Endpoint guide

OpenAI-compatible endpoint for AI apps

InferGate gives developers a compatible endpoint for apps, agents, SaaS features, and internal tools. Create an account and test with $20 trial credits.

Who it is for

Developers with existing OpenAI-style SDK integrations who want to test InferGate by changing the base URL and API key.

Use cases

  • Chat completions.
  • Responses API testing where supported.
  • Coding assistants.
  • Agent backends.
  • Internal AI workflows.

How InferGate connects

Set your client API key to an InferGate key and the base URL to the compatible endpoint below.

Base URL

https://api.useinfergate.com/v1

curl example

curl https://api.useinfergate.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_INFERGATE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "Test a compatible endpoint."}
    ]
  }'

JavaScript example

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.INFERGATE_API_KEY,
  baseURL: "https://api.useinfergate.com/v1"
});

const completion = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Test a compatible endpoint." }]
});

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

Python example

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["INFERGATE_API_KEY"],
    base_url="https://api.useinfergate.com/v1",
)

completion = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Test a compatible endpoint."}],
)

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

Trial credits and pricing

New accounts currently include $20 in trial credits. Move to prepaid API credits when ready. Pricing depends on selected model/provider route.

FAQ

What do I change in my SDK?

Use your InferGate API key and set the base URL to https://api.useinfergate.com/v1.

Can I list models?

Use /v1/models with your API key to inspect enabled models.

Can I track usage?

Review usage and balance activity in the dashboard.

Should I test exact workloads?

Yes. Test your prompts, model choice, latency, and cost behavior before production use.