Qwen3
language modelAlibaba (Qwen)
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,… License: apache-2.0.
Key facts
| Made by | Alibaba (Qwen) |
|---|---|
| Type | language model |
| Released | April 27, 2025 |
| License | apache-2.0 |
| Reads at once | 262,144 tokens |
| Price (API, per million tokens) | $0.1 in · $0.3 out |
| Input → output | text → text |
| Sizes | 32B, 4B, 30B, 235B, 14B |
| Downloads (recent) | 2.9M |
| Likes on Hugging Face | 1K |
Questions about Qwen3
Who makes Qwen3?
Qwen3 is made by Alibaba (Qwen).
When was Qwen3 released?
We first saw Qwen3 listed on April 27, 2025.
How much does Qwen3 cost?
Through OpenRouter it costs $0.1 per million input tokens and $0.3 per million output tokens. Prices change, so check the provider before you build on it.
How much text can Qwen3 read at once?
Up to 262,144 tokens, roughly 196.6K words.
More from Alibaba (Qwen)
Other language models
Modelcast collects this page automatically from public sources (Hugging Face, OpenRouter). Facts are copied from those sources, not written by the maker. Not affiliated with Alibaba (Qwen).