AI Gateway

Set one line in your spec and your agent gets a managed API key for calling supported models — no provider account, no API keys to store, no key rotation to manage.

Quick start

Add astro_ai_gateway: true to your agent in astropods.yml:

1
agent:
2
  image: my-agent:latest
3
  astro_ai_gateway: true

On ast deploy (and ast dev), your agent container receives two environment variables:

Wire them into the SDK or framework you’re already using. The gateway is OpenAI-API-compatible — anything that accepts a custom base URL works:

1
from openai import OpenAI
2
import os
3
4
client = OpenAI(
5
    api_key=os.environ["ASTRO_GATEWAY_API_KEY"],
6
    base_url=os.environ["ASTRO_GATEWAY_URL"],
7
)
8
9
response = client.chat.completions.create(
10
    model="claude-sonnet-4-6",
11
    messages=[{"role": "user", "content": "Hello"}],
12
)

For Mastra: the AI-SDK provider returned by createOpenAI is what Agent.model: accepts, so the rest of your Agent / Workflow / Tool definitions stay the same.

Supported models

Pass any of these strings as model on the SDK call:

Local development

ast dev handles the gateway automatically. Run:

$
ast login
$
ast dev project start

Your local agent container receives the same ASTRO_GATEWAY_* env vars it would have in production. Code written against those env vars works identically in dev and prod.

Mixing with your own keys

astro_ai_gateway: true is independent of any models you declare. You can use the gateway for some calls and your own provider key for others:

1
agent:
2
  image: my-agent:latest
3
  astro_ai_gateway: true        # gateway-managed models
4
models:
5
  custom-fine-tune:
6
    provider: openai      # your own OpenAI key for a specific use case

Your agent code reads ASTRO_GATEWAY_API_KEY for gateway calls and OPENAI_API_KEY for the BYOK provider.

What it doesn’t cover

• Anthropic-native SDK. Use the OpenAI SDK (or one of the frameworks above) pointed at ASTRO_GATEWAY_URL. Calling Anthropic’s native messages endpoint isn’t supported.
• Vision / image generation. The supported model list is text-only.
• Bring-your-own-model. Adding new models or fine-tunes to the gateway isn’t self-serve; reach out to support.