Back to Models

Qwen3 Max Thinking (Preview)

Alibaba
32/ 57

Intelligence Score

Intelligence

32

#46 of 210 (top 22%)

Speed

42 tok/s

#121 of 148

Price

$2.40

per M tokens

#115 cheapest of 144

Context Window

262K

tokens

Latency: 4ms (#120)

Score Breakdown

Quality Score56%
Speed Score7%
Cost Score76%

Similar Models

Qwen3.5 9B

Alibaba

32intelligence

K-EXAONE

LG AI Research

32intelligence

DeepSeek V3.2

DeepSeek

32intelligence

Grok 3 mini Reasoning (high)

xAI

32intelligence

Nova 2.0 Pro Preview (low)

Amazon

32intelligence

Use This Model

Claude Code

claude --model qwen3-max-thinking-preview

API (cURL)

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "qwen3-max-thinking-preview",
    "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-max-thinking-preview"),
  prompt: "Hello",
});
Back to Models