ZMIME
Alibaba (Qwen) · Released Mar 5, 2025

QwQ 32B

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

  • Open weights
  • Reasoning
  • Tool calling
Capability
136.5ECI · #122 of 158
Input
$0.53per 1M tokens
Output
$0.70per 1M tokens
Context
131K8K max output
Pricing

What it costs

Input
$0.53per million tokens
Output
$0.70per million tokens
Blended (3:1)
$0.573cheaper than 54% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$1.41
Team assistant25M input + 5M output tokens$16.75
Production app250M input + 50M output tokens$167.50

Median of 2 paid API providers on models.dev.

Capability

Independent benchmarks

136.5Epoch Capabilities Index
#122 of 158 scored models
68Median 147174

The shaded band is Epoch AI’s confidence range (133.7–139.2); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions65.3%
  • OTIS Mock AIME 2024–2025Competition mathematics59.2%

Scores from Epoch AI, run independently of Alibaba (Qwen).

Specifications

The details

Lab
Alibaba (Qwen)
Released
Mar 5, 2025
Knowledge cutoff
Apr 2024
Context window
131,072 tokens
Max output
8,192 tokens
Inputs
Text
Output
Text
Reasoning
Always on
Tool calling
Yes
Structured output
No
Availability
2 API providerslisted on models.dev
Same lab

More from Alibaba (Qwen)

Questions

About QwQ 32B

How much does QwQ 32B cost?

QwQ 32B costs $0.53 input / $0.70 output per million tokens (median across 2 API providers). At a 3:1 input-to-output mix that is $0.573 per million tokens, cheaper than 54% of the 469 priced models we track.

What is the context window of QwQ 32B?

QwQ 32B accepts up to 131,072 tokens per request and can write up to 8,192 tokens in one response.

How good is QwQ 32B?

Epoch AI gives QwQ 32B a Capabilities Index score of 136.5 (likely range 133.7–139.2), ranking it #122 of 158 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 65.3%, OTIS Mock AIME 2024–2025 59.2%.

Is QwQ 32B open source?

Yes. Alibaba (Qwen) publishes the weights, so it can be downloaded and self-hosted.

What inputs does QwQ 32B support?

QwQ 32B accepts text and replies in text. It is a reasoning model, supports tool calling.

When was QwQ 32B released?

Alibaba (Qwen) released QwQ 32B on Mar 5, 2025. Its training data runs to Apr 2024.

What are the best alternatives to QwQ 32B?

The closest current models from other labs on capability, price and release date are DeepSeek V3 0324 (DeepSeek, ECI 135.3, $0.275 / $1.12), GPT-4.1 mini (OpenAI, ECI 134.3, $0.40 / $1.60), Llama 4 Maverick 17B Instruct (Meta, ECI 132.2, $0.27 / $0.86) and Gemini 2.5 Flash (Google, ECI 140.8, $0.30 / $2.50).