verifier.org

Bifrost

apache 2.0 on paper, open-core in the build

free (self-host) — enterprise is custom#latency-sensitive-proxyi

the fastest thing here and the most permissively licensed on paper, but the features that make a gateway safe in production are not in the apache build.

bifrost is a go binary with a published overhead of roughly 20 microseconds per request, and the licence file at github.com/maximhq/bifrost is unmodified apache 2.0 with no enterprise directory and no second licence anywhere in the repository. on those two facts alone it looks like the most permissive option in the category.

the readme then says enterprise deployments 'unlock advanced capabilities including adaptive load balancing, clustering, guardrails, mcp gateway, and other features', plus custom plugins and oidc user provisioning — documented at docs.getbifrost.ai/enterprise and absent from the apache-licensed build. this is the harder open-core pattern to spot: nothing in the licence restricts you, the code simply is not there. litellm's explicit carve-out is more honest about the same arrangement.

the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.

category
llm gateways
pricing
free (self-host) — enterprise is custom
our verdict

the fastest thing here and the most permissively licensed on paper, but the features that make a gateway safe in production are not in the apache build.

we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.

more llm gateways

Unify

routes each prompt to whichever provider wins on your own benchmark

#routing#benchmarks

Not Diamond

learns which model to route each request to, from your feedback

#routing#learned

LangDB

gateway with tracing and cost controls in front of many providers

#tracing#cost-control

Vercel AI Gateway

we checked this$0 — usable on the free hobby plan

zero markup stated plainly, including on byok

#teams-already-deploying-