/ Models

Language models

Qwen: Qwen3.6 Plus

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...

Maker
Qwen
Context window
1M
Max output
66K
Input / 1M
$0.325
Output / 1M
$1.95
1M in + 1M out
$2.27

Everything else

Max output66K
Input / 1M$0.325
Output / 1M$1.95
Cache read / 1M
Cache write / 1M$0.406
1M in + 1M out$2.27
Takestext, image, video
Returnstext
Toolsyes
Reasoningoptional
Open weightsno
Released2026-04-02
Knowledge cutoff
Retires
Catalog idqwen/qwen3.6-plus

Benchmarks

sourceepoch
eci149.17
confidenceConfident
accessibilityAPI access
gpqa0.874
gpqaStderr0.019
sweBenchVerified0.579
sweBenchVerifiedStderr0.0225
frontierMath0.262
frontierMathStderr0.0259
aime0.906
aimeStderr0.0367
simpleQA0.491
simpleQAStderr0.0158

Benchmark scores by Epoch AI, CC BY 4.0.

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models