How to Get Started
pip install requestsCode language: Bash (bash)
import requests
api_url = "https://api.regolo.ai/v1/chat/completions"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer YOUR_REGOLO_KEY"
}
data = {
"model": "gemma4-31b",
"messages": [
{
"role": "user",
"content": "What is the capital of Italy, and which region does it belong to?"
}
],
"reasoning_effort": "low"
}
response = requests.post(api_url, headers=headers, json=data)
print(response.json())Code language: Python (python)
Output
{
"id": "chatcmpl-a4988541-84b1-41a5-843f-06790a11f7fc",
"created": 1769560420,
"model": "hosted_vllm/gemma4-31b",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "The capital of Italy is Rome (Italian: Roma). Rome belongs to the Lazio region.",
"role": "assistant"
}
}
],
"usage": {
"completion_tokens": 62,
"prompt_tokens": 45,
"total_tokens": 107
}
}Code language: JSON / JSON with Comments (json)
Applications & Use Cases
- Multimodal chat assistants for customer support, knowledge bases, and internal copilots that combine text, image, and video understanding in 140+ languages.
- Reasoning and coding copilots that use thinking mode for step‑by‑step problem solving, mathematical proofs, and complex code generation or debugging.
- Document intelligence pipelines for PDFs, forms, and scanned contracts, leveraging native OCR and handwriting recognition with 256K context for large documents.
- Tool‑ and function‑calling agents that orchestrate APIs, databases, and multi‑step workflows inside enterprise automation or data retrieval backends.
- Video understanding workflows for surveillance, education, or sports analytics, using up to 60‑second video inputs processed as frame sequences.
- On‑device and workstation deployments where the 30.7B dense architecture fits a single high‑end GPU (≈17.4 GB at 4‑bit quantization) without MoE infrastructure overhead.
