/ Models

Language models

Qwen: Qwen3.7 Max

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...

Maker
Qwen
Context window
1M
Max output
66K
Input / 1M
$1.48
Output / 1M
$4.42
1M in + 1M out
$5.90

Everything else

Max output66K
Input / 1M$1.48
Output / 1M$4.42
Cache read / 1M$0.295
Cache write / 1M$1.84
1M in + 1M out$5.90
Takestext
Returnstext
Toolsyes
Reasoningoptional
Open weightsno
Released2026-05-21
Knowledge cutoff
Retires
Catalog idqwen/qwen3.7-max

Benchmarks

sourceepoch
eci153.09
confidenceConfident
accessibilityAPI access
gpqa0.916
gpqaStderr0.0168
sweBenchVerified0.773
sweBenchVerifiedStderr0.0191
aime0.95
aimeStderr0.0274
simpleQA0.585
simpleQAStderr0.0156

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