by Datadog

Datadog LLM Observability pricing, plans and limits

Traces, evaluates and monitors LLM apps and AI agents inside Datadog, billing only on LLM spans, with up to 40K of them free each month.

Best for
Platform engineer
Not for
Solo developer wanting a self-hosted tracer

Should you use Datadog LLM Observability?

Pick it if your team already runs Datadog and wants agent traces, experiments and evals beside service metrics. Skip it if you need a self-hosted open-source tracer or more than 15 days of retention without an add-on. Only LLM calls are billed, so tool-heavy agents stay cheaper to trace.

Agent traces share one account with backend services, infrastructure and user sessions.

Datadog keeps LLM traces in the same account as its infrastructure and application monitoring, per its product page.

Also for

  • ML engineer
  • Platform engineers at companies already running Datadog
Show 2 more
  • ML engineers shipping LLM agents to production
  • AI product teams that need traces, evals and monitoring in one place

Main trade-off

Retention is 15 days on the public plans and pricing above 100K LLM spans is not published.

Datadog LLM Observability pricing

PlanMonthly priceWhat it includes
FreeFreeUp to 40K LLM spans a month, 15-day retention of traces and experiments, Full feature access, evals included
Pro$160/moUp to 100K LLM spans a month, On-demand usage beyond 100K spans, Same feature set as Free

Datadog bills per LLM span, and neither plan gates features. Free costs $0 and Pro costs $160 a month, both in US dollars. Month-to-month and annual commitments are discounted. The product page prints no rate for on-demand usage or for retention add-ons. Checked on 2026-11-22.

What Datadog LLM Observability does

Datadog LLM Observability, now headlined by Datadog as Agent Observability, is a closed-source tracing and evaluation product for LLM apps and AI agents. It bills only on LLM spans, runs inside the Datadog platform, and its Python SDK auto-instruments OpenAI, LangChain, AWS Bedrock and Anthropic calls.

  • End-to-end tracing

    Follows each request across prompts, retrieval steps, tool calls and agent decisions, with latency, token usage, retries and errors per step.

  • Datasets from production traces

    Turns real traces into versioned datasets that experiments can be rerun against; Datadog keeps datasets for three years.

  • Experiments and playground

    Compares prompts, models and configurations against the same data before a change reaches users.

  • Evaluators and annotation

    Offers built-in and custom evaluators plus human review, and flags hallucinations, prompt injection attempts and PII exposure.

Show all 6 features
  • Sensitive data scanning

    Sensitive Data Scanner is included and scales with LLM usage, so personal data in prompts can be redacted.

  • Correlation with the rest of Datadog

    Links agent traces to backend services, infrastructure and user sessions in the same account.

Works with

  • OpenAI
  • Anthropic
  • Gemini
  • Vertex AI
  • AWS Bedrock
  • LangChain
  • CrewAI
  • Pydantic
  • LiteLLM
  • Strands Agents
  • OpenTelemetry

Strengths and limits

Strengths

  • Billing counts LLM calls only, so a trace holding ten tool calls and one model call is a single billed span, per Datadog's pricing page.
  • The Free plan carries the full feature set, experiments and evals included, per the vendor pricing page read on 2026-11-22.
  • Python SDK auto-instrumentation covers OpenAI, LangChain, AWS Bedrock and Anthropic without code changes, per Datadog's docs, and OpenTelemetry or the HTTP API cover other stacks.
  • Agent traces sit beside service, infrastructure and session data, so a slow model call can be separated from a slow database in one account.

Limits

  • Datadog's docs state the product is not supported on its government sites, app.ddog-gov.com and us2.ddog-gov.com, which rules it out for teams that must run there.
  • Free and Pro plans keep trace data for 15 days; teams that need 30 to 90 days must buy a retention add-on, and no price for it is printed on the product page.
  • Public pricing stops at 100K LLM spans a month, so a team above that has no published rate and must work out its bill from on-demand usage or a quote.

How Hokai rates it

  • Ease of use7.0 / 10
  • Features8.5 / 10
  • Value for money6.5 / 10
  • Support7.0 / 10

Datadog LLM Observability alternatives

ToolPrice fromFree planRuns onRating
Datadog LLM Observability This page$160/moYesWeb3.6
Confident AIPick Datadog LLM Observability if traces must sit beside your infrastructure monitoring; pick Confident AI if evals and CI regression tests are the main job.$200/moYesWeb--
CodagCuts AI coding-agent costs by trimming oversized tool results, from test runs to grep output, down to the lines that matter, with the rest kept on your machine.$499/moYesMac · Windows3.5
ReasonBlocksYC-backed startup that audits a team's AI evals and tests judge scores against people, with candidate model training on the side. No public pricing.QuoteNoWeb3.5

Datadog LLM Observability facts

Data retention
15 days
Compliance
HIPAA (named on the vendor product page)
Works offline
No
Minimum skill level
Intermediate
Price band
Mid-range

Data and privacy

Proprietary

Questions about Datadog LLM Observability

How much does Datadog LLM Observability cost?

