# Last9 vs CubeAPM: A CubeAPM Alternative with an AI Agent > Last9 vs CubeAPM compared on AI and MCP, how each is priced and what each plan includes, trace sampling, mobile RUM and LLM monitoring, deployment in your own cloud, and APM agents, with where each one fits. Source: https://last9.io/compare/cubeapm/ Both run inside your own cloud account. Last9 adds an AI agent on your model provider, a hosted MCP server an agent can write through, and mobile RUM, on one licence. CubeAPM bills per GB and puts distributed tracing and custom dashboards on its Enterprise plan. - **Gartner Cool Vendor 2025:** Named a Gartner® Cool Vendor in AI for SRE and Observability, cited for its unified telemetry platform. - **Your model, your cloud:** The Last9 agent runs on your model provider, with no per-investigation charge, in your own cloud account. - **One licence:** Distributed tracing, profiling, custom dashboards, RBAC, and forward deployed engineers on one licence. The infrastructure runs on your own cloud bill. ## Last9 vs CubeAPM at a glance The questions engineering teams ask when they compare the two. | | **Last9** | **CubeAPM** | |---|---|---| | Does it have an MCP server for coding agents? | ✓ Yes, hosted, since March 2025, for any MCP client. An agent can act through it: add drop rules and edit dashboards | Yes, since January 2026, on your own CubeAPM instance. Its tools can only query logs, metrics, and traces | | Does it have an AI SRE agent? | ✓ Yes. The Last9 agent investigates in the app, in Slack, and in your IDE, on your model provider, with no per-investigation charge | No. CubeAPM uses AI to sample traces and index logs, and has no agent that investigates an incident | | How is it priced? | ✓ One licence. The infrastructure runs on your own cloud bill, at your negotiated rates | Per GB ingested on the Pro plan, or a custom annual price on Enterprise. Users are free, and the infrastructure runs on your own cloud bill | | Which features need a higher plan? | ✓ None. One licence covers distributed tracing, profiling, custom metrics, custom dashboards, alerting, RBAC, and forward deployed engineers | Distributed tracing, the profiler, runtime metrics, custom metrics, custom dashboards, rich alerting, RBAC, unlimited retention, and an account rep need Enterprise. Pro keeps data for 15 days | | Is trace data sampled? | ✓ No. Every trace is kept. You decide what to drop or aggregate, with rules you preview against live data | Yes. Smart Sampling decides which traces to keep, from latency, errors, and other context. The only documented setting is how many error traces to keep per service, API, and error type | | Does it cover mobile apps? | ✓ Yes. RUM SDKs for Android, iOS, React Native, and Flutter, plus the web, next to your backend telemetry | Browser RUM only. CubeAPM's docs have no Android, iOS, React Native, or Flutter SDK | | Can it monitor LLM apps and coding agents? | ✓ Yes. Agents Monitoring reports conversations, tokens, cost, latency, and success rate from OpenTelemetry GenAI telemetry, with a view for coding agents | No. CubeAPM documents no view of LLM tokens, cost, or models | | Can it run in our own cloud account? | ✓ Yes. Last9 runs in your own cloud account, on AWS or GCP in any region, and manages it for you | ✓ Yes. CubeAPM deploys in your own account on AWS, Azure, or GCP, or on-prem, and its team handles upgrades | | What about our APM agents and integrations? | 100+ integrations, plus anything with OpenTelemetry or Prometheus. The Datadog Agent can dual-ship metrics and traces to Last9 | ✓ CubeAPM also takes data from Datadog tracers, New Relic agents, and Elastic APM agents on their own protocols, so those services keep their instrumentation | ## An AI agent that investigates, on your model - **Last9:** One assistant in the app, in Slack, and in your IDE through MCP. It investigates, builds a diagnosis dashboard, and hands you the link. - **Last9:** 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. - **Last9:** An agent can do more than read. Through MCP it can add a drop rule and stop ingesting the noisy source it found. - **CubeAPM:** An MCP server on your own CubeAPM instance, documented since January 2026, with tools that can only query