Resources / Compare / Portkey alternatives

COMPARE · PORTKEY

Portkey alternatives for small teams

Palo Alto Networks acquired Portkey, and its pricing page now calls it the Prisma AIRS AI Gateway for enterprises. If you're a small team, here are three gateways that do Portkey's routing job, plus LLMtrack for AI cost tracking per feature and customer on top of whichever you pick.

Checked against each product's own pages on 16 Oct 2026 · 7 min read

Quick answer

Self-host with LiteLLM, use OpenRouter for one bill across providers, or use Cloudflare AI Gateway for caching and analytics. LLMtrack isn't a gateway. It connects to all three and adds cost per feature, margin per customer and a forecast.

What changed at Portkey

Portkey's pricing page reads: "Portkey is now PRISMA AIRS AI Gateway, generally available for all enterprises." The free Developer plan still lists 10,000 logs a month with 3 days of log retention, and Production is $49 a month.

Source: portkey.ai/pricing, 16 Oct 2026

If Portkey still works for you, nothing forces a move. Teams looking around usually want either a self-hosted option or a tool aimed at their size.

What to look for in a replacement

GATEWAY JOB

  • Routing and fallbacks across providers
  • Caching and rate limits
  • Where it runs: hosted or your own servers

COST JOB

  • Spend per feature, not just per key
  • Customer cost against plan price
  • Prices that stay current as models change

The alternatives

LiteLLM

self-hosted proxy

A proxy you run yourself. Its docs say it tracks spend "for keys, users, and teams across 100+ LLMs". Tag-level spend is an enterprise feature.

Best for: teams that want the gateway on their own servers. Connect it with LiteLLM cost tracking in LLMtrack.

OpenRouter

hosted router

One API and one bill across many providers, with automatic fallback when a provider errors. It charges a 5.5% fee ($0.80 minimum) when you buy credits and says there's no markup on inference prices.

Best for: small teams that want many models without many accounts. Connect it with OpenRouter cost tracking in LLMtrack.

Cloudflare AI Gateway

hosted gateway

Caching, rate limiting, retries, model fallback, logs and analytics including cost. Cloudflare lists it as available on all plans.

Best for: apps already on Cloudflare. Connect it with Cloudflare AI Gateway cost tracking in LLMtrack.

LLMtrack

cost layer, not a gateway

Sits beside any of the three above, or works alone through the Node and Python SDKs. Prices every request component by component from the AI API pricing sheet for 422 models, then shows cost per feature, margin per customer and the day you'll pass your budget.

Free plan: 3,000 requests a month, every feature. Pro: $11.99 a month.

Side by side

LiteLLMOpenRouterCloudflare AI GatewayLLMtrack
Routes requestsYesYesYesNo
Runs whereYour serversHostedHostedHosted, outside the request path
Spend breakdownKey, user, teamSee OpenRouter's dashboardAnalytics incl. costFeature, model, customer, margin
Connects to LLMtrackYes, one URLYes, one URLYes, one URLn/a

From each product's own docs and pricing pages, 16 Oct 2026.

Questions

Is Portkey still available for small teams?

Its pricing page still lists a free Developer plan and a $49 Production plan, alongside the new Prisma AIRS branding. Check the page for current terms.

Can LLMtrack replace Portkey on its own?

Only for the cost side. LLMtrack doesn't route, cache or retry requests. Pair it with a gateway for that.

Which gateway is cheapest?

LiteLLM costs whatever your servers cost. OpenRouter adds 5.5% on credit purchases. For the model rates themselves, compare them on the AI API cost calculator.

Keep your gateway. See where the money goes.

One URL in your gateway settings, and your next request shows up already priced.