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.
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.
クエリをすぐに実行し、使用した分だけお支払い
| 入力長 | 入力価格(100万トークン) | 出力価格(100万トークン) | 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 |
The API is OpenAI-compatible: point any OpenAI SDK at the base URL and pass this model ID.
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)