 41.0K | 20K | |
 Alibaba (China) | qwen3-235b-a22b | $0.29/MTok | $1.15/MTok | 131.1K | 16.4K | |
 302.AI | qwen3-235b-a22b | $0.29/MTok | $2.86/MTok | 128K | 16.4K | |
 Chutes | Qwen/Qwen3-235B-A22B | $0.30/MTok | $1.20/MTok | 41.0K | 41.0K | |
 Alibaba | qwen3-235b-a22b | $0.70/MTok | $2.80/MTok | 131.1K | 16.4K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output