Back

Qwen: Qwen3 235B A22B

Qwen3
Input: text
Output: text
Released: Apr 28, 2025Updated: May 11, 2025

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 context window and extends up to 131K tokens using YaRN-based scaling.

40,960 Token Context

Process and analyze large documents and conversations.

Hybrid Reasoning

Choose between rapid responses and extended, step-by-step processing for complex tasks.

Advanced Coding

Improved capabilities in front-end development and full-stack updates.

Agentic Workflows

Autonomously navigate multi-step processes with improved reliability.

Available On

ProviderModel IDContextMax OutputInput CostOutput CostThroughputLatency
DeepInfradeepInfra41K41K$0.13/M$0.60/M22.0 t/s1384 ms
Parasailparasail41K41K$0.13/M$0.85/M62.0 t/s972 ms
KlusterklusterAi41K41K$0.14/M$2.00/M42.5 t/s1594 ms
GMICloudgmiCloud33K-$0.17/M$1.09/M61.6 t/s931 ms
Togethertogether41K-$0.20/M$0.60/M27.2 t/s1178 ms
NebiusnebiusAiStudio41K-$0.20/M$0.60/M29.5 t/s819 ms
NovitanovitaAi41K20K$0.20/M$0.80/M23.0 t/s1624 ms
Fireworksfireworks128K-$0.22/M$0.88/M68.1 t/s799 ms
Standard Pricing
Input Tokens
$0.00000013

per 1K tokens

Output Tokens
$0.0000006

per 1K tokens

Do Work. With AI.