logs, metrics, and traces. CubeAPM uses AI to sample traces and index logs, and has no investigation agent. ## One licence, every feature - **Last9:** One licence covers distributed tracing, profiling, custom metrics, custom dashboards, alerting, and RBAC, with forward deployed engineers on your account. The infrastructure runs on your own cloud bill, at your negotiated rates. - **Last9:** 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. - **CubeAPM:** Pro bills per GB ingested, with users free, and keeps data for 15 days. Distributed tracing, the continuous profiler, runtime metrics, custom metrics, custom dashboards, rich alerting, RBAC, unlimited retention, and a dedicated account rep are on Enterprise, at a custom annual price. - **Matters most for:** Teams that need distributed tracing and their own dashboards, not only logs and infrastructure metrics. ## Every trace, and every label - **Last9:** Last9 applies no sampling. Every trace stays available for an investigation, and you decide what to drop or aggregate with rules you write and preview against live data. - **Last9:** Labels like customer_id or tenant stay on the metric, with no hard cardinality limit and no charge per label or metric name. - **CubeAPM:** Smart Sampling decides which traces to keep, from latency, errors, and other context. The only documented setting is how many error traces to keep per service, API, and error type. CubeAPM publishes no cardinality limit. - **Tradeoff:** CubeAPM's Smart Sampling cuts trace volume with no rules to write. Compare both on a trace you needed during your last incident. ## Mobile apps and LLM apps, in the same platform - **Last9:** RUM SDKs for Android, iOS, React Native, and Flutter, plus the web. Each network request from the app links to the backend trace behind it. - **Last9:** Agents Monitoring reports conversations, tokens, cost, latency, and success rate for your own LLM apps, on OpenTelemetry GenAI conventions, with a separate view for coding agents. - **CubeAPM:** Browser RUM and synthetic monitoring are on both plans. CubeAPM's docs have no mobile SDK and no view of LLM tokens, cost, or models. - **Matters most for:** Teams that ship Android or iOS apps, or LLM features, and want them and the backend in one investigation. ## Which one fits your team? **Choose Last9 if:** - You want an AI agent that investigates on your own model provider, and an MCP server an agent can write through - You need distributed tracing, custom metrics, and custom dashboards on one licence - You want every trace kept, with drop and aggregate rules you set, not a sample Smart Sampling picks - You ship mobile apps, and want Android, iOS, React Native, and Flutter RUM on the same platform **Choose CubeAPM if:** - Logs, infrastructure, and browser RUM cover what you monitor today, and the Pro plan fits - You want trace volume cut automatically, with no sampling rules to write - You run on Azure or on-prem - Your services run on New Relic or Elastic agents, and you will not re-instrument them yet ## Moving off CubeAPM What the switch involves, and what Last9 does for you. - **Forward deployed engineers:** A Last9 engineer runs the move with your team. - **Keep your instrumentation:** Services already on OpenTelemetry or Prometheus need only a new endpoint. Datadog Agent metrics and traces can dual-ship to Last9, and services on New Relic or Elastic agents move to OpenTelemetry. - **Move what you rely on:** PromQL metric queries carry over. The Last9 agent moves your dashboards and alerts with your team, and rewrites CubeAPM log queries. - **Run both:** Keep CubeAPM for services on New Relic or Elastic agents, and move your Kubernetes and OpenTelemetry services to Last9. The OpenTelemetry Collector can send the same data to both while you compare them on your own incidents. ## The objections we hear most Each one is a fair reason to hesitate. ### CubeAPM bills per GB, with no per-host or per-user fees. Why change? That is the Pro plan, and users are free on it. Distributed tracing, profiling, custom metrics, custom dashboards, RBAC, and a dedicated account rep are on Enterprise, at a custom annual price, and Pro keeps data for 15 days. Price the plan that matches what you monitor. Last9 