tencent/HunyuanOCR

Released in late 2025, HunyuanOCR is an open-source contribution from Tencent that outperforms many larger proprietary models. It utilizes a "Global-to-Local" architecture with a SigLIP-v2 visual encoder to handle high-resolution inputs and extreme aspect ratios (like long receipts) without splitting images artificially.

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/v1/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,
  "stream": true,
  "language": "en",
  "ocr_mode": "general"
}'

from openai import OpenAI

# Initialize the OpenAI client with Qubrid base URL
client = OpenAI(
    base_url="https://platform.qubrid.com/v1",
    api_key="QUBRID_API_KEY",
)

stream = client.chat.completions.create(
    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,
    stream=True,
    extra_body={
        "language": "en",
        "ocr_mode": "general",
    }
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

print("\n")

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://platform.qubrid.com/v1',
  apiKey: 'QUBRID_API_KEY',
});

const stream = await client.chat.completions.create({
  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,
  stream: true,
  extra_body: {
    language: 'en',
    ocr_mode: 'general',
  }
});

for await (const chunk of stream) {
  if (chunk.choices[0]?.delta?.content) {
    process.stdout.write(chunk.choices[0].delta.content);
  }
}
console.log('\n');

package main

import (
  "bytes"
  "encoding/json"
  "net/http"
)

func main() {
  url := "https://platform.qubrid.com/v1/chat/completions"

  data := {
  "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,
  "stream": true,
  "language": "en",
  "ocr_mode": "general"
}
  jsonData, _ := json.Marshal(data)

  req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
  req.Header.Set("Authorization", "Bearer QUBRID_API_KEY")
  req.Header.Set("Content-Type", "application/json")

  client := &http.Client{}
  res, _ := client.Do(req)
}

Technical Specifications

Model Architecture & Performance

Model Size 1.0B params

Context Length 16K Tokens

Quantization fp16

Tokens/Second 386

Architecture Hunyuan-ViT (SigLIP-v2 visual encoder) + MLP + Lightweight LLM

Precision bfloat16

License Tencent Hunyuan Community License

Release Date November 2025

Developers Tencent Hunyuan Team

Pricing

Pay-per-use, no commitments

Input Tokens $0.21/1M Tokens

Output Tokens $0.35/1M Tokens

API Reference

Complete parameter documentation

Parameter	Type	Default	Description
stream	boolean	true	Enable streaming responses for real-time output.
language	select	en	Optional language hint to improve OCR accuracy for specific languages.
ocr_mode	select	general	Select optimized OCR mode based on the image type.
max_tokens	number	4096	Maximum number of tokens for the generated text.
temperature	number	0	Controls randomness. Keep at 0 for accurate text extraction.

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

Performance

Strengths & considerations

Strengths	Considerations
Lightweight (1B parameters) with SOTA performance Native support for high-resolution & extreme aspect ratios Unified end-to-end architecture (no separate detection box errors) Exceptional handling of rotated and vertical text Strong multilingual support (English, Chinese, and mixed scripts)	Purely OCR-focused; not intended for general visual QA May hallucinate on extremely blurred low-resolution text Output speed is dependent on visual token density

Use cases

Recommended applications for this model

Dense Document Digitization (PDF/Scanned)

Key-Information Extraction (KIE) from Receipts

Multilingual Scene Text Spotting

Handwriting Recognition

LaTeX Formula Extraction

End-to-End Image Translation

Enterprise
Platform Integration

Docker Support

Official Docker images for containerized deployments

Kubernetes Ready

Production-grade KBS manifests and Helm charts

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.

Get Started

"Qubrid scaled our personalized outreach from hundreds to tens of thousands of prospects. AI-driven research and content generation doubled our campaign velocity without sacrificing quality."

Demand Generation Team

Marketing & Sales Operations