AlibabaQwenTool use

Qwen3 235B A22B pricing

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and code tasks, and a "non-thinking" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token c. Live index: 5 priced offers. Best input $0.180 per million tokens from DeepInfra. Best output $0.540 per million tokens from DeepInfra.

41K context·5 providers·verified Apr 7, 2026
Best input$0.180per 1M tokens · DeepInfra
Best output$0.540per 1M tokens · DeepInfra

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 5 offers are listed for Qwen3 235B A22B. Best input in this view: DeepInfra.

O
Openrouter
Input / 1M
$0.455
Output / 1M
$1.82
N
Nebius
Input / 1M
$0.200
Output / 1M
$0.600
H
Hyperbolic
Input / 1M
$2.00
Output / 1M
$2.00
FA
Fireworks AI
Input / 1M
$0.220
Output / 1M
$0.880
D
DeepInfra
Input / 1M
$0.180
Output / 1M
$0.540

Input vs output · per provider

Cost calculator

The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how Qwen3 235B A22B cost scales with traffic.

Provider

In: $0.455/M·Out: $1.82/M

0.045500¢ / req

0.091000¢ / req

Daily
$14
Monthly
$410
Annual
$5.0K

Model specifications

Context length, caps, and capability flags for Qwen3 235B A22B. Family: Qwen. Values follow the main provider (Alibaba) record in our index.

Context window
40,960 tokens
Max output
40,960 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
Apr 2025
Primary provider
Alibaba
Model family
Qwen

Compare Qwen3 235B A22B

These links open full side by side pages for Qwen3 235B A22B. We picked pairs that people often shop together. 6 ready to open.

Frequently asked questions

Quick frequently asked items for Qwen3 235B A22B pricing and limits. The short model note from our index: Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and ...

Yes. Qwen3 235B A22B is available on Openrouter, Nebius, Hyperbolic, Fireworks AI, DeepInfra.

Also from Alibaba

Other models by Alibaba with live pricing in our catalog.