/ Models

Language models

Qwen: Qwen3.6 Flash

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...

Maker
Qwen
Context window
1M
Max output
66K
Input / 1M
$0.188
Output / 1M
$1.13
1M in + 1M out
$1.31

Everything else

Max output66K
Input / 1M$0.188
Output / 1M$1.13
Cache read / 1M
Cache write / 1M$0.234
1M in + 1M out$1.31
Takestext, image, video
Returnstext
Toolsyes
Reasoningoptional
Open weightsno
Released2026-04-27
Knowledge cutoff
Retires
Catalog idqwen/qwen3.6-flash

Benchmarks

sourceepoch
eci144.2
confidenceUnverified
gpqa0.844
gpqaStderr0.0211
frontierMath0.103
frontierMathStderr0.0179
aime0.861
aimeStderr0.0474
simpleQA0.212
simpleQAStderr0.0129

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