Qwen3 235B A22B (Qwen)

View on Alibaba Cloud View on Hugging Face View on OpenRouter

Verified provider routes accept text input and produce text output. Supported combinations depend on the provider route.

Source 1 · Source 2

Identity and capabilities

Status: active
Local execution: Available weights · transformers · apache-2.0 Hardware requirements and licence restrictions apply.
Context window: 131,072
Maximum output: 8,192
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
	Hugging Face Inference Providers ⊕ 2 routes ▾	OpenRouter	Alibaba / Qwen
Standard	Nscale
Input	$0.2	$0.455	Default offer · Thinking mode $0.7
Output	$0.6	$1.82	Default offer $2.8
Output	—	—	Thinking mode $8.4

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	Novitaunconfirmed
Input	$0.2	$0.2
Output	$0.6	$0.8

Active promotions

No officially confirmed promotion applies to this model.

Recent price changes

No price changes in the last 7 days.