Know your agents worked, not just that they ran.

Every plan watches your agents run; paid plans also evaluate whether each run achieved its goal, out of the box, nothing to configure. Free plan, no card required. Named limits. No metered billing. No surprise overages.

Free
Free

For wiring up your first agents.

  • 2 agents
  • 100k events / month included
  • Unlimited health checks
  • 7 days step-by-step detail
  • 30 days run history
  • Unlimited seats + teams
Start free
Starter
$99/mo

For your first production agents.

  • 10 agents
  • 2M events / month included
  • 1,000 evaluations / month
  • 30 days step-by-step detail
  • 90 days run history
  • Email + Slack + webhook alerts
  • 1 public status page
Start free trial
Business
$399/mo

For larger fleets and longer memory.

  • Unlimited agents
  • 25M events / month included
  • 20,000 evaluations / month
  • 180 days step-by-step detail
  • A full year of run history
  • Spend guard + unlimited status pages
  • SSO / SAML + audit log
  • Priority support
Start free trial
Named limits. No metered billing. No surprise overages. Every limit above is the whole story; there is nothing metered behind it. Custom Enterprise terms are available; contact us with your agent count and event volume.
Pricing as machine-readable markdown →

AgentPing vs your LLM bill.

Most customers spend between $1,500 and $50,000 a month on LLM tokens. AgentPing typically costs 1 to 3% of that. The maths is straightforward: every paid tier sits below the variance you already see month to month on your OpenAI or Anthropic invoice. The first cost spike AgentPing catches, the kind of bug that turns a $4,000 bill into $12,000, pays for the next twelve to twenty-four months of subscription on its own.

StarterTeamBusiness
AgentPing$99/mo$199/mo$399/mo
Typical events tracked1M5M12.5M
Implied agent runs~100K~500K~1.25M
Typical LLM spend~$3,000/mo~$15,000/mo~$37,500/mo
% of LLM bill3.3%1.3%1.1%

Calculate it for your team.

Drop in your monthly LLM spend; we'll show you which tier fits and how much of your bill we'd account for.

$

Rough monthly OpenAI + Anthropic + Bedrock + Gemini total. If you're not sure, $15,000 is a typical mid-size team.

Your implied LLM spend$15,000 / month
Implied agent runs / month500,000
Recommended AgentPing tierTeam ($199/mo)
AgentPing as % of LLM bill1.3%

These numbers assume an average of 10 events per run and a balanced model mix at around $0.03 per run. Your actual mileage depends on how chatty your agents are and which models they use. The point isn't the exact percentage; it's the order of magnitude. If your monthly LLM spend has a comma in it, AgentPing pricing rounds to a rounding error.

If you don't know what your monthly LLM bill is right now, that is exactly the problem AgentPing is built to solve. Once you can see cost per agent, per customer, and per feature, the conversation moves from "is this expensive" to "where do we cut without breaking things."

A full year of run history on Team and Business.

Retention is two honest numbers: how long you can open the full step-by-step trace of a run, and how long every run's outcome, evaluation result, cost, and trend survives. Most tools keep 14 to 30 days unless you pay per-trace for more; AgentPing keeps your run history for a year on Team and Business, with 180 days of full detail on Business.

Unlimited seats. Unlimited teams.

We charge for what your agents do, not how many people watch them. Invite your whole team on every plan, including Free, and use teams to separate staging from production or one client from another.

How does AgentPing pricing compare to my LLM spend?
Most customers find AgentPing costs between 1 and 3% of their monthly LLM bill. A team spending $15,000 per month on OpenAI and Anthropic typically lands on the Team plan at $199 per month, about 1.3% of LLM spend. The first cost spike AgentPing catches almost always pays for the next twelve to twenty-four months of subscription on its own. Use the calculator above with your actual numbers.
What if I don't know my monthly LLM bill yet?
That is exactly the problem AgentPing was built to solve. Start on the free plan, point it at your agents, and within a month you will have a precise breakdown of cost per agent, per customer, and per feature. Most teams discover they are either spending less than they thought (good, upgrade to track it properly) or more (also good, they finally know where to cut). Either way, you will know.
What happens if I go over my included events?
Nothing breaks. Your data keeps flowing, your dashboards keep working, and there is no overage charge, ever. We let you know as you approach the number, and if you exceed it month after month we talk about the right plan together.
What is an evaluated run?
An evaluation is an AI review of whether a run achieved its goal, out of the box, with nothing to configure. Each paid plan includes a monthly allowance of evaluated runs, spread evenly across the month and concentrated on new and unusual runs. Health checks (completion, errors, anomalies) are separate, automatic, and unlimited on every plan.
Do evaluation top-ups roll over?
No. A top-up adds 5,000 evaluations for $25 and applies to the current calendar month only, up to 3 per month. If you need top-ups every month, your agents have outgrown the plan.
Is there per-seat pricing?
No. Unlimited seats on every plan, including Free, and unlimited teams too. We charge for what your agents do, not how many people watch them.
What counts as an event?
Each step your agent reports: a model call, a tool call, a log line, a status update. Most agents report 5 to 30 events per run; the docs have sizing examples and your live usage is always on the billing page.
What are the founding member terms?
Founding-cohort accounts keep their original price wherever it is lower than the new list, and carry double the evaluation allowance of their plan, for life.
Do you offer annual billing?
Yes. Annual billing gives you 2 months free (pay for ten, get twelve) across Starter, Team, and Business.
Can I switch plans later?
Yes. Upgrades are immediate with proration; downgrades are self-serve and take effect at the end of the cycle. Your data is never deleted by a plan change; the new retention windows apply going forward.
Do you offer custom enterprise pricing?
Yes. For single-tenant deployment, custom limits, or procurement requirements, contact us with your agent count and event volume.

Ship agents knowing what they cost, how they're running, and whether they're still good.

Free plan, no card required. Evaluations from \$99/mo. Named limits, never a surprise bill.

Or read the docs first: Spend Pulse Verify