Qwen 3 MoE Small
Alibaba
Qwen 3 with mixture-of-experts
Text Generation API Qwen Family
Parameters
-
params
Context Window
128K
tokens
Max Output
8K
tokens
Input Price
$0.2
per 1M tokens
Output Price
$0.6
per 1M tokens
Qwen Family 14 models
The full Qwen line by generation — pricing and capabilities vary across the family.
3.5
3.5 35B-A3B
Efficient inference, agentic tasks, edge deployment
262K
context
3.5 27B
Reasoning, coding, analysis, multimodal
262K
context
3.5 Plus
AI agents, multilingual tasks, reasoning, multimodal
$0.4 / $2.4
in / out · 1M
3.5 9B
General-purpose, coding, reasoning, multilingual
262K
context
3
3 Max
Flagship Qwen 3, agent tasks
$1 / $3
in / out · 1M
3 MoE Large
Advanced reasoning, agents
$0.8 / $2.4
in / out · 1M
3 MoE Small Current
Hybrid reasoning, MoE architecture
$0.2 / $0.6
in / out · 1M
Alibaba
Capabilities
👁️
Vision
⚡
Function Calling
📋
JSON Mode
🌊
Streaming
💬
System Prompt
🖥️
Code Execution
🔍
Web Search
🔌
MCP Support
Details
- Release Date
- April 15, 2025
- Knowledge Cutoff
- September 1, 2024
- Source
- API
- API Key Required
- Yes
- License
- Proprietary
- Model ID
- qwen3-moe-small
Last updated: November 26, 2025