Qwen
Qwen3.5 Plus 2026-02-15
Released 2026-02-16
The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...
You send / 1M
$0.260
tokens in
It replies / 1M
$1.56
tokens out
Memory
1M
tokens it can read at once
Typical request
$0.0011
1,000 words in, 400 out
Data privacy
No training or retention: Unknown. Check the provider's terms before sending sensitive data.
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text, image, video
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 66K tokens
Similar models
- Perceptron Mk1.5Perceptron · $0.150 in / $1.50 out per 1M
- Command A+Cohere · $0.300 in / $1.50 out per 1M
- Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google · $0.250 in / $1.50 out per 1M
- Perceptron Mk1Perceptron · $0.150 in / $1.50 out per 1M
- Gemini 3.1 Flash LiteGoogle · $0.250 in / $1.50 out per 1M
- Gemini 3.1 Flash Lite PreviewGoogle · $0.250 in / $1.50 out per 1M