Skip to content
Seedance 2.0 Face is here — generate video from real-person reference photos.Try it now →
Back to Models
qwenqwen·Apr 2, 2026

Qwen: Qwen3.6 Plus

qwen/qwen3.6-plus
context
1M
Max Output
65.5K
Input / 1M
$0.50
Output / 1M
$3.00

About

Qwen3.6 Plus is Alibaba's flagship model built on a hybrid architecture that combines efficient linear attention with sparse Mixture-of-Experts (MoE) routing for scalable, high-performance inference. Compared with the 3.5 series, it delivers gains in agentic coding, front-end development, and overall reasoning, and handles complex tasks such as 3D scenes, games, and repository-level problem solving. It scores 78.8 on SWE-bench Verified. The model accepts text, image, and video input with text output, supports reasoning, and provides a 1M token context window with up to 65K output tokens.

Capabilities

Context Length
1M
Max Output
65.5K
Reasoning
Yes
In
text, image, video
Out
text

Benchmarks

View leaderboard
39.6#28 of 133
Intelligence Index
42.9#30 of 118
Coding Index

Reasoning & Knowledge

GPQA Diamond88.2%
HLE25.7%

Coding & Agentic

SciCode40.7%
Terminal-Bench Hard43.9%

Source: Artificial Analysis

Pricing

Full pricing
Type≤256K>256K
Input$0.50$2.00
Output$3.00$6.00
Cache Write$0.625$2.50

API

API reference

OpenAI-compatible · Model ID qwen/qwen3.6-plus

curl https://api.elliotgate.com/v1/chat/completions \
  -H "Authorization: Bearer sk-omg-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.6-plus",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

OFTEN COMPARED

Qwen3.6 Plus comparisons

Decide which model wins on the dimensions that matter for your workload — context, benchmarks, pricing, or serving latency.