QwenReleased on Jul 25, 2025

Qwen3-235B-A22B-Thinking-2507: Benchmarks, Pricing & Context Window

Qwen3-235B-A22B-Thinking-2507 is a language model from Qwen, released in July 2025.

Qwen3-235B-A22B-Thinking-2507 is a state-of-the-art thinking-enabled Mixture-of-Experts (MoE) model with 235B total parameters (22B activated). It features 94 layers, 128 experts (8 activated), and supports 262K native context length. This

Input
Text
Output
Text
Speed
—
Cost
$0.60/ 1M · 8:1 in:out
$0.30 in · $3.00 out

Qwen3-235B-A22B-Thinking-2507 pricing

Providers

Qwen3-235B-A22B-Thinking-2507 starts at $0.300 per million input tokens and $3.00 per million output tokens via Fireworks. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.

ProviderInput $/MOutput $/MMax InputMax OutputLatency sThroughputQuantInputOutput
Fireworks logoFireworks
$0.300$3.00262.1K131.1K
—
—
—
Novita logoNovita
$0.300$3.00256.0K32.8K
—
—
fp8
Loading chart...
Loading chart...
Loading chart...

Qwen3-235B-A22B-Thinking-2507 API

API access coming soon

Qwen3-235B-A22B-Thinking-2507 will be available through our gateway shortly.

Qwen3-235B-A22B-Thinking-2507 examples

Recent arena outputs from Qwen3-235B-A22B-Thinking-2507, picked from the highest-ranked matchups.

Qwen3-235B-A22B-Thinking-2507 license

Qwen3-235B-A22B-Thinking-2507 is released under the Apache 2.0 license, which permits commercial use, has 235.0B parameters.

License
Apache 2.0
Commercial use allowed
Parameters
235.0B

Apache License 2.0 - allows commercial use

FAQ

Common questions about Qwen3-235B-A22B-Thinking-2507.

When was Qwen3-235B-A22B-Thinking-2507 released?

Qwen3-235B-A22B-Thinking-2507 was released on July 25, 2025 by Qwen. This is the official Qwen3-235B-A22B-Thinking-2507 release date tracked on LLM Stats.

Is Qwen3-235B-A22B-Thinking-2507 available via API?

Yes, Qwen3-235B-A22B-Thinking-2507 is available via API. See the official documentation for authentication and endpoint details. It is served by 2 providers tracked on LLM Stats.

How many parameters does Qwen3-235B-A22B-Thinking-2507 have?

Qwen3-235B-A22B-Thinking-2507 has 235 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Qwen3-235B-A22B-Thinking-2507?

Qwen3-235B-A22B-Thinking-2507 was created by Qwen.

What is the license for Qwen3-235B-A22B-Thinking-2507?

Qwen3-235B-A22B-Thinking-2507 is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Where can I use Qwen3-235B-A22B-Thinking-2507?

Qwen3-235B-A22B-Thinking-2507 is available through 2 providers including Fireworks, Novita.

Where is the Qwen3-235B-A22B-Thinking-2507 paper or technical report?

Qwen3-235B-A22B-Thinking-2507 has a paper or technical report available at https://qwenlm.github.io/blog/qwen3-thinking/. Use that source for architecture, training, release and evaluation details.