Alibaba (Qwen)

Qwq 32B

Generally availableOpen weights24K contextReasoning

Summary

Qwq 32B is an open-weight language model from Alibaba (Qwen), released on 5 Mar 2025. It accepts text and generates text, with a 24K-token context window and up to 24K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.66 per million input tokens and $1 per million output tokens (Cloudflare Workers AI), across 1 provider we track.

Qwen reasoning model for deliberate problem solving, math, and coding

Last verified 4 Oct 2026. Every figure on this page links to its source.

Specifications

DeveloperAlibaba (Qwen)
Release date5 Mar 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [models.dev]
Context window24K (24,000 tokens) [models.dev]
Max output24K tokens [models.dev]
Knowledge cutoffApr 2024 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingNo [models.dev]
Structured outputNo [models.dev]

Qwq 32B API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Cloudflare Workers AI
@cf/qwen/qwq-32b
$0.66$1–24Kmodels.dev, 4 Oct 2026

Frequently asked questions

What is the context window of Qwq 32B?

Qwq 32B has a context window of 24,000 tokens (24K) and can generate up to 24,000 tokens in a single response, according to models.dev.

How much does the Qwq 32B API cost?

Qwq 32B is listed from $0.66 per million input tokens and $1 per million output tokens (Cloudflare Workers AI). Prices last verified 4 Oct 2026.

Is Qwq 32B open source?

Qwq 32B is an open-weight model. Check the license terms before commercial use.

When was Qwq 32B released?

Alibaba (Qwen) released Qwq 32B on 5 Mar 2025, according to models.dev.

Change history

No changes detected since we started tracking this model. We re-check every source daily.

Sources