Start from what you already run

Every other page here starts with a product. This one starts with your infrastructure. Pick something you already run and see which of the 31 products slot into it — and, more usefully, which ones say they do and mean something else.

The middle column is the point of this page. A product lands there when the support is real but not the thing the marketing implies: documented by somebody else, a community package with no support obligation, or a Helm chart nobody names. Those are workable answers. They are not the same answer as a yes, and this page refuses to round them up into one.

The OpenAI SDK

26 fit · 5 with a caveat · 0 no

My code already uses the OpenAI SDK. What can I point it at?

Fits26

  • Eden AI Drop-in: change the base URL and key, nothing else.
  • OpenRouter Drop-in: change the base URL and key, nothing else.
  • Requesty Drop-in: change the base URL and key, nothing else.
  • Braintrust Gateway Drop-in: change the base URL and key, nothing else.
  • Helicone Drop-in: change the base URL and key, nothing else.
  • Merge Gateway Drop-in: change the base URL and key, nothing else.
  • Orq.ai Router Drop-in once set up — but first-call work is cloud console setup.
  • Portkey Drop-in once set up — but first-call work is sdk install.
  • Respan Drop-in: change the base URL and key, nothing else.
  • Vercel AI Gateway Drop-in once set up — but first-call work is sdk install.
  • agentgateway Drop-in once set up — but first-call work is cli or container.
  • Bifrost Drop-in once set up — but first-call work is cli or container.
  • Envoy AI Gateway Drop-in once set up — but first-call work is cli or container.
  • Higress Drop-in once set up — but first-call work is cli or container.
  • LiteLLM Drop-in once set up — but first-call work is cli or container.
  • LLM Gateway Drop-in: change the base URL and key, nothing else.
  • MLflow AI Gateway Drop-in once set up — but first-call work is cli or container.
  • New API Drop-in once set up — but first-call work is cli or container.
  • Amazon Bedrock Drop-in once set up — but first-call work is cloud console setup.
  • Azure AI Foundry Drop-in once set up — but first-call work is cloud console setup.
  • Cloudflare AI Gateway Drop-in once set up — but first-call work is cloud console setup.
  • Google Vertex AI Drop-in once set up — but first-call work is cloud console setup.
  • TrueFoundry AI Gateway Drop-in once set up — but first-call work is cloud console setup.
  • Fireworks AI Drop-in once set up — but first-call work is sdk install.
  • Groq Drop-in once set up — but first-call work is sdk install.
  • Together AI Drop-in once set up — but first-call work is sdk install.

With a caveat5

No0

Everything here has some answer.

Back to top ↑

The Vercel AI SDK

15 fit · 7 with a caveat · 9 no

I build with the AI SDK. Which products have a real provider package?

Only “official provider” means a maintained first-party package. The rest are workarounds of varying quality.

Fits15

With a caveat7

No9

Back to top ↑

Cloudflare Workers

4 fit · 2 with a caveat · 25 no

I run on Workers. What can I actually call from the edge?

Three products market Cloudflare Workers heavily and mean their own gateway runs there. That does not help you call them from your Worker, so they are not counted as a fit.

Fits4

With a caveat2

No25

Back to top ↑

Kubernetes

15 fit · 2 with a caveat · 14 no

I have a cluster and want this inside it. What can I install?

Fits15

  • Requesty Helm repo https://helm.requesty.ai (chart name not stated)
  • Braintrust Gateway braintrust from oci://public.ecr.aws/braintrust/helm/braintrust
  • Helicone helicone-core, helicone-infrastructure, helicone-monitoring, helicone-argocd
  • Kong AI Gateway kong/ingress and kong/kong from https://charts.konghq.com
  • Orq.ai Router single Orq chart, Kubernetes 1.28+
  • Portkey charts/portkey-gateway and charts/portkey-app in Portkey-AI/helm
  • agentgateway agentgateway-standalone (standalone mode); agentgateway-crds + agentgateway (Kubernetes mode), all OCI charts under cr.agentgateway.dev/charts
  • Apache APISIX AI Gateway apache/apisix-helm-chart; API7 ships api7/gateway from https://charts.api7.ai
  • Bifrost bifrost/bifrost from https://maximhq.github.io/bifrost/helm-charts
  • Envoy AI Gateway oci://docker.io/envoyproxy/ai-gateway-helm plus oci://docker.io/envoyproxy/ai-gateway-crds-helm (Envoy Gateway's oci://docker.io/envoyproxy/gateway-helm required first)
  • Higress `higress.io/higress` from the `https://higress.io/helm-charts` repo, installed into namespace `higress-system`; sub-charts `higress-core` (controller + gateway) and `higress-console`
  • LiteLLM litellm-helm at oci://ghcr.io/berriai/litellm-helm — the GitHub page describes it as community maintained
  • LLM Gateway OCI chart on GHCR; deploys gateway, API, UI and worker, and needs PostgreSQL plus Redis
  • MLflow AI Gateway official chart at oci://ghcr.io/mlflow/charts/mlflow
  • TrueFoundry AI Gateway tfy-llm-gateway for the Gateway Plane, truefoundry for the full control plane plus gateway plane

With a caveat2

No14

Back to top ↑

Terraform or OpenTofu

4 fit · 11 with a caveat · 16 no

Everything I run is in code. What can I declare?

