Qwen3 VL Plus

Vision

qwen3-vl-plus · Qwen · vision

Back to Models Back to Docs

Platform

Qwen

Visit Official Site

API Pricing

Input / 1M

$0.45/M

Output / 1M

$4.47/M

Overview

Alibaba Cloud's Tongyi Qianwen vision model Qwen3 VL Plus offers a 128K context window with support for image, video, and PDF understanding. It is ideal for multimodal Q&A, document parsing, and image content extraction, and supports Function Calling and JSON mode.

Capabilities

128K context; vision understanding (image/video/PDF); Function Calling; JSON mode; OpenAI-compatible interface.

Use Cases

Multimodal Q&A; document parsing (PDF/Word); image content extraction; video content understanding; form extraction; image recognition.

Limitations

Does not generate images; no explicit caching support; 128K context; high concurrency requires an Alibaba Cloud quota.

Examples

Claude Code

Anthropic official CLI coding agent. Multi-file edits, tool use, long-context reasoning.

Terminal

export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://api.robovai.com"
export ANTHROPIC_MODEL="qwen3-vl-plus"
claude

Context Window

260K ctx

Thinking Mode

Not supported

Overview

Qwen3 VL Plus vision understanding model, with a 260K context window. Supports image and document understanding along with multimodal reasoning.