/ Models

Language models

Qwen: Qwen3.5-Flash

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...

Maker
Qwen
Context window
1M
Max output
66K
Input / 1M
$0.065
Output / 1M
$0.26
1M in + 1M out
$0.325

Everything else

Max output66K
Input / 1M$0.065
Output / 1M$0.26
Cache read / 1M
Cache write / 1M
1M in + 1M out$0.325
Takestext, image, video
Returnstext
Toolsyes
Reasoningoptional
Open weightsno
Released2026-02-25
Knowledge cutoff
Retires
Catalog idqwen/qwen3.5-flash-02-23

Benchmarks

sourceepoch
gpqa0.838
gpqaStderr0.022
frontierMath0.062
frontierMathStderr0.0142
aime0.856
aimeStderr0.046
simpleQA0.198
simpleQAStderr0.0126

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