Skip to main content
Models

Qwen3-VL-Plus

Model Overview

Direct supply
ChatStreamingVisionToolsThinkingCache

Qwen3-VL-Plus：通义千问 Qwen3 系列视觉理解模型，融合思考与非思考模式，支持图片与超长视频理解、视觉 Coding 与空间感知。

Input Modalities

Text, Image

Output Modalities

Text

Recommended for

Smart chat assistant with vision, tool use, and streaming output.

Capabilities

Chat

Multi-turn conversational completions

Streaming

Tokens are delivered incrementally as they are generated

Vision

Accepts image input alongside text

Tool Use

Can call functions/tools defined in the request

Thinking

Produces an extended internal reasoning trace before the final answer

Prompt Caching

Reuses previously processed prompt prefixes at a lower rate

Supported Modes

Chat

Model Pricing

13% off
Pay-as-you-go

Full Pricing Breakdown

Every billed dimension for Qwen3-VL-Plus

Token Pricing

Cache Read$0.03per 1M tokens
  • From 32000 tokens$0.04 per 1M tokens
  • From 128000 tokens$0.08 per 1M tokens
Input$0.13per 1M tokens
  • From 32000 tokens$0.19 per 1M tokens
  • From 128000 tokens$0.38 per 1M tokens
Output$1.27per 1M tokens
  • From 32000 tokens$1.90 per 1M tokens
  • From 128000 tokens$3.79 per 1M tokens
Thinking$1.27per 1M tokens
  • From 32000 tokens$1.90 per 1M tokens
  • From 128000 tokens$3.79 per 1M tokens

Cache Write

Cache Write$0.16per 1M tokens
  • From 32000 tokens$0.24 per 1M tokens
  • From 128000 tokens$0.48 per 1M tokens

Indicative pricing — final cost is confirmed at request time.

Volume Tiers

InputOutput
From 32000 tokens$0.19$1.90
From 128000 tokens$0.38$3.79

Context & Limits

Context Window
262,144 tokens
Max Output
32,768 tokens

API Code Example

Get API Key
OpenAI Compatible
import openai
 
client = openai.OpenAI(
base_url="https://api.modelsite.ai/v1",
api_key="sk-ms-...",
)
 
response = client.chat.completions.create(
model="qwen3-vl-plus",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)