Skip to content

Artificial intelligence infrastructure

One contract. Every model provider.

A single, stable, OpenAI-compatible API in front of every provider your team uses. Your app keeps one integration; the gateway owns authentication, routing, rate limits, budgets, caching, costs and observability.

View on GitHubDeploy it

Call the gateway

# One key, one alias: the gateway picks
# the provider and falls back for you
curl https://gateway.boelabs.com/v1/chat/completions \
  -H "Authorization: Bearer $VIRTUAL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "fast",
    "messages": [{ "role": "user", "content": "Hola" }]
  }'

01Why a gateway

Switching providers stops being a release

Without a gateway

  • One SDK and auth scheme per vendor
  • Vendor outages reach your users
  • Vendor keys scattered across every service
  • Spend and latency invisible until the invoice
  • Provider migrations are code changes

With AI Gateway

  • One OpenAI-compatible contract for all of them
  • Weighted pools, cooldowns, retries and fallbacks
  • Virtual keys with scopes, limits and budgets
  • Per-request costs, logs and OpenTelemetry
  • Provider migrations are configuration changes

02What's inside

Everything between your app and the models

  • Public contracts

    Exact OpenAI shapes for chat, Responses, images, embeddings, audio, video, reranking and models, plus an Anthropic-compatible /v1/messages.

  • Providers

    OpenAI, Anthropic, Google AI Studio, Azure, Vercel AI Gateway, OpenRouter, DeepSeek and more, or any OpenAI-compatible endpoint.

  • Routing

    Public aliases over weighted deployment pools, with cooldowns, retries and explicit fallback chains.

  • Access control

    A master key for operations and virtual keys per client, with model scopes, per-minute limits and budgets.

  • Operations

    Opt-in caching, durable logs, per-request cost accounting, and OpenTelemetry metrics and traces.

  • Extensions

    Request, response and stream hooks loaded at runtime through the Admin API, without forking the gateway.

03How it works

Translate, route, execute

  1. 1

    Translate

    Every request, whether it uses the OpenAI or the Anthropic contract, becomes one canonical representation.

  2. 2

    Route

    The router picks a deployment from the alias's pool based on strategy, cooldowns and configured fallbacks.

  3. 3

    Execute

    One adapter per provider speaks its protocol; nothing provider-specific leaks into the core or your response.

04Open source

Yours to run wherever you want

MIT licensed. Published images that only need Postgres and Redis, plus an optional operator dashboard on its own domain for models, keys, logs, usage and a playground.

  • Behind our own products, in production.
  • One image is promoted between environments: configuration doesn't live in it.
  • Before 1.0, breaking changes are still possible.
boelabs/ai-gateway
  • The APIghcr.io/boelabs/ai-gateway-api
  • The operator dashboardghcr.io/boelabs/ai-gateway-dashboard

Try Boberth today. It's free.

Create your account in seconds, or reach out if you want to integrate Billete into your business.

Try Boberth for freeTalk to the team