Loading tool details…
Sentry AI Monitoring is Sentry's AI and LLM observability capability for monitoring agent runs, LLM calls, model costs, token usage, errors, traces, and production performance inside the broader Sentry platform.
Sentry AI Monitoring makes the most sense when you look at it as an extension of a familiar developer stack, not as a standalone LLM lab. It helps teams trace AI agents, model calls, token usage, costs, errors, and latency inside the same Sentry workflows used for application monitoring.
Sentry AI Monitoring is best for engineering teams that want LLM and agent observability inside Sentry's existing production monitoring stack, with public pricing starting on a free Developer plan, Team from $26/month annually, Business from $80/month annually, and custom Enterprise pricing before usage-based telemetry costs. It is best understood as an extension of Sentry's broader application monitoring platform into AI, LLM, and agent-based production systems. Instead of treating AI observability as a completely separate workflow, it connects model calls, token usage, costs, tool executions, traces, latency, and errors with the same issue tracking and performance monitoring workflows many engineering teams already use. That makes it most useful for production teams that need to debug AI behavior in the context of application code, releases, user sessions, backend services, and alerts. Public Sentry materials describe AI monitoring coverage for agent runs, LLM calls, error rates, token usage, traffic patterns, duration, and trace context when applications are instrumented with supported SDKs and integrations. The practical value is strongest when AI issues need to be investigated alongside ordinary production incidents: a slow assistant response, a failed tool call, an expensive model invocation, or a release that changed prompt behavior can be examined in the same operational environment as backend exceptions and performance traces. Teams evaluating it should distinguish this monitoring use case from prompt experimentation, offline evaluation, dataset management, or model benchmarking, where a dedicated LLM observability or evaluation product may be more suitable. Buyers should also model event volume, spans, logs, replays, attachments, retention needs, and separately priced Sentry products such as Seer before assuming the plan price reflects full production cost. Privacy review is important because prompt and response context may contain sensitive user or business data, so capture settings, scrubbing rules, access controls, retention, and regional requirements should be checked before rollout. Buyers should verify current capture behavior, data retention, plan limits, privacy settings, and framework support before relying on prompt, response, or token-level telemetry in production.
Application monitoring platform with specialized AI agent error tracking and performance monitoring.
Sentry can represent LLM calls and AI workflow steps as spans inside distributed traces, helping teams inspect the path from a user request through model calls, tools, retrieval, and application code when instrumentation is configured.
Use Case:
A multi-step RAG pipeline with slow p95 latency: the trace view helps identify whether latency is coming from retrieval, model response time, custom application code, or a downstream service.
Where supported by SDK instrumentation and model metadata, Sentry can surface token counts and cost-related usage signals so teams can investigate expensive operations and model usage trends.
Use Case:
Engineering team catches a token spike after a prompt template change deployed to production, then compares traces to identify the workflow responsible for the increase.
When AI pipeline errors occur, they can appear in Sentry's issue and trace workflows alongside application errors, making it easier to connect AI failures with releases, user sessions, and backend behavior.
Use Case:
Investigating user reports of broken AI responses: searching Sentry for the relevant user session surfaces the related trace, error, and AI workflow context.
Sentry documents AI monitoring setup examples for OpenAI Agents in Python and the Vercel AI SDK in JavaScript, while broader Sentry SDKs cover many common application environments.
Use Case:
An engineering team adds Sentry AI monitoring to a supported AI application by following the documented integration path and then validating spans in the Sentry dashboard.
Sentry's production monitoring workflow can be used to alert on relevant operational signals such as errors and latency, while AI-specific alerting depends on captured telemetry and configured metrics.
Use Case:
Setting a latency or error-rate alert for a customer-facing AI assistant so the on-call engineer can investigate slow or failing requests with trace context.
Free
Starts at $26/month when billed annually with default prepaid data
Starts at $80/month when billed annually with default prepaid data
Custom
Ready to get started with Sentry AI Monitoring?
View Pricing Options →We believe in transparent reviews. Here's what Sentry AI Monitoring doesn't handle well:
The available content positions Sentry AI Monitoring as part of Sentry's current AI observability direction for production LLM and agent systems, with coverage for agent runs, LLM calls, token usage, model cost signals, traces, and tool execution context when supported instrumentation is configured.
LLM Observability
Open-source LLM engineering platform that captures traces, runs evaluations, and helps teams analyze cost, latency, and quality across production AI apps.
AI Observability
Arize Phoenix is an open-source AI observability and evaluation platform for tracing, testing, and improving LLM applications and agents.
AI Monitoring
Open-source LLM observability and gateway platform offering one-line integration, request logging, prompt management, evals, and a multi-provider proxy.
AI Gateway
Portkey is an AI gateway for routing, observing, securing, and governing production traffic across model providers, agents, and MCP tools. It centralizes fallbacks, guardrails, prompt operations, cost tracking, and access policy for engineering teams.
Pricing and features change often. If anything on this Sentry AI Monitoring page is wrong or missing, tell us and include a link to the source. We review every correction.