Plain-English Summary
Qwen’s flagship open MoE model for reasoning, coding, multilingual work, and agents.
Qwen3-235B-A22B
Qwen’s flagship open MoE model for reasoning, coding, multilingual work, and agents.
Qwen3
Reasoning LLM
Open weights
Open weights: Yes
API: Yes and self-hosted
Technical Notes
235B-total, 22B-active MoE transformer with hybrid thinking/non-thinking modes and long-context support.
Best For
Open enterprise assistants, coding, multilingual agents, research
Watch Out For
Large serving footprint; performance depends heavily on inference stack and reasoning settings.
Model Specs
- Maker
- Alibaba Cloud / Qwen
- Country
- China
- Family
- Qwen3
- Type
- Reasoning LLM
- Release date
- 2025-04-29
- Date confidence
- Exact
- Status
- Open weights
- Context window
- 131,072 tokens
- Max output
- 32,768
- Parameters
- 235B
- Active parameters
- 22B
- Architecture
- Mixture-of-experts transformer
- Reasoning
- Yes — thinking or non-thinking
- Tool calling
- Yes / host dependent
- Structured output
- Host dependent
- API available
- Yes and self-hosted
- Open weights
- Yes
- Self-hostable
- Yes
- License
- Apache 2.0
- Inputs
- Text
- Outputs
- Text
- Approx. price
- See provider pricing
- How to access
- Provider website
- Model / API ID
- Qwen3-235B-A22B
- Knowledge cutoff
- Not publicly disclosed
- Fine-tuning
- Fine-tuning, quantization, self-hosting
- Completeness
- 100 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source