Back to Models

Qwen: Qwen3.5 Plus 2026-02-15

qwen/qwen3.5-plus-02-15
Feb 16, 20261M context65.5K max output$0.40/M in · $2.40/M outReasoning

Description

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 task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.

Specifications

Provider
qwen
Context Length
1M
Max Output
65.5K
Modality
Intextimagevideo
Outtext

Pricing

Type≤256K>256K
Input$0.40$0.50
Output$2.40$3.00
Cache Write$0.50$0.63

Quick Start

curl https://api.ominigate.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-omg-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.5-plus-02-15",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Qwen: Qwen3.5 Plus 2026-02-15 — Pricing & API on OminiGate