Managed gateway + controlsBest forAdding a gateway when your main goal is logging and debugging every request, with caching and rate limits on the side.
Trade-offIts focus is observability; routing features are thinner than a dedicated gateway's.
Used by 1 maker's product for this
Hosted model marketplaceFree tierFrom Pay per token + 5.5% fee on creditsllms.txtIn Replit Best forTrying many models from many providers with one API key and one bill, without opening an account at each.
Trade-offA fee on top of provider prices, and your traffic and data pass through a third party.
No maker product tracked for this yet
Self-hosted proxyBest forRunning your own OpenAI-compatible proxy in front of your own provider keys, with retries, routing and per-key budgets.
Trade-offYou deploy, monitor and upgrade it yourself; SSO and audit logs are in the paid enterprise tier.
No maker product tracked for this yet
Managed gateway + controlsBest forA gateway that also handles guardrails, prompt management and request logs in one dashboard.
Trade-offThe free tier caps logged requests; the full control layer is a paid hosted product.
No maker product tracked for this yet
Hosted model marketplaceBest forOne key and one bill for hundreds of models at provider list prices, with fallbacks and budgets, built into the AI SDK.
Trade-offTied to a Vercel team and prepaid credits, and bringing your own provider keys needs the paid tier.
No maker product tracked for this yet
Self-hosted proxyOpen source
Best forRouting, auth, token budgets and usage analytics for LLM, MCP and agent-to-agent traffic, run as AI plugins on Kong Gateway.
Trade-offBuilt for platform teams; the quickstart needs a Konnect account and token, and it is a heavy setup if all you want is one key for several models.
Used by 2 makers' products for this
Hosted model marketplaceBest forOne API in front of many models that routed each prompt to the best one for quality, cost and speed.
Trade-offPivoted away from routing (now continual-learning models for agent teams); there is no gateway or pricing page.
Used by 1 maker's product for this
Managed gateway + controlsFree tierFrom $199/mo
Best forOne OpenAI-compatible endpoint to 1,000+ models with fallbacks, caching, spend limits and every request logged in the same place you run evals.
Trade-offRequests pass through its cloud; the free plan caps proxy throughput at 412 requests a minute, and the self-hostable part is only the new open-source gateway.
No maker product tracked for this yet
Managed gateway + controlsBest forLogging, caching, rate limits, spend limits and fallbacks in front of OpenAI, Anthropic, Workers AI and 20+ other providers, free on any Cloudflare account.
Trade-offLogs count against Workers Logs pricing for new accounts, buying model credits through Unified Billing adds a 5% fee, and dynamic routing, guardrails and BYOK are still in beta.
No maker product tracked for this yet