← All providers
Docs·API
Portkey AI

Portkey AI

AgentFREE TIER

AI gateway — routing, fallbacks, guardrails, observability

portkey.ai ↗Pricing →/api/v1/latency

Operational

All systems responding normally

Last checked 20/07/2026, 9:02:56 pm

370ms response

Uptime History100.00% uptime
2026-07-16Today

Uptime

100.00%

Avg Latency

330ms

P95 Latency

440ms

Fastest

180ms

Checks

150

Response Time

Last 60 checks
180ms min330ms avg510ms max

💰 Pricing

gatewayFREE

Growth: $49/mo. Enterprise: custom

10k requests/month free

⚡ Rate Limits

free
RPM: 100

Free: 100 RPM, 10k requests/month. Growth: 1000 RPM.

🤖 Models (1)

ModelTaskContextVisionToolsJSON
Gateway

AI gateway with routing and observability. Not an LLM.

llm————

Recent Checks

Showing last 15
Operational
370ms20 July, 09:02 pm
Operational
355ms20 July, 07:51 pm
Operational
304ms20 July, 06:47 pm
Operational
368ms20 July, 05:43 pm
Operational
264ms20 July, 04:36 pm
Operational
362ms20 July, 03:36 pm
Operational
389ms20 July, 02:18 pm
Operational
313ms20 July, 12:52 pm
Operational
269ms20 July, 11:48 am
Operational
260ms20 July, 10:57 am
Operational
422ms20 July, 10:13 am
Operational
391ms20 July, 09:48 am
Operational
440ms20 July, 09:20 am
Operational
251ms20 July, 08:52 am
Operational
381ms20 July, 08:28 am

API Quick Access

HealthLatencyFreshnessPricingModels

Other Agent Providers

E2B

E2B

Secure cloud sandboxes for AI agents — code execution

Browserbase

Browserbase

Cloud browser infrastructure for AI agents — Playwright/Puppeteer

LangSmith

LangSmith

LLM observability, tracing, and evaluation platform

Helicone

Helicone

LLM observability, caching, and cost tracking for agents

Vapi

Vapi

Voice AI infrastructure for agents — real-time phone calls

Composio

Composio

100+ tool integrations for AI agents — GitHub, Slack, Gmail

Visit Portkey AI →View Pricing← All Providers