Vercel AI Gateway alternatives (and the AI SDK without a gateway)
Vercel AI Gateway charges no markup on tokens, so the reason to look elsewhere is control, not price: when a request on your own key fails it is retried on Vercel's system credentials and charged to your Vercel balance, and its budgets do not count your own-key spend. The alternatives are INFRO, Cloudflare AI Gateway, OpenRouter, LiteLLM and Portkey, or the AI SDK pointed straight at a provider with no gateway at all.
Vercel AI Gateway charges "no markup and no platform fee on tokens", including with your own keys. It is a good default for an app on Vercel. Two documented behaviours are the usual reasons to look further:
A failed BYOK request runs on Vercel's credentials. Vercel's pricing page says that when a request on your credentials fails, AI Gateway retries it with its own system credentials and charges that usage to your AI Gateway balance. Good for availability; but a request you meant to keep on your own contract and data terms can run on Vercel's.
Budgets do not see BYOK spend. Spend through your own credentials is not counted in budgets, so a budget cannot cap BYOK traffic.
The AI SDK uses AI Gateway by default when you pass a model string, but it does not need it. Set a provider package such as @ai-sdk/openai as the default, or pass a provider instance, and the SDK calls that provider directly with your key. For one provider and one app, that removes a hop and a dashboard; you give up cross-provider failover and budgets, which you then build yourself.
Each option is described from its own pricing page and documentation, checked on the date at the top. INFRO is listed first because this is INFRO's site; its limits are listed as plainly as everyone else's.
Teams that hold, or want to hold, their own provider contracts and need routing, failover, budgets and cost per customer across them.
How it charges
A flat plan of $35–$599 a month, chosen by request volume (100K–10M requests a month), never by spend. 0% markup on model spend: your providers bill you directly.
Strengths
Every request runs on a provider account you own; INFRO holds none, so nothing falls back onto someone else's contract.
Budgets refuse a request before the provider is called, per organization, project, member and key, and (from the Team plan) per end customer.
Each response names the provider, connection and model that served it, with an estimated provider cost.
Limits
No shared capacity: when every connection you own fails, the request fails with an error that says why.
Hosted only on its plans; a self-hosted deployment needs an enterprise agreement.
No prompt management or output evaluation.
A subscription, where Vercel charges nothing on tokens.
Enterprises buying an AI gateway as part of a security platform, or teams self-hosting Portkey's open-source gateway.
How it charges
Production is $49 a month with 100,000 recorded logs, plus $9 per additional 100,000. The open-source gateway is MIT licensed. Enterprise is custom.
Strengths
Mature routing, fallbacks, guardrails and observability.
An MIT-licensed gateway you can host yourself.
Limits
Palo Alto Networks completed its acquisition on 29 May 2026; the product is now Prisma AIRS AI Gateway, so check its roadmap fits a team not buying the wider platform.
Logs, observability and prompt management are in the hosted app, not the open-source gateway.
Vercel says it charges no markup and no platform fee on tokens, including with your own keys; some capabilities are paid add-ons.
What happens when my own key fails on Vercel AI Gateway?
Vercel retries the request with its own system credentials and charges that usage to your AI Gateway balance.
Can I use the Vercel AI SDK without AI Gateway?
Yes. The SDK defaults to AI Gateway for model strings, but you can set a provider such as @ai-sdk/openai as the default, or pass a provider instance, and call the provider directly.
Sources
Every statement about another company on this page comes from that company's own page, opened on the date shown. Prices and defaults change; check the source before you decide.
Vercel AI Gateway charges no markup and no platform fee on tokens; you pay the provider's list price.
Bringing your own provider key adds no Vercel fee.
When a request on your own credentials fails, Vercel retries it on its own system credentials and charges that usage to your Vercel AI Gateway balance.
Spend on your own credentials is not counted in Vercel AI Gateway budgets, so a budget cannot cap BYOK spend.
Past the allowance, BYOK usage is charged 5% of what the same model and provider would cost on OpenRouter.
By default, a BYOK request that fails or is rate limited on your key falls back to OpenRouter's shared endpoints, paid from your OpenRouter balance; a per-key "Shared capacity fallback" setting turns that off.
On 24 March 2026, litellm 1.82.7 and 1.82.8 on PyPI carried credential-stealing code for about 40 minutes; LiteLLM says the official Proxy Docker image was not affected and 1.83.0 is clean.
OpenAI sets rate limits per organization and per project, not per user.
The team building INFRO, a BYOK-first control plane for production AI. Articles are written from the engineering work on the gateway and cite their external sources.