Docs·API

Helicone

AgentFREE TIER

LLM observability, caching, and cost tracking for agents

helicone.ai ↗Pricing →/api/v1/latency

Operational

All systems responding normally

Last checked 21/07/2026, 10:00:56 am

414ms response

Uptime History100.00% uptime

2026-07-17Today

Uptime

100.00%

Avg Latency

555ms

P95 Latency

672ms

Fastest

395ms

Checks

150

Response Time

Last 60 checks

395ms min555ms avg736ms max

💰 Pricing

observabilityFREE

Growth: $20/mo. Team: $200/mo

10k requests/month free

⚡ Rate Limits

free

Proxy layer. Rate limits depend on underlying provider. 10k requests/month cap on free.

🤖 Models (1)

Model	Task	Context	Vision	Tools	JSON
Observability LLM observability and caching. Not an LLM.	llm	—	—	—	—

Recent Checks

Showing last 15

Operational

414ms21 July, 10:00 am

Operational

530ms21 July, 09:32 am

Operational

467ms21 July, 09:06 am

Operational

577ms21 July, 08:39 am

Operational

648ms21 July, 08:11 am

Operational

438ms21 July, 07:46 am

Operational

673ms21 July, 07:18 am

Operational

631ms21 July, 06:47 am

Operational

514ms21 July, 06:10 am

Operational

675ms21 July, 05:33 am

Operational

520ms21 July, 04:50 am

Operational

599ms21 July, 04:07 am

Operational

635ms21 July, 03:19 am

Operational

609ms21 July, 02:41 am

Operational

441ms21 July, 02:00 am

API Quick Access

Health Latency Freshness Pricing Models

Other Agent Providers

E2B

Secure cloud sandboxes for AI agents — code execution

Browserbase

Cloud browser infrastructure for AI agents — Playwright/Puppeteer

LangSmith

LLM observability, tracing, and evaluation platform

Portkey AI

AI gateway — routing, fallbacks, guardrails, observability

Vapi

Voice AI infrastructure for agents — real-time phone calls

Composio

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

Visit Helicone →View Pricing ← All Providers