Fits4

With a caveat11

No16

Back to top ↑

An existing API gateway

12 fit · 6 with a caveat · 13 no

I already run Kong or APISIX. Can AI traffic go through it?

Fits12

  • Eden AI This is that gateway — AI traffic becomes a plugin, not a new hop.
  • Hugging Face Inference Providers This is that gateway — AI traffic becomes a plugin, not a new hop.
  • Velokey This is that gateway — AI traffic becomes a plugin, not a new hop.
  • AI Gateway HQ This is that gateway — AI traffic becomes a plugin, not a new hop.
  • Kong AI Gateway This is that gateway — AI traffic becomes a plugin, not a new hop.
  • Respan This is that gateway — AI traffic becomes a plugin, not a new hop.
  • agentgateway This is that gateway — AI traffic becomes a plugin, not a new hop.
  • Apache APISIX AI Gateway This is that gateway — AI traffic becomes a plugin, not a new hop.
  • Envoy AI Gateway This is that gateway — AI traffic becomes a plugin, not a new hop.
  • Higress This is that gateway — AI traffic becomes a plugin, not a new hop.
  • MLflow AI Gateway This is that gateway — AI traffic becomes a plugin, not a new hop.
  • New API This is that gateway — AI traffic becomes a plugin, not a new hop.

With a caveat6

No13

Back to top ↑

Cloud IAM I already run

12 fit · 1 with a caveat · 18 no

Can I authenticate with my existing cloud identity instead of another API key?

Fits12

With a caveat1

No18

  • Eden AI No identity integration published.
  • Hugging Face Inference Providers No identity integration published.
  • OpenRouter Static upstream credentials only. Your calls to it still use its own key.
  • Requesty No identity integration published.
  • Velokey No identity integration published.
  • AI Gateway HQ Static upstream credentials only. Your calls to it still use its own key.
  • Helicone No identity integration published.
  • Merge Gateway Static upstream credentials only. Your calls to it still use its own key.
  • Orq.ai Router Static upstream credentials only. Your calls to it still use its own key.
  • Portkey No identity integration published.
  • Respan Static upstream credentials only. Your calls to it still use its own key.
  • Higress Static upstream credentials only. Your calls to it still use its own key.
  • LLM Gateway No identity integration published.
  • MLflow AI Gateway Static upstream credentials only. Your calls to it still use its own key.
  • New API Static upstream credentials only. Your calls to it still use its own key.
  • Cloudflare AI Gateway Static upstream credentials only. Your calls to it still use its own key.
  • Groq No identity integration published.
  • Together AI No identity integration published.
Back to top ↑

LangChain or LlamaIndex

17 fit · 8 with a caveat · 6 no

I orchestrate in Python. What has documented framework integrations?

Fits17

With a caveat8

No6

Back to top ↑

MCP servers to govern

10 fit · 19 with a caveat · 2 no

I have MCP servers and need one place to control access to them.

Only an MCP gateway answers this. A hosted MCP server or MCP tool support in a completion API is a different product shape wearing the same acronym.

Fits10

With a caveat19

No2

Back to top ↑

Nothing — plain Node or Python

11 fit · 12 with a caveat · 8 no

I want to write code and call something. No console, no cluster.

Fits11

With a caveat12

  • Eden AI Change one base URL, but a payment method is needed first.
  • Kong AI Gateway You have to run a process locally before any call works.
  • Merge Gateway Change one base URL, but a payment method is needed first.
  • Portkey Install a package, but an upstream provider key is a prerequisite.
  • agentgateway You have to run a process locally before any call works.
  • Apache APISIX AI Gateway You have to run a process locally before any call works.
  • Bifrost You have to run a process locally before any call works.
  • Envoy AI Gateway You have to run a process locally before any call works.
  • Higress You have to run a process locally before any call works.
  • LiteLLM You have to run a process locally before any call works.
  • MLflow AI Gateway You have to run a process locally before any call works.
  • New API You have to run a process locally before any call works.

No8

Back to top ↑

A note on what “no” means here

Almost every “no” on this page is silence in the vendor’s documentation rather than a refused feature. A product with no published Workers guidance may well work fine from a Worker — it is a fetch call — but nobody has committed to that in writing, so verifying it is your job rather than theirs. That distinction is worth more when you are choosing than a confident tick would be.

Reading it the other way round: each product’s own page carries the same checklist scored for that one product, alongside the evidence links behind every answer. See the full list, or answer a few questions and let the site narrow it for you.