Hunyuan OCR (1B)

Released in late 2025, Hunyuan OCR is an open-source contribution from Tencent that outperforms many larger proprietary models. It uses a global-to-local architecture with a SigLIP-v2 visual encoder to handle high-resolution inputs and extreme aspect ratios without artificial image splitting.

Tencent Hunyuan OCR 16K Tokens
Get API Key
Try in Playground
Free Trial Credit No Credit Card Required
$1.00

api_example.sh

curl -X POST "https://platform.qubrid.com/chat/completions" \
  -H "Authorization: Bearer $QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "tencent/HunyuanOCR",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
          }
        }
      ]
    }
  ],
  "max_tokens": 4096,
  "temperature": 0,
  "language": "auto",
  "ocr_mode": "general"
}'

Technical Specifications

Model Architecture & Performance

Model Size 1.0B params
Context Length 16K Tokens
Quantization fp16
Tokens/Second 386
License Tencent Hunyuan Community License
Release Date November 2025
Developers Tencent Hunyuan Team

Pricing

Pay-per-use, no commitments

Input Tokens $0.00021/1K Tokens
Output Tokens $0.00035/1K Tokens

API Reference

Complete parameter documentation

ParameterTypeDefaultDescription
streambooleantrueEnable streaming responses for real-time output.
max_tokensnumber4096Maximum number of tokens for the generated text.
temperaturenumber0Controls randomness. Keep at 0 for accurate text extraction.
ocr_modestringgeneralOptimizes the system prompt for specific content types such as tables, handwriting, or formulas.

Explore the full request and response schema in our external API documentation

Performance

Strengths & considerations

StrengthsConsiderations
Lightweight 1B parameter model with state-of-the-art OCR accuracy
Native support for high-resolution and extreme aspect ratios
Unified end-to-end architecture without bounding-box error propagation
Exceptional handling of rotated and vertical text
Strong multilingual support including mixed scripts
Focused purely on OCR, not general visual question answering
May hallucinate on extremely blurred or low-resolution text
Throughput depends on visual token density

Enterprise
Platform Integration

Docker

Docker Support

Official Docker images for containerized deployments

Kubernetes

Kubernetes Ready

Production-grade KBS manifests and Helm charts

SDK

SDK Libraries

Official SDKs for Python, Javascript, Go, and Java

Don't let your AI control you. Control your AI the Qubrid way!

Have questions? Want to Partner with us? Looking for larger deployments or custom fine-tuning? Let's collaborate on the right setup for your workloads.

"Qubrid's medical OCR and research parsing cut our document extraction time in half. We now have traceable pipelines and reproducible outputs that meet our compliance requirements."

Clinical AI Team

Research & Clinical Intelligence