AMD Radeon Cloud MiniCPM-V 4.6

AMD Radeon Cloud endpoint for MiniCPM-V 4.6 edge-multimodal flagship vision model.

Updated 9/2/20261 code examples

About the Model

Why Choose MiniCPM-V 4.6?

MiniCPM-V 4.6 is OpenBMB's leading edge multimodal model, delivering GPT-4V level visual perception, extreme-detail OCR, and table extraction with high efficiency on AMD GPUs.

Key Strengths & Capabilities

  • 256K Context Window: Capable of multi-image analysis and lengthy visual question answering.
  • Superb OCR & Diagram Understanding: High precision on complex receipts, architectural diagrams, and dense text.
  • Efficient vLLM Engine: Accelerated on AMD Radeon Cloud for low-latency visual inference.

How to Access for Free (via AMD Radeon Cloud)

Why Choose AMD MiniCPM-V 4.6?

Leading multimodal vision model from OpenBMB, providing high-precision OCR and document analysis served by AMD Radeon Cloud.

Try it in your browser

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

Code Examples

curl
curl https://developer.amd.com.cn/radeon/api/v1/chat/completions \
  -H "Authorization: Bearer $AMD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniCPM-V46",
    "messages": [{"role": "user", "content": "What is MiniCPM?"}]
  }'

Community Feedback

Comments are tied to your GitHub account — sign in to join the discussion.