One-Router — Local LLM Gateway Dashboard

Active Models 🤖

Local backends connected

Customers & Projects 👥

Active tenant accounts

Total Tokens Processed ⚡

Input & Output metered

Engine Health 🛡️

Ready

SQLite WAL + FastAPI Proxy

Customer Quota Overview

Loading customers...

Quick Verification

OpenAI Compatible

Use standard OpenAI client configuration pointing to this gateway:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.one-router.ai.one-bit.net/v1",
    api_key="sk-llm-your-key-here"
)

models = client.models.list()
print([m.id for m in models.data])

Registered Local Models

Public model aliases routed securely to internal LLM engines (Ollama, vLLM, etc.)

Loading models...

Customer Accounts & API Keys

Manage tenants, allocate monthly token budgets, and issue hashed Bearer API keys.

Customer Name	ID	Email	Status	Token Budget	Used Tokens	API Keys	Actions
Loading customer accounts...

API Test Console

Test authentication and verify model listing in real-time.

Request Parameters

API Key (Bearer Token) Pre-filled with the active key generated during bootstrap.

Endpoint

Response

Awaiting test

Click "Send Request" to execute API call...

Developer Integration Guide

Connect your applications using standard OpenAI client libraries without code modifications.

🐍 Python (OpenAI Official SDK)

import os
from openai import OpenAI

# Initialize client pointing to your One-Router gateway
client = OpenAI(
    base_url="https://api.one-router.ai.one-bit.net/v1",
    api_key="sk-llm-your-api-key"
)

# 1. List Available Models
models = client.models.list()
print("Available Models:", [m.id for m in models.data])

# 2. Chat Completion
response = client.chat.completions.create(
    model="qwen3-32b",
    messages=[
        {"role": "system", "content": "You are a secure local AI."},
        {"role": "user", "content": "Explain zero trust architecture."}
    ],
    temperature=0.7
)

print(response.choices[0].message.content)

🌐 cURL / Shell Request

# 1. Check Health
curl -s https://api.one-router.ai.one-bit.net/health

# 2. Fetch Models
curl -s -X GET "https://api.one-router.ai.one-bit.net/v1/models" \
  -H "Authorization: Bearer sk-llm-your-key-here"

# 3. Chat Completion
curl -s -X POST "https://api.one-router.ai.one-bit.net/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-llm-your-key-here" \
  -d '{
    "model": "qwen3-32b",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Local LLM Gateway Control Center