RealRelay.ai
Qwen

Qwen-VL-Max

Qwen vision-language model that takes images and text as input and answers in text.

Starting at
Input
$0.80/ 1M
Output
$3.20/ 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-max
Input
$0.80 USD per 1M tokens
Output
$3.20 USD per 1M tokens
Cache read
$0.16 USD per 1M tokens
Cache write
- USD per 1M tokens

Endpoints

POST/v1/chat/completionsChat Completions

Call it

Using qwen/qwen-vl-max

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-max",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-max",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-max",6    "messages": [{ "role": "user", "content": "Hello" }]7  }'

Prices and availability as published on Oct 12, 2026.

Capabilities

Qwen-VL-Max accepts image and text input and returns text. That covers image analysis, answering questions about a picture and reading text inside images (OCR), the tasks Alibaba Cloud lists for its image understanding models.

Cached input is priced lower than regular input, which helps when the same prompt prefix is reused across many image requests.

Input
TextImage
Output
Text

Overview

Qwen-VL-Max is a vision-language model from Alibaba Cloud's Qwen family. It accepts images together with text and returns text, so it can describe, interpret and answer questions about visual content. Alibaba Cloud groups it with its image understanding models, whose documented tasks include image analysis and OCR. It is priced at $0.80 per 1M input tokens.

It accepts text and image input and returns text.

Pricing

Qwen-VL-Max is priced per 1M tokens at $0.80 for input and $3.20 for output, with cached input at $0.16.

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

Use cases

Use Qwen-VL-Max to analyze images: describe a photo, answer questions about a chart or screenshot, or extract the text from a scanned page or a sign.

In an application it can sit behind an upload form to review product photos or read document images and return text answers that downstream code or support staff can use.

Frequently asked questions

What is Qwen-VL-Max?
Qwen-VL-Max is a vision-language model from Alibaba Cloud's Qwen family. It accepts images together with text and returns text, so it can describe, interpret and answer questions about visual content.
How much does Qwen-VL-Max cost?
Qwen-VL-Max costs $0.80 per 1M input tokens and $3.20 per 1M output tokens, and cached input is $0.16 per 1M tokens.
What inputs and outputs does Qwen-VL-Max support?
Qwen-VL-Max accepts text and image input and returns text.
What is Qwen-VL-Max used for?
Qwen-VL-Max is used for image analysis, answering questions about pictures and reading text in images, with text as the output.
How do I call Qwen-VL-Max through the API?
Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen-vl-max.

More from Qwen

All 41 Qwen models