Datadog prices it per LLM span, meaning a single call to a model provider. Free is $0 a month with up to 40K LLM spans, and Pro is $160 a month with up to 100K. Usage past 100K is billed on demand, and retention add-ons are billed per 10K spans. The product page prints no rate for either, and annual commitments are discounted.

Is Datadog LLM Observability free?

Yes, within a limit. The Free plan allows up to 40K LLM spans a month with 15-day retention and the full feature set, including evals. Teams that outgrow it move to Pro or on-demand billing.

What counts as an LLM span?

An LLM span is one call to an LLM provider such as OpenAI or Anthropic. Spans for tools, workflows, agents, embeddings and retrieval are not billed. One agent run can therefore contain many spans but only a few billed ones.

Which frameworks and languages does it support?

Datadog lists OpenAI, Anthropic, Gemini, Vertex AI, Bedrock, LangChain, CrewAI, Pydantic, LiteLLM and Strands Agents. SDKs cover Python, Node.js and Java, and OpenTelemetry or the HTTP API handle other stacks.

How long does Datadog keep LLM trace data?

Free and Pro keep traces, spans and experiment data for 15 days. Add-ons extend traces to 30, 60 or 90 days and experiments to 6, 9 or 12 months. Datasets are kept for three years, versioned for repeat runs.

About Datadog LLM Observability

Datadog LLM Observability is the AI tracing and evaluation product from Datadog, the monitoring vendor co-founded by CEO Olivier Pomel. Datadog's product page and docs now headline it as Agent Observability, and the old name still appears in the page title and the docs address. It sits in the AI agent observability tools category, where its main pull is that LLM traces live in the same account as a team's infrastructure and application monitoring.

Read the full background

Each request your app handles becomes a trace made of spans: an LLM call with its tokens, latency and errors, a fixed workflow of calls, or a dynamic run by an agent. The Python SDK auto-instruments frameworks and providers such as OpenAI, LangChain, AWS Bedrock and Anthropic, and Datadog's docs say this needs no code changes. CrewAI and LiteLLM are on the vendor's supported list, and any stack that can emit OpenTelemetry spans or call the HTTP API can send data too.

Beyond tracing it covers datasets built from production traces, experiments that compare prompts and models, built-in and custom evaluators, human annotation, and checks for prompt injection and sensitive data. It suits platform and ML engineers who already run Datadog and want agent traces next to service traces and user sessions. The three jobs of agent observability guide explains where tracing ends and testing begins.

It is a weaker pick for a solo developer who wants a self-hosted, open-source tracer, or for a team whose main job is evaluation rather than monitoring. Confident AI is built around evals and regression tests, Openlayer leans toward governance evidence, and Kashikoi focuses on simulating agents before release. Langfuse, MIT-licensed and free to self-host according to its pricing page is the open-source alternative for teams that must run the tracer themselves. Datadog's docs also leave its government regions out of scope. Datadog's product page lists HIPAA compliance among its controls and offers local tracing on your own machine with no signup, which is the cheapest way to test it, though Hokai has not run that trial.

Bottom line: choose it if your team already pays for Datadog; choose Confident AI if evals are the main job, or Langfuse if the tracer has to be self-hosted.

Sources and guides

More AI Tools on Hokai

  • KashikoiKashikoi is a no-code simulation platform for evaluating AI agents, built by the ex-Moveworks lead behind 250+ shipped enterprise agents.
  • MaitaiMaitai is a $50 to $200/mo control plane that indexes production LLM traffic and auto-corrects bad output in real time with Sentinels.
  • SuperPenguinAI spend platform with 2 native SDKs (Python, TypeScript) that attributes provider costs to a customer, feature, or pull request instead of one monthly total.
  • CallMissedAI receptionist that answers phone calls and WhatsApp in 22 Indian languages, books appointments and sends the owner a summary. Launched in Pune in 2026.
  • CognigyBuilds voice, chat and messaging AI agents for large contact centres, running 2.6B+ interactions a year; now sold as NiCE Cognigy.
  • ParahelpSupport agent that resolves tickets over email, chat and Slack, set up by your own coding agents; Kit's AI lead is quoted beside a 70.3% auto-resolution rate.