/ Models

Language models

Qwen: Qwen3.6 35B A3B

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

Maker
Qwen
Context window
262K
Max output
262K
Input / 1M
$0.14
Output / 1M
$1
1M in + 1M out
$1.14

Everything else

Max output262K
Input / 1M$0.14
Output / 1M$1
Cache read / 1M
Cache write / 1M
1M in + 1M out$1.14
Takestext, image, video
Returnstext
Toolsyes
Reasoningoptional
Open weightsyes
Released2026-04-27
Knowledge cutoff
Retires
Catalog idqwen/qwen3.6-35b-a3b

Benchmarks

sourceepoch
eci143.31
confidenceUnverified
accessibilityOpen weights (unrestricted)

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