Portkey
LLM observability and an AI gateway — logging, routing, and guardrails.
- Status
- Generally available
- Last checked
- Checked · Oct 12, 2026
- License
- Proprietary
- Pricing
- Free tier
What it is
Portkey is an AI gateway and observability layer for LLM apps: request logging/metrics, smart routing/fallbacks across providers, caching, and guardrails.
An AI gateway that pairs LLM observability with routing and guardrails.
When it fits — and when it doesn’t
A good fit for
Monitoring LLM API calls and costs
Logging, metrics, and routing for LLMs
Multi-provider LLM resilience
Fallbacks and caching
Known weaknesses
Each one links to the public issue, changelog or docs page it came from, where we have one.
- 01
Adds a proxy hop
Gateway sits in the request path
- 02
Younger ecosystem
Newer than general APM
What it does well
AI gateway + observability
One layer for logging, routing, fallbacks, and caching
Multi-provider routing/fallbacks
Resilience across LLM providers
Guardrails and caching
Control cost and safety
Pricing
- Free tier
- YesFree tier with monthly request allowance
- Paid from
- —
- Model
- Usage-based
- Enterprise plan
- Yes
Pricing not independently confirmed — check the vendor’s page.
Performance benchmarks
How Fast Is It?
Set up Portkey
Setup steps, common gotchas and what to check after 30 days.
Get the badge
A small badge for Portkey’s README or site: its name, “Tracked on AI Navigator”, and the availability status and check month from this page. It updates as the catalog does.
Markdown
[](https://navigateaitools.com/explorer/tool/portkey)HTML
<a href="https://navigateaitools.com/explorer/tool/portkey"><img src="https://navigateaitools.com/badge/portkey.svg" alt="Portkey — tracked on AI Navigator" height="58"></a>