modelgrep
Q

Qwen: Qwen3.5 Plus 2026-02-15

qwen/qwen3.5-plus-02-15

ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
Design Elo
1234
UI Component
Speed
36
211th fastest
Latency
1.8s
first token
Input price
$0.260
118th cheapest
Context
1M
66K max out

How it compares

Faster than29%
of all ranked models
Cheaper than60%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Design Arena · Elo9,621 tournaments
UI Component
1234
Website
1232
codecategories
1219
3D
1201
Data Viz
1179
Game Dev
1175
svg
1165
asciiart
1136

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Alibaba$0.260$1.56100%

Specifications

Context window1M
Max output66K
Knowledge cutoff
Input modalitiestext, image, video
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Qwen3.5 Plus 2026-02-15 FAQ

How much does Qwen3.5 Plus 2026-02-15 cost?

Qwen3.5 Plus 2026-02-15 costs $0.260 per million input tokens and $1.56 per million output tokens via OpenRouter, making it 118th cheapest of 298 paid models.

How fast is Qwen3.5 Plus 2026-02-15?

Qwen3.5 Plus 2026-02-15 generates around 36 tokens per second with 1.8s time-to-first-token (p50), the 211th fastest tracked model.

What is Qwen3.5 Plus 2026-02-15's context window?

Qwen3.5 Plus 2026-02-15 supports a 1M-token context window and can output up to 66K tokens. It accepts text, image, video input.

Compare head-to-head