What it is

An AI gateway that sits between your app and providers: one API for 250+ models with automatic fallbacks, load balancing, retries, semantic caching, budget-capped virtual keys and guardrails, plus built-in observability. It is a control plane, not a model host.

Why it earns a slot

When one provider going down must not take your app with it, Portkey fails over automatically. Virtual keys with hard budget caps stop a runaway loop or a leaked key from producing a five-figure bill.

Know before you commit

The free tier keeps logs for only 3 days, often too short to debug an incident reported the next week. The hosted gateway adds a network hop unless you self-host it.

Getting started

npm i portkey-ai (or pip install portkey-ai)

Field notes

0 from the community

Sign in to add a field note. Reading is always open.

Loading notes…

Field check

Unverified

Sign in to confirm this entry is still accurate.

Pricing snapshot

Developer free forever (10,000 logs/mo, 3-day log retention), Production $49/mo (100k logs, $9 per extra 100k), Enterprise custom for 10M+ logs. Open-source gateway is self-hostable.

Snapshots move fast — verify at checkout, and post a field note if it changed.

Drop into your Lovable chat

Evaluate Portkey (https://portkey.ai) for this project, then use it only if it fits what we are already building.
Context: AI gateway with guardrails. An AI gateway that sits between your app and providers: one API for 250+ models with automatic fallbacks, load balancing, retries, semantic caching, budget-capped virtual keys and guardrails, plus built-in observability. It is a control plane, not a model host.
Reviewer notes (general, not written for this codebase): When one provider going down must not take your app with it, Portkey fails over automatically. Virtual keys with hard budget caps stop a runaway loop or a leaked key from producing a five-figure bill.
Watch out for: The free tier keeps logs for only 3 days, often too short to debug an incident reported the next week. The hosted gateway adds a network hop unless you self-host it.
Pricing: Developer free forever (10,000 logs/mo, 3-day log retention), Production $49/mo (100k logs, $9 per extra 100k), Enterprise custom for 10M+ logs. Open-source gateway is self-hostable.
Setup: npm i portkey-ai (or pip install portkey-ai)
Rules: treat the notes above as background only. Do not assume a theme, style, layout or feature that is not already in this project — inspect the existing code first and ask me before changing visual direction.

/api/public/tools/portkey

Also in Model APIs, routers & observability

Anthropic API / Claude Platform

platform.claude.com

Frontier model provider API

PaidModel APIs, routers & observability

Per token. Opus 5 $5/$25 per M in/out; Sonnet 5 $2/$10; Haiku 4.5 $1/$5; Fable 5 and Mythos 5 $10/$50. Batch API 50% off; cache reads 0.1x input.

Open dossier

Braintrust

braintrust.dev

LLM eval and experiment platform

Free tier + paidModel APIs, routers & observability

Starter free ($10/mo model credits, 1GB data, 10k scores, 14-day retention), Pro $249/mo ($249 credits, 5GB, 50k scores), Enterprise custom. Overage $3-4/GB and $1.50-$2.50 per 1k scores.

Open dossier

Fal.ai

fal.ai

Generative media inference host

PaidModel APIs, routers & observability

Per output or per second for media models: images ~$0.02-$0.04 at 1MP, video $0.05-$0.40 per second. Serverless GPU rates $1.10-$8.50/hr with committed-use discounts.

Open dossier

Fireworks AI

fireworks.ai

Open-model inference host

Free tier + paidModel APIs, routers & observability

Per token serverless across Standard/Priority/Fast tiers; embeddings $0.008-$0.10/M. On-demand GPUs billed per second: H100/H200 ~$7-8/hr, B200 ~$10-13/hr. Fine-tuning $0.50-$40 per M training tokens. $1 free credit.

Open dossier