Get started

Ship your first call in 90 seconds.

Three steps. No waitlists, no sales call, no "schedule an integration review". Sign in, change a base URL, call any model.

Sign in with GitHub →API referenceFor coding agents
STEP 00

One command (optional)

If you'd rather skip everything below, the CLI walks through it. `aig init` prompts for a key, writes it to .env, and scaffolds a working starter file in TypeScript, JavaScript, or Python — whichever your project already uses.

npx aigateway-cli init
# or install globally
npm i -g aigateway-cli && aig init
STEP 01

Sign in + get a key

One click with GitHub or Google. Your first test key lands in your clipboard. No card required.

# .env
AIGATEWAY_API_KEY=sk-aig-...
STEP 02

Point any SDK at us

Change one line — base_url. Every OpenAI SDK, every language, every framework, every agent.

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIGATEWAY_API_KEY"],
    base_url="https://api.aigateway.sh/v1",
)

resp = client.chat.completions.create(
    model="anthropic/claude-opus-4.7",
    messages=[{"role": "user", "content": "hello"}],
)
STEP 03

Swap any model, any modality

Same shape for text, images, audio, embeddings. Change the slug, nothing else.

# image
client.images.generate(model="black-forest-labs/flux-2-klein-9b", prompt="...")

# stt
client.audio.transcriptions.create(model="deepgram/nova-3", file=open("a.mp3","rb"))

# tts
client.audio.speech.create(model="deepgram/aura-2-en", voice="asteria", input="...")

# embeddings
client.embeddings.create(model="baai/bge-m3", input="hello")
Or let your agent do it

Point your coding agent at our URL.

A capable coding agent reads one of these and can call every modality without a human editing config.

Next

When you're ready for production.

Everything below is optional on day one — turn each on when the problem it solves actually hurts.