Why engineering teams choose Last9 vs New Relic
Both have an AI assistant, an SRE agent, and an MCP server. Last9 uses your model provider, charges nothing per investigation, runs in your own cloud account, and bills one licence. New Relic has the longer APM track record and 780+ integrations, and bills its AI in compute units.
A Last9 engineer runs the move with your team.
Named a Gartner® Cool Vendor in AI for SRE and Observability, cited for its unified telemetry platform.
The Last9 agent runs on your model provider, with no per-investigation charge, in your own cloud account.
No compute units on top of ingest. The infrastructure runs on your own cloud bill.
At a glance
Last9 vs New Relic at a glance
The questions engineering teams ask when they compare the two.
Does it have an MCP server for coding agents?
Yes, for any MCP client. An agent can also add drop rules and edit dashboards through it
Yes, a hosted MCP server, generally available since September 2026. Its tools query and investigate, and none change configuration
What does the AI cost?
No per-query or per-investigation charge
New Relic AI, the Autopilot SRE agent, and plain-English NRQL draw Advanced Compute units, a paid add-on
Can the AI use our model provider, in our own cloud?
Yes. The Last9 agent runs on your model provider or inference endpoint, and Last9 runs in your own cloud account
No. The AI runs in New Relic's own cloud, with no documented option to bring your own model, and New Relic AI is not available to HIPAA or FedRAMP accounts
How is it priced?
One licence. The infrastructure runs on your own cloud bill, at your negotiated rates
Per GB ingested, plus user seats on the user plan or compute units on the compute plan, which is in preview. Advanced Compute is an add-on
How much metric cardinality can I keep?
20M series per metric per day by default, with no sampling and no charge per label or metric name
100k series per metric name and 15M per account each day by default. Above 15M needs Advanced Compute
Can I filter telemetry before I pay to store it?
Yes. The Control Plane drops, aggregates, and routes at ingest
Yes. Pipeline Control drops data before it is stored, as part of the Advanced Compute add-on
What about our APM agents and integrations?
100+ integrations, plus anything with OpenTelemetry or Prometheus
780+ integrations, and APM agents with years of production use on Java, .NET, PHP, Ruby, and more
| Capability | Last9 | New Relic |
|---|---|---|
| Does it have an MCP server for coding agents? | Yes, for any MCP client. An agent can also add drop rules and edit dashboards through it | Yes, a hosted MCP server, generally available since September 2026. Its tools query and investigate, and none change configuration |
| What does the AI cost? | No per-query or per-investigation charge | New Relic AI, the Autopilot SRE agent, and plain-English NRQL draw Advanced Compute units, a paid add-on |
| Can the AI use our model provider, in our own cloud? | Yes. The Last9 agent runs on your model provider or inference endpoint, and Last9 runs in your own cloud account | No. The AI runs in New Relic's own cloud, with no documented option to bring your own model, and New Relic AI is not available to HIPAA or FedRAMP accounts |
| How is it priced? | One licence. The infrastructure runs on your own cloud bill, at your negotiated rates | Per GB ingested, plus user seats on the user plan or compute units on the compute plan, which is in preview. Advanced Compute is an add-on |
| How much metric cardinality can I keep? | 20M series per metric per day by default, with no sampling and no charge per label or metric name | 100k series per metric name and 15M per account each day by default. Above 15M needs Advanced Compute |
| Can I filter telemetry before I pay to store it? | Yes. The Control Plane drops, aggregates, and routes at ingest | Yes. Pipeline Control drops data before it is stored, as part of the Advanced Compute add-on |
| What about our APM agents and integrations? | 100+ integrations, plus anything with OpenTelemetry or Prometheus | 780+ integrations, and APM agents with years of production use on Java, .NET, PHP, Ruby, and more |
Differences
Where Last9 and New Relic differ
Three places the two platforms take a different approach, with the tradeoffs stated.
AI on your model, in your cloud
-
One assistant in the app, in Slack, and in your IDE through MCP. It investigates, builds a diagnosis dashboard, and hands you the link.
-
The production agent, Last9, responds to pages with context from Slack, Linear, and PagerDuty. It runs on your model provider or inference endpoint and picks the model for each step. Customer data is never used for training.
-
An agent can do more than read. Through MCP it can add a drop rule and stop ingesting the noisy source it found.
-
Agents Monitoring and a Coding Agents view for Claude Code, Cursor, Copilot, and Codex are part of the platform.
