🎉 Early adopter bonus: $10 free credits for the first 100 users!Sign up now
Qwen 3.5 · 3.6 · QwQ · Coder · VL · 47 models, 0% fee

Access the world's fastest-improving
Qwen model family

47 Qwen models from 0.8B to 480B parameters — language, code, vision, reasoning, and TTS. Zero platform fee. Multi-provider failover. One unified API.

Available Models

Chat, code, vision, reasoning, image & video generation — all through one platform.

Chat

Qwen3.6 Plus

Best balance of speed and quality. #1 most-used model on OpenRouter.

qwen3.6-plus
Code

Qwen3 Coder Plus

Top coding model. Generation, completion, and refactoring across 80+ languages.

qwen3-coder-plus
Image Gen

Qwen Image 2.0 Pro

High-quality text-to-image generation with strong text rendering.

qwen-image-2.0-pro
Video Gen

Wan 2.7 T2V

Text-to-video generation with audio support. 2-15 seconds at up to 1080P.

wan2.7-t2v

See It in Action

Watch videos generated through Qwen models on MagicRouter.

Qwen Models Are Top-Ranked Globally

Independent benchmarks confirm Qwen as the leading open-weight model family.

BenchmarkQwen3.5 397BGPT-4.1Claude Opus 4.6Gemini 2.5 Pro
MMLU88.590.289.589.8
GPQA Diamond88.4 #1 open66.388.584.0
AIME 202581.599.895.0
SWE-bench Verified76.454.680.8
IFBench76.5 #158.0
BFCL-V4 (Tool Use)72.9 #163.3
#1
Open-Weight GPQA Diamond

Qwen3.5-397B scores 88.4 — the highest GPQA Diamond score from any open-weight model

#1
Tool Use & Instruction Following

Leads BFCL-V4 at 72.9 and IFBench at 76.5, beating both closed and open models

9B > 120B
Compact Efficiency

Qwen3.5-9B beats OpenAI's GPT-OSS-120B on MMLU-Pro (82.5 vs 80.8)

Qwen3.5 leads in tool use and instruction following. Claude Opus 4.6 leads in math reasoning (AIME) and software engineering (SWE-bench). GPT-4.1 leads in MMLU knowledge.

Qwen 3.6 Plus Is the #1 Most-Used Model

Live usage rankings from OpenRouter — the largest multi-model API gateway processing 20T+ tokens/week.

RankModelProviderWeekly TokensTrend
1Qwen3.6 PlusAlibaba5.53TNEW
2MiMo V2 ProXiaomi2.41T+42%
3Qwen3.6 Plus PreviewAlibaba1.62T+9,088%
4Step 3.5 FlashStepfun1.25T+15%
5DeepSeek V3.2DeepSeek1.19T+4%
6MiniMax M2.7MiniMax1.18T+10%
7Claude Sonnet 4.6Anthropic1.03T+2%
8Claude Opus 4.6Anthropic1.0T+2%
9Gemini 3 FlashGoogle996B+2%
10MiniMax M2.5MiniMax918B+10%
#1 & #3
Two Qwen models in top 3

Qwen3.6 Plus took #1 within days of launch — 5.53T tokens/week

700M+
Hugging Face Downloads

Most downloaded open-source LLM family, surpassing Meta Llama

90,000+
Enterprises Using Qwen

Deployed via Alibaba Cloud Model Studio for production workloads

Source: OpenRouter Live Rankings · Digital Applied Analysis · Open Source For You Rankings reflect rolling 7-day token volume as of April 2026.

Why Qwen on MagicRouter?

Get the best of open-weight AI with zero platform fees and smart routing.

0%
Platform Fee

on all 47 Qwen models

0ms
Added Latency

Client-side routing, no proxy

3+
Providers per Model

Alibaba, Together, DeepInfra & more

Auto
Failover & Cost Routing

Always the cheapest healthy provider

47
Qwen Models
6
Model Families
0.8B—480B
Parameter Range
1M
Max Context
85+
Total Models (incl. Tier 2)

Build with the best open-weight models. Zero fees.

Free tier available. No credit card required.

MagicRouter — The Qwen-first model router for builders