AIARCOASC Docs
Sign inStart free

AI Gateway

Universal LLM proxy with caching, BYOK, rate-limit and request logging.

What it is

AI Gateway is the standalone proxy primitive on top of the Edge LLM Gateway. Bring your own keys for upstream providers, get one API with caching, per-tenant rate limits and full request/response logs.

When to use it

  • One surface across multiple model vendors.
  • Cache identical prompts.
  • Per-tenant rate-limit upstream calls.

Quickstart

asc gateway routes create cheap --provider openai --model gpt-4o-mini --cache 300s --rate-limit '50/min/tenant'
client.gateway.routes.create('cheap', provider='openai', model='gpt-4o-mini', cache_ttl_s=300, rate_limit='50/min/tenant')
await client.gateway.routes.create({ name: 'cheap', provider: 'openai', model: 'gpt-4o-mini', cacheTtlS: 300 });

Limits & quotas

LimitDefaultBurstNotes
Per proxied request$0.10 / M—
Per cached response$0.02 / M—

Pricing

See pricing. Pay-as-you-go, billed monthly via Stripe.

API surface

  • POST /v1/gateway/routes
  • POST /v1/gateway/{route}/chat

Required scope(s): gateway:read, gateway:write. See Scopes.

Security

All access is authenticated and scoped. See Auth & scopes and Network controls.