is one licence that covers all of them, with forward deployed engineers on your account. ### CubeAPM already runs in our own cloud account. It does, and its team manages it. CubeAPM states that no log or trace data leaves your cloud, and it also runs on Azure and on-prem, where Last9 runs on AWS or GCP. The difference is in what runs there: Last9 runs its AI agent in your account too. ### CubeAPM support answers in minutes on Slack. Its reviewers praise that most, and Last9 works the same way: a shared channel in Slack, Microsoft Teams, or Google Chat, with forward deployed engineers on your account. ### Our services run on New Relic and Datadog agents. CubeAPM takes data from those agents on their own protocols. Last9 takes dual-shipped Datadog Agent metrics and traces, and services on New Relic agents move to OpenTelemetry. If a service depends on a New Relic agent, keep it on CubeAPM 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. ## FAQ ### Is Last9 a good CubeAPM alternative? CubeAPM runs in your own cloud account, bills per GB, and puts distributed tracing and custom dashboards on its Enterprise plan. Last9 also runs in your own cloud account, and adds an AI agent on your model provider, a hosted MCP server an agent can write through, and mobile RUM, on one licence. CubeAPM fits better if your services stay on New Relic or Elastic agents, or you run on Azure or on-prem. ### How does Last9's MCP server compare with the CubeAPM MCP server? The CubeAPM MCP server, documented since January 2026, runs on your own CubeAPM instance, and its tools can only query logs, metrics, and traces. Last9's hosted MCP server, available since March 2025, works with any MCP client, such as Claude Code or Cursor, and lets an agent act on what it finds: add drop rules to change what is ingested, and edit dashboards. ### How does Last9's AI compare with CubeAPM? CubeAPM uses AI to sample traces and index logs, and has no agent that investigates an incident. The Last9 agent investigates in the app, in Slack, and in your IDE, runs on your model provider inside your own cloud account, and has no per-query or per-investigation charge. ### How does Last9 billing compare with CubeAPM pricing? CubeAPM pricing is per GB ingested on the Pro plan, with users free, and a custom annual price on Enterprise, which adds distributed tracing, profiling, custom metrics, custom dashboards, RBAC, unlimited retention, and a dedicated account rep. Last9 is one licence that covers all of them, with forward deployed engineers on your account, and the infrastructure runs on your own cloud bill at your negotiated rates. ### How does Last9 compare with CubeAPM metrics? CubeAPM answers PromQL for metrics, puts custom metrics on Enterprise, and publishes no cardinality limit or series-per-metric figure. Last9 answers the same PromQL and has no hard cardinality limit: 20M series per metric per day by default, raised on request, with no sampling and no charge per label or metric name. ### Is there a CubeAPM alternative that runs in our cloud account? CubeAPM deploys in your own cloud account on AWS, Azure, or GCP, or on-prem, and its team handles upgrades. Last9 runs single-tenant in your own cloud account, on AWS or GCP in any region, and manages it for you, including the AI. ### Can Last9 replace CubeAPM APM? CubeAPM takes data from Datadog, New Relic, and Elastic APM agents and from OpenTelemetry, and puts distributed tracing on Enterprise. Last9 covers service discovery, dependency maps, database and external calls, Apdex, exceptions, and trace correlation, from OpenTelemetry, as part of the platform. ### Can Last9 run alongside CubeAPM? Yes. CubeAPM takes data from New Relic and Elastic APM agents on their own protocols, so keep it for services on those agents, and move your Kubernetes and OpenTelemetry services to Last9. The OpenTelemetry Collector can send the same data to both, and a Last9 engineer plans the split with your team. ### How do I migrate from CubeAPM to Last9? CubeAPM is OpenTelemetry-native, so services already sending OTLP need only a new endpoint, and PromQL metric queries carry over. The Last9 agent moves your dashboards and alerts with your team, and rewrites CubeAPM log queries.