Pricing/Qwen3 VL Plus
Qwen3 VL Plus

Qwen3 VL Plus

qwen/qwen3-vl-plus
by Qwen
Context window
256Ktokens
Max output
31Ktokens

The Qwen3 series VL models effectively integrates thinking and non-thinking modes, achieving world-leading performance in visual agent capabilities on public benchmark datasets such as OS World. This version features comprehensive upgrades in areas like visual coding, spatial perception, and multimodal reasoning, significantly enhancing visual perception and recognition abilities, and supporting the understanding of ultra-long videos.

Features

Serverless API

Docs

qwen/qwen3-vl-plus is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.

Available Serverless

Run queries immediately, pay only for usage

Input$1 / M Tokens
Cache Read$1 / M Tokens
Output$1 / M Tokens

Tiered pricing

Input lengthInput price (M tokens)Output Price (M tokens)Cache Write(5m)Cache Read
1 <= tokens < 32,000$0.144$1.434$0.18$0.014
32,000 <= tokens < 128,000$0.216$2.151$0.27$0.022
128,000 <= tokens < 256,000$0.431$4.301$0.539$0.043
  1. Get your API key

    Sign up and create a key to run the code below. The API is OpenAI-compatible.

  2. Make your first request

    The API is OpenAI-compatible: point any OpenAI SDK at the base URL and pass this model ID.

    Base URL
    https://api.novita.ai/openaihttps://api.novita.ai/anthropic
    Model ID
    qwen/qwen3-vl-plus
    API Endpoint
    chat/completionsresponses
    1from openai import OpenAI
    2
    3client = OpenAI(
    4    api_key="<Your API Key>",
    5    base_url="https://api.novita.ai/openai"
    6)
    7
    8response = client.chat.completions.create(
    9    model="qwen/qwen3-vl-plus",
    10    messages=[
    11        {"role": "system", "content": "You are a helpful assistant."},
    12        {"role": "user", "content": "Hello, how are you?"}
    13    ],
    14    max_tokens=32000,
    15    temperature=0.7
    16)
    17
    18print(response.choices[0].message.content)