Qwen3 Thinking

language modelAlibaba (Qwen)

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

Try it on OpenRouter

Key facts

Made byAlibaba (Qwen)
Typelanguage model
ReleasedJuly 25, 2025
Reads at once128,000 tokens
Price (API, per million tokens)$0.45 in · $3.5 out
Input → outputtext → text
Sizes235B

Questions about Qwen3 Thinking

Who makes Qwen3 Thinking?

Qwen3 Thinking is made by Alibaba (Qwen).

When was Qwen3 Thinking released?

We first saw Qwen3 Thinking listed on July 25, 2025.

How much does Qwen3 Thinking cost?

Through OpenRouter it costs $0.45 per million input tokens and $3.5 per million output tokens. Prices change, so check the provider before you build on it.

How much text can Qwen3 Thinking read at once?

Up to 128,000 tokens, roughly 96K words.

More from Alibaba (Qwen)

Qwen3.8Alibaba (Qwen) · language model
Aug 5, 2026released
Qwen3 VLAlibaba (Qwen) · language model
Sep 23, 2025released
Qwen2.5 VLAlibaba (Qwen) · language model
Jan 26, 2025released
Qwen3.6Alibaba (Qwen) · language model
Apr 15, 2026released
Qwen3.8-Flash-NextAlibaba (Qwen) · vision and multimodal model
Aug 24, 2026released
Qwen3Alibaba (Qwen) · language model
Apr 27, 2025released

Other language models

gpt2Openai Community · language model
Mar 2, 2022released
Qwen3.8Alibaba (Qwen) · language model
Aug 5, 2026released
Qwen3 VLAlibaba (Qwen) · language model
Sep 23, 2025released
Qwen2.5 VLAlibaba (Qwen) · language model
Jan 26, 2025released
optMeta · language model
May 11, 2022released
Qwen3.6Alibaba (Qwen) · language model
Apr 15, 2026released
Ollamaollama · language model
Jun 26, 2023released
pythiaEleutherAI · language model
Feb 8, 2023released

Modelcast collects this page automatically from public sources (OpenRouter). Facts are copied from those sources, not written by the maker. Not affiliated with Alibaba (Qwen).