Stop AI data leaks and control spend with a drop-in proxy that sits between your app and LLM providers.
PII redaction (28+ entities + OCR) · Prompt injection blocking · Budget enforcement · Full governance dashboard.

Website · Docs · API Reference · Product Tour · Model Catalog

Your App  ──▶  AI ModelGate  ──▶  LLM Provider
               (AI Firewall)
               ├─ PII Scan (28+ entities + OCR)
               ├─ Prompt Injection Detection
               ├─ Budget & Token Enforcement
               └─ Smart Cost Routing

ModelGate is an OpenAI-compatible proxy. If your app uses the OpenAI SDK, integration is a two-line change — swap the baseURL and apiKey:

import OpenAI from "openai";

const client = new OpenAI({
  apiKey:  "os_hub_your_key_here",                    // ← Hub API key
  baseURL: "https://api.aimodelgate.ai/v1",       // ← Hub endpoint
});

const res = await client.chat.completions.create({
  model: "oah/llama-3.3-70b",   // smart-routed virtual model
  messages: [{ role: "user", content: "Explain zero-trust architecture." }],
});

console.log(res.choices[0].message.content);

from openai import OpenAI

client = OpenAI(
    api_key="os_hub_your_key_here",                    # ← Hub API key
    base_url="https://api.aimodelgate.ai/v1",      # ← Hub endpoint
)

res = client.chat.completions.create(
    model="oah/llama-3.3-70b",
    messages=[{"role": "user", "content": "Explain zero-trust architecture."}],
)

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

package main

import (
	"context"
	"fmt"

	"github.com/openai/openai-go"
	"github.com/openai/openai-go/option"
)

func main() {
	client := openai.NewClient(
		option.WithAPIKey("os_hub_your_key_here"),                // ← Hub API key
		option.WithBaseURL("https://api.aimodelgate.ai/v1"), // ← Hub endpoint
	)

	completion, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
		Model: "oah/llama-3.3-70b",
		Messages: []openai.ChatCompletionMessageParamUnion{
			openai.UserMessage("Explain zero-trust architecture."),
		},
	})

	fmt.Println(completion.Choices[0].Message.Content)
}

curl -X POST https://api.aimodelgate.ai/v1/chat/completions \
  -H "Authorization: Bearer os_hub_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "oah/llama-3.3-70b",
    "messages": [{"role": "user", "content": "Explain zero-trust architecture."}],
    "max_tokens": 512
  }'

Model names: Use oah/ prefixed virtual models for smart cost-routing, or explicit provider models like groq/llama-3.3-70b-versatile. See the full model catalog.

Route to 100+ models across 9 providers with one API key:

No credit card required to start. Sign up and get 1M credits instantly.

Get Started — 1M Free Credits →

_{Security · Privacy Policy · Terms of Service · Contact}

_{Built by Datum Fuse LLC · Stateless Architecture · No Data Retention · AES-256 Encryption}