Models / QwQ 32B

QwQ 32B

Tier 1Apache-2.0

Dedicated reasoning model. Competitive with DeepSeek-R1 and o1-mini on math, logic, and code reasoning tasks.

qwen/qwq-32b

Context Window

33K

Max Output

16K

Providers

Released

2025-03

Capabilities

ChatCodeReasoningThinkingStreaming

Pricing by Provider

Prices shown are the official rate published by the model provider, before any platform discounts. Your actual rate may be lower based on your account's discount tier.

Provider	Price	Latency p50	Latency p95	Status
alibaba	$0.80 /M in · $2.40 /M out	400ms	1200ms

Quick Start

Python

import magicrouter

mr = magicrouter.Client(
    provider_keys={"alibaba": "your-api-key"}
)

response = mr.chat(
    "qwen/qwq-32b",
    "Your prompt here"
)
print(response.choices[0].message.content)

TypeScript

import { MagicRouter } from "magicrouter";

const mr = new MagicRouter({
  providerKeys: { alibaba: "your-api-key" }
});

const response = await mr.chat({
  model: "qwen/qwq-32b",
  messages: [{ role: "user", content: "Your prompt here" }]
});
console.log(response.choices[0].message.content);

cURL

curl https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwq-plus",
    "messages": [{"role": "user", "content": "Your prompt here"}]
  }'

Use this model

Get Started