Qwen3-VL-Plus
The Plus tier of Alibaba's Qwen3-VL vision-language models, for questions about images and text.
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/qwen3-vl-plusEndpoints
/v1/chat/completionsChat CompletionsCall it
Using qwen/qwen3-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/qwen3-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/qwen3-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/qwen3-vl-plus",6 "messages": [{ "role": "user", "content": "Hello" }]7 }'Prices and availability as published on Oct 12, 2026.
Capabilities
Qwen3-VL-Plus accepts text and image input and returns text.
Alibaba documents function calling for the Qwen3-VL series, so the model can act on image content, and structured output in non-thinking mode, for example valid JSON from a visual input.
Overview
Qwen3-VL-Plus is the Plus tier of Alibaba's Qwen3-VL vision-language models. It takes image and text input and returns text, and it is the tier to choose when you want a vision-language model from this series with function calling and structured output.
It accepts text and image input and returns text.
Pricing
Pricing for Qwen3-VL-Plus starts from $0.20 per 1M input tokens and $1.60 per 1M output tokens, with cache reads from $0.04 per 1M tokens. Pricing is tiered, so these figures are the starting tier. Qwen3-VL-Plus is available through RealRelay's OpenAI-compatible API.
Use cases
Use Qwen3-VL-Plus for visual question answering over images, where a request pairs a picture with a text question.
Its structured output suits extraction pipelines that turn visual inputs, such as product photos, into JSON, and function calling lets those pipelines trigger follow-up actions from what the model sees.
Frequently asked questions
- What is Qwen3-VL-Plus?
- Qwen3-VL-Plus is the Plus tier of Alibaba's Qwen3-VL vision-language models.
- How much does Qwen3-VL-Plus cost?
- Pricing for Qwen3-VL-Plus starts from $0.20 per 1M input tokens and $1.60 per 1M output tokens, with cache reads from $0.04 per 1M tokens. Pricing is tiered, so these figures are the starting tier.
- What inputs and outputs does Qwen3-VL-Plus support?
- Qwen3-VL-Plus accepts text and image input and returns text.
- Does Qwen3-VL-Plus support function calling?
- Yes. Alibaba documents function calling for the Qwen3-VL series, and Qwen3-VL-Plus also supports structured output in non-thinking mode.
- How do I call Qwen3-VL-Plus via the API?
- Send requests to RealRelay's OpenAI-compatible API with the model ID qwen/qwen3-vl-plus to use Qwen3-VL-Plus.