# Qwen3.5-Plus

> Plus tier of Alibaba's Qwen3.5 series: a reasoning model that reads images, text and video.

## Key facts

- Model author: Qwen
- Input: $0.1143 per 1M tokens (starting tier)
- Output: $0.6857 per 1M tokens (starting tier)
- Cached input: $0.0114 per 1M tokens
- Context window: 1,000,000 tokens
- Maximum output: 64,000 tokens
- Input modalities: image, text, video
- Output modalities: text
- Capabilities: reasoning, structured_output, tools, vision
- Released: 2026-02-15
- Model IDs: `jd/qwen3.5-plus`, `qwen/qwen3.5-plus`
- Model page: https://www.realrelay.ai/model/qwen/qwen3.5-plus

## Overview

Qwen3.5-Plus is the Plus tier of Alibaba's Qwen3.5 series, a reasoning model that accepts image, text and video input and returns text. It supports tool calling and structured output, so one model can look at visual content and then call tools or answer in a fixed format.

It has a 1M-token context window and can generate up to 64,000 output tokens. It accepts text, image and video input and returns text. It was released on February 15, 2026.

## Capabilities

Qwen3.5-Plus supports tool calling, reasoning, structured output and vision. It accepts text, image and video input and returns text.

Alibaba documents function calling for the Qwen3.5 series, so the model can act on image or video content, and structured output in non-thinking mode, such as valid JSON from a visual input.

## Pricing

Pricing for Qwen3.5-Plus starts from $0.1143 per 1M input tokens and $0.6857 per 1M output tokens, with cache reads from $0.0114 per 1M tokens. Pricing is tiered, so these figures are the starting tier. Qwen3.5-Plus is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Qwen3.5-Plus for multimodal assistants that answer questions about screenshots, photos and video, and for agents that call tools based on what they see.

The 1M-token context window suits long documents and extended conversations, and structured output helps when results feed a database or another program. Tool calling lets an agent act on what the model reads in an image.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen/qwen3.5-plus", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Qwen3.5-Plus?

Qwen3.5-Plus is the Plus tier of Alibaba's Qwen3.5 series, a reasoning model that accepts image, text and video input and returns text.

### How much does Qwen3.5-Plus cost?

Pricing for Qwen3.5-Plus starts from $0.1143 per 1M input tokens and $0.6857 per 1M output tokens, with cache reads from $0.0114 per 1M tokens. Pricing is tiered, so these figures are the starting tier.

### What is the context window of Qwen3.5-Plus?

Qwen3.5-Plus has a 1M-token context window and can generate up to 64,000 output tokens.

### What inputs and outputs does Qwen3.5-Plus support?

Qwen3.5-Plus accepts text, image and video input and returns text.

### Does Qwen3.5-Plus support tool calling?

Yes. Qwen3.5-Plus supports tool calling, reasoning, structured output and vision.

### When was Qwen3.5-Plus released?

Qwen3.5-Plus was released on February 15, 2026.

### How do I call Qwen3.5-Plus via the API?

Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen3.5-plus to use Qwen3.5-Plus.