QwQ 32B

AlibabaMCP Tool CallReasoning
alibaba/qwq-32bOpen Weights

Open reasoning model from the Qwen team for math, coding, and step-by-step problem solving

Benchmark Pricing$0.40 / 1M in$0.40 / 1M out
Context: 131,072 tokens•Max Output: 8,192 tokens•Knowledge: 2024-04•Released: 2025-03-05

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens
Max Output8,1928.2K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ QwQ 32B natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling QwQ 32B via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ALIBABA_API_KEY,
});

const response = await client.chat.completions.create({
  model: "alibaba/qwq-32b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);

PRICING BY PROVIDER

3 providers
AbacusQwen/QwQ-32B
$0.40 / $0.40
Alibaba (China)qwq-32b
$0.29 / $0.86
Cloudflare Workers AI@cf/qwen/qwq-32b
$0.66 / $1.00

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.