Qwen3 32B (Qwen)

View on Alibaba Cloud View on Hugging Face View on DeepInfra View on OpenRouter

Identity and capabilities

Status: active
Local execution: Available weights · transformers · apache-2.0 Hardware requirements and licence restrictions apply.
Context window: 40,960
Maximum output: 16,384
Image input: No
Reasoning: Yes
Tool calling: Yes
Release date: Apr 29, 2025
First seen: 2026-08-29 19:40:01Z UTC
Last verified: 1 min ago

Current offers - prices in USD · per 1M tokens

Prices by provider, service tier, context and offer route
	Amazon Bedrock	DeepInfra	Hugging Face Inference Providers ⊕ 2 routes ▾	OpenRouter	Alibaba / Qwen
Standard			Nscale		Default offer · Thinking mode
Input	$0.15	$0.08	$0.08	$0.08	$0.16
Output	$0.6	$0.28	$0.25	$0.28	$0.64
Flex
Input	$0.075	—	—	—	—
Output	$0.3	—	—	—	—
Priority
Input	$0.2625	—	—	—	—
Output	$1.05	—	—	—	—

Hugging Face Inference Providers · 2 routes — show all prices

The main table shows Nscale: the lowest available starting token price for 2 input tokens per output token. Other input lengths, service tiers and usage ratios may favour another route.

Prices by provider, service tier, context and offer route
	Nscale	DeepInfra
Input	$0.08	$0.08
Output	$0.25	$0.28

Active promotions

No officially confirmed promotion applies to this model.

Recent price changes

No price changes in the last 7 days.