New Relic
New Relic AI, the Autopilot SRE agent, and a hosted MCP server whose tools read and investigate. The AI draws Advanced Compute units and runs in New Relic's cloud. Coding-agent tracking is Preflight, an experimental open-source tool.
Tradeoff
New Relic's AI works on NRQL and on the data model your team already knows. Compare both on your own incidents.
One licence instead of seats and compute units
-
One licence. The infrastructure runs on your own cloud bill, at your negotiated rates.
-
Labels like customer_id or tenant stay on the metric, with no charge per label or metric name.
-
Drop, remap, redact, forward, and aggregate metrics, logs, and traces at ingest, from the UI. Every rule is previewed against live data before you save it.
New Relic
The user plan bills per GB ingested and per core or full platform user. The compute plan, in preview, bills compute units instead of seats. Advanced Compute, an add-on, covers New Relic AI, Pipeline Control, and cardinality above 15M series a day.
Matters most for
Teams whose headcount grows faster than their telemetry, and teams with per-customer or per-tenant labels.
Which fits you
Which one fits your team?
Choose Last9 if
- You want AI on your own model provider, with no charge per investigation
- You want one licence instead of seats or compute units on top of ingest
- Your metrics carry per-customer or per-tenant labels past New Relic's cardinality limits
- Production data must stay in your own cloud account, managed for you
- You work in PromQL, LogQL, and OpenTelemetry, and do not want to learn NRQL
Choose New Relic if
- Your services depend on New Relic's APM agents
- Your team writes NRQL every day and does not want to rebuild its dashboards
- You need 780+ integrations in one catalogue
- A small team fits inside New Relic's free tier
Migration
Moving off New Relic
What the switch involves, and what Last9 does for you.
Forward deployed engineers
A Last9 engineer runs the move with your team.
Talk to an engineerInstrument with OpenTelemetry
Services already on OpenTelemetry or Prometheus need only a new endpoint. Services on New Relic APM agents move to OpenTelemetry instrumentation.
See the integrationsRebuild what you rely on
There is no New Relic importer. Dashboards and alerts are rebuilt, and NRQL queries are rewritten in PromQL or LogQL.
Start with the cloud-native estate
Move your Kubernetes and OpenTelemetry services to Last9 first, and keep New Relic's agents on the services that depend on them. Compare the two on your own incidents as you go.
Objections
The objections we hear most
Each one is a fair reason to hesitate.
New Relic already has New Relic AI, Autopilot, and an MCP server. Why switch for AI?
AI alone is not the difference. What differs is the model, the cost, and where it runs: the Last9 agent runs on your model provider, has no per-investigation charge, and runs inside your own cloud account.
Our team knows NRQL, and our dashboards are built on it.
NRQL does not travel, so dashboards and alerts are rebuilt and queries are rewritten in PromQL or LogQL. Anyone who does not write queries can ask in plain English. A Last9 engineer scopes the rebuild with you before you sign.
New Relic's APM agents have instrumented our services for years.
Those agents are mature, and New Relic has ingested OpenTelemetry natively since 2021. Last9 builds service discovery, dependency maps, database and external calls, Apdex, exceptions, and trace correlation from OpenTelemetry. If a service depends on a New Relic agent, keep it there and move the rest first.
Is Last9 proven at our scale?
Last9 regularly handles 500M+ events a minute and 60M+ concurrent users, and has monitored 12 of the world's 20 largest streaming events. It is SOC 2 Type II certified and PCI ready, with SSO and access controls. Teams across fintech, healthcare, gaming, media, and commerce run it in production, including Replit, Pine Labs, Tata 1mg, and Housing.com.
67%
Average reduction in observability costs
2.5x
More telemetry retained without sampling
100+
Native integrations, OpenTelemetry-first
24x7
Support from forward deployed engineers
Customers
What do Last9 customers say?
With Last9, we just eliminated the toil. No more worrying about failing dashboards or alerts — we can finally use our metrics. It just works.
Last9 allowed us to offload the operational overhead of scaling so we could focus on business alerting rather than infrastructure management.
Frequently asked questions
Ask AI about this comparison
Do not take our word for it. Send the question to an assistant and check what it finds.
Can't find the answer to your question?
Talk to our support team for help.
Start observing for free. No lock-in.
OpenTelemetry · Prometheus
Just update your config. Start seeing data on Last9 in seconds.
Datadog · New Relic · Others
We've got you covered. Bring over your dashboards & alerts in one click.
Built on Open Standards
100+ integrations. OTel native, works with your existing stack.
