Aegis
Request access →
Connect anything

Connect Anything.

Aegis is a drop-in replacement for the OpenAI and Anthropic APIs, and it routes to Google models too. Point your app, IDE, or SDK at it and instantly spend less, with full governance and analytics - with no code changes.

Base URL
OpenAI & Anthropic Ready
http://129.121.135.39:8080/v1
Paste this one URL into any tool - OpenAI-compatible apps and Claude Code alike. That's it.
1
Copy the base URL
Set it in your tool's API base-URL field.
2
Use your aegis key
Generate it in your dashboard, paste as API key.
3
Run - unchanged
Same SDK calls, now cheaper and metered.
Works with

Your stack, unchanged

If it can set an API base URL, it works. No SDK to adopt, no rewrite.

IDEs & editors
CursorClaude CodeContinueClineRooVS Code
SDKs & frameworks
OpenAI SDKAnthropic SDKPythonNode.jsLangChainLlamaIndex
CLI
Claude CLIaidercurl
Integration guides

Copy-paste setup, by provider

Two request shapes, every model reachable from either. Pick whichever matches what you already speak.

Coding in Cursor or VS Code? Get the biggest savings.

Cut your coding bill without changing how you work:

  1. 1. Bring your own key for Anthropic, OpenAI, or Google in Settings.
  2. 2. Point your editor at the model you already use.
  3. 3. Aegis does the rest - live dashboard itemizes your net savings.

Any model Aegis routes to is reachable here - OpenAI, Anthropic, or Google - the "OpenAI-compatible" name describes the request/response shape, not which provider ends up serving it. Change only the model field to switch providers.

Cursor / IDE Integration

Settings → Models → enable OpenAI API Key, paste your aegis_sk_ key, tick Override OpenAI Base URL and set it to the URL below.

text
Base URL:  http://129.121.135.39:8080/v1API Key:   aegis_sk_live_your_key_here
Python (openai SDK)

Pass base_url and your Aegis key during client initialization:

python
from openai import OpenAIclient = OpenAI(    base_url="http://129.121.135.39:8080/v1",    api_key="aegis_sk_live_your_key_here",)response = client.chat.completions.create(    model="gpt-4o",  # or "claude-sonnet-4-5", "google/gemini-2.5-flash" - same call    messages=[{"role": "user", "content": "Hello Aegis!"}],)
TypeScript / Node.js (openai SDK)

Change baseURL in your client instantiation:

typescript
import OpenAI from "openai";const client = new OpenAI({  baseURL: "http://129.121.135.39:8080/v1",  apiKey: process.env.AEGIS_API_KEY,});const response = await client.chat.completions.create({  model: "gpt-4o",  messages: [{ role: "user", content: "Summarize this data" }],});
Raw HTTP / cURL

Standard HTTP POST to the completions endpoint:

bash
curl http://129.121.135.39:8080/v1/chat/completions \  -H "Authorization: Bearer aegis_sk_live_your_key_here" \  -H "Content-Type: application/json" \  -d '{    "model": "gpt-4o",    "messages": [{"role": "user", "content": "Hello Aegis!"}]  }'