RealRelay.ai
Qwen

Qwen-VL-Plus

Qwen vision-language model that accepts image and text input and replies in text.

Starting at
Input
$0.21/ 1M
Output
$0.63/ 1M
Open dashboard

Channel

Each channel is compared at its lowest input-price tier; output breaks ties. A dash means /api/pricing does not provide that rate. Selecting a channel updates the endpoints and call example below.

qwen/qwen-vl-plus
Input
$0.21 USD per 1M tokens
Output
$0.63 USD per 1M tokens
Cache read
$0.042 USD per 1M tokens
Cache write
- USD per 1M tokens

Endpoints

POST/v1/chat/completionsChat Completions

Call it

Using qwen/qwen-vl-plus

1from openai import OpenAI23client = OpenAI(4    base_url="https://www.realrelay.ai/v1",5    api_key="sk-***",6)78response = client.chat.completions.create(9    model="qwen/qwen-vl-plus",10    messages=[{"role": "user", "content": "Hello"}],11)1213print(response.choices[0].message.content)
1import OpenAI from "openai";23const client = new OpenAI({4  baseURL: "https://www.realrelay.ai/v1",5  apiKey: process.env.REALRELAY_API_KEY,6});78const response = await client.chat.completions.create({9  model: "qwen/qwen-vl-plus",10  messages: [{ role: "user", content: "Hello" }],11});1213console.log(response.choices[0].message.content);
1curl https://www.realrelay.ai/v1/chat/completions \2  -H "Authorization: Bearer $REALRELAY_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "model": "qwen/qwen-vl-plus",6    "messages": [{ "role": "user", "content": "Hello" }]7  }'

Prices and availability as published on Oct 12, 2026.

Capabilities

Qwen-VL-Plus takes image and text input and returns text. Typical requests ask it to caption an image, answer a question about a screenshot or pull out the words printed in a photo.

Cached input is billed at $0.042 per 1M tokens, lower than regular input, so repeated instructions placed before an image cost less.

Input
TextImage
Output
Text

Overview

Qwen-VL-Plus is a vision-language model from Alibaba Cloud's Qwen family. It accepts images together with text and returns text, so it can caption pictures, answer questions about them and read the text they contain. Alibaba Cloud groups it with its image understanding models. It is priced at $0.21 per 1M input tokens and $0.63 per 1M output tokens.

It accepts text and image input and returns text.

Pricing

Qwen-VL-Plus is priced per 1M tokens at $0.21 for input and $0.63 for output, with cached input at $0.042.

Qwen-VL-Plus is available through RealRelay's OpenAI-compatible API.

Use cases

Use Qwen-VL-Plus for image captioning and visual question answering, for example labeling photos in a media library or answering a customer's question about a picture they uploaded.

It also suits OCR-style tasks such as reading text from photographed documents, receipts or signs and returning it as plain text for search or data entry.

Frequently asked questions

What is Qwen-VL-Plus?
Qwen-VL-Plus is a vision-language model from Alibaba Cloud's Qwen family. It accepts images together with text and returns text, so it can caption pictures, answer questions about them and read the text they contain.
How much does Qwen-VL-Plus cost?
Qwen-VL-Plus costs $0.21 per 1M input tokens and $0.63 per 1M output tokens, and cached input is $0.042 per 1M tokens.
What inputs and outputs does Qwen-VL-Plus support?
Qwen-VL-Plus accepts text and image input and returns text.
What is Qwen-VL-Plus used for?
Qwen-VL-Plus is used for image captioning, visual question answering and reading text from photos, with text as the output.
How do I call Qwen-VL-Plus through the API?
Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen-vl-plus.

More from Qwen

All 41 Qwen models