Back to Models

Qwen3 Next 80B A3B

![Alibaba](https://artificialanalysis.ai/img/logos/alibaba_small.svg)Alibaba
27/ 57

Intelligence Score

Intelligence

27

#99 of 212 (top 47%)

Speed

172 tok/s

#28 of 141

Price

$1.88

per M tokens

#106 cheapest of 142

Context Window

262K

tokens

Latency: 2ms (#87)

Score Breakdown

Quality Score45%
Speed Score22%
Cost Score83%

Similar Models

Qwen3.5 9B

![Alibaba](https://artificialanalysis.ai/img/logos/alibaba_small.svg)Alibaba

27intelligence

Magistral Medium 1.2

![Mistral](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Fmistral_small.png&w=32&q=75)Mistral

27intelligence

Gemma 4 26B A4B

![Google](https://artificialanalysis.ai/img/logos/google_small.svg)Google

27intelligence

Qwen3.5 4B

![Alibaba](https://artificialanalysis.ai/img/logos/alibaba_small.svg)Alibaba

27intelligence

DeepSeek R1 0528

![DeepSeek](https://artificialanalysis.ai/img/logos/deepseek_small.svg)DeepSeek

27intelligence

Use This Model

Claude Code

claude --model qwen3-next-80b-a3b-reasoning

API (cURL)

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "qwen3-next-80b-a3b-reasoning",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Vercel AI SDK

import { generateText } from "ai";
import { openrouter } from "@openrouter/ai-sdk-provider";

const { text } = await generateText({
  model: openrouter("qwen3-next-80b-a3b-reasoning"),
  prompt: "Hello",
});
Back to Models