Add-ons to APM and analytics products - verified
Datadog Agent Observability
Datadog Agent Observability is listed under add-ons to apm and analytics products. Datadog's docs and pricing list present the product as Agent Observability, while the docs path still reads /llm_observability and the same page still links material titled Datadog LLM Observability. No date given. Its first listed price, in its own words: Price columns: billed annually / month-to-month / on-demand (billing column headers). Stated or listed on its pages: OpenTelemetry ingest, tracing, online evals and cost tracking. Read from the vendor's own pages on October 18, 2026.
Read from docs.datadoghq.com, datadoghq.com. Docs - Pricing - Compare every tool
What changed
- Shown as Agent ObservabilityDatadog Agent Observability
Datadog's docs and pricing list present the product as Agent Observability, while the docs path still reads /llm_observability and the same page still links material titled Datadog LLM Observability. No date given.
“With Agent Observability, you can monitor, troubleshoot, and evaluate your LLM-powered applications, such as chatbots.”
docs.datadoghq.com “Agent Observability For first 100k LLM spans, per month, with 15-day retention by default For first 100k LLM spans, per month, with 15-day retention by default $160 $200 $240”
datadoghq.com
- Status, as we read it
Generally available (inferred)inferred
No page we read labels this product GA or beta. It is sold or downloadable without a beta label, so we read it as generally available.
- Ownership, name or terms changes, as recorded
Product now presented as Agent Observability (docs path remains /llm_observability)
“With Agent Observability, you can monitor, troubleshoot, and evaluate your LLM-powered applications, such as chatbots.”
docs.datadoghq.com
How Datadog Agent Observability charges
Every price line Datadog Agent Observability states, in its own words and units, with the quote. Nothing is converted.
| Price, in the vendor's words | Unit | Quote and source |
|---|---|---|
| Price columns: billed annually / month-to-month / on-demand | billing column headers | “Product Billing Unit Billed Annually Billed Month-to-month Billed On-demand” |
| First 100k LLM spans per month (15-day retention default): $160 annually, $200 month-to-month, $240 on-demand | per first 100k LLM spans per month | “Agent Observability For first 100k LLM spans, per month, with 15-day retention by default For first 100k LLM spans, per month, with 15-day retention by default $160 $200 $240” |
| 15-day retention: $3.50 / $4.20 / $5 per 10K LLM spans | per 10K LLM spans per month | “Per 10K LLM spans, per month, with 15-day trace retention and 3 month experiment retention $3.50 $4.20 $5” |
| 30-day retention: $5 / $5.70 / $6.50 per 10K LLM spans | per 10K LLM spans per month | “Per 10K LLM spans, per month, with 30-day trace retention and 6 month experiment retention $5 $5.70 $6.50” |
| 60-day retention: $6.50 / $7.20 / $8 per 10K LLM spans | per 10K LLM spans per month | “Per 10K LLM spans, per month, with 60-day trace retention and 9 month experiment retention $6.50 $7.20 $8” |
| 90-day retention: $7.50 / $8.20 / $9 per 10K LLM spans | per 10K LLM spans per month | “Per 10K LLM spans, per month, with 90-day trace retention and 12 month experiment retention $7.50 $8.20 $9” |
Free tier and retention
- Free tier
40k LLM spans are free (footnote)scope unclear
A footnote on the pricing list. Its marker sits on the on-demand price for the first 100k LLM spans, and the page does not say which plans or billing options it covers.“40k LLM spans are free.”
datadoghq.com - Data retention
90-day trace retention tier, 12 month experiment retention
“Per 10K LLM spans, per month, with 90-day trace retention and 12 month experiment retention”
datadoghq.com Default 15-day retention on base allotment
“with 15-day retention by default”
datadoghq.com
Tracing and evaluation
- OpenTelemetry / OTLP ingest
Yes, OpenTelemetry GenAI semantic conventions
“you can instrument your LLM applications with any OpenTelemetry-compatible library or framework and visualize the traces in Agent Observability.”
docs.datadoghq.com Supports OTel 1.37+ GenAI semantic conventions or OpenInference conventions
“Agent Observability supports ingesting OpenTelemetry traces that follow either the OpenTelemetry 1.37+ semantic conventions for generative AI or the supported OpenInference semantic conventions”
docs.datadoghq.com - Tracing
Yes, end-to-end tracing
“View every step of your LLM application chains and calls to pinpoint problematic requests and identify the root cause of errors.”
docs.datadoghq.com - Evals (LLM-as-a-judge)
- Not stated
Not stated on the overview or pricing pages reviewed
- Online evals
Evaluates quality, privacy and safety of LLM applications
“evaluate the quality, privacy, and safety of your LLM applications”
docs.datadoghq.com - Datasets
- Not stated
Not stated on the overview or pricing pages reviewed
Prompts, playground and cost
- Prompt management
- Not stated
Not stated on the overview or pricing pages reviewed
- Playground
- Not stated
Not stated on the overview or pricing pages reviewed
- Cost tracking
Yes, cost monitoring dashboards
“Monitor the cost, latency, performance, and usage trends for all your LLM applications”
docs.datadoghq.com
Self-hosting, license and compliance
- Self-hosting
- Not stated
Not stated on the pricing list or docs pages
- License
- Not stated
Not stated (commercial SaaS)
- SOC 2 (as listed)
- Not stated
Not stated on the pages reviewed
- HIPAA (as listed)
- Not stated
Not stated on the pages reviewed
- Regions
- Not stated
Not stated on the pricing list or overview docs pages reviewed
SDKs and integrations
- SDKs
Auto-instrumentation for Python, Node.js and Java
“Auto-instrumentation captures LLM calls for Python, Node.js, and Java applications without requiring code changes”
docs.datadoghq.com - Integrations
- Not stated
No integration count stated on the pages reviewed
Vendor claims
Scale, speed and cost statements as Datadog Agent Observability makes them. Vendor-stated, not measured.
- Vendor-stated
- Not stated
None recorded
FAQ
How much does Datadog Agent Observability cost?
In Datadog Agent Observability's own terms: Price columns: billed annually / month-to-month / on-demand (billing column headers); First 100k LLM spans per month (15-day retention default): $160 annually, $200 month-to-month, $240 on-demand (per first 100k LLM spans per month); 15-day retention: $3.50 / $4.20 / $5 per 10K LLM spans (per 10K LLM spans per month); 30-day retention: $5 / $5.70 / $6.50 per 10K LLM spans (per 10K LLM spans per month); 60-day retention: $6.50 / $7.20 / $8 per 10K LLM spans (per 10K LLM spans per month); 90-day retention: $7.50 / $8.20 / $9 per 10K LLM spans (per 10K LLM spans per month). As of October 18, 2026; prices are not converted.
Does Datadog Agent Observability accept OpenTelemetry traces?
Yes, OpenTelemetry GenAI semantic conventions, per the vendor: "you can instrument your LLM applications with any OpenTelemetry-compatible library or framework and visualize the traces in Agent Observability."
Can I self-host Datadog Agent Observability?
Not stated. Not stated on the pricing list or docs pages. License: not stated. Not stated (commercial SaaS).
What changed at Datadog Agent Observability?
Datadog's docs and pricing list present the product as Agent Observability, while the docs path still reads /llm_observability and the same page still links material titled Datadog LLM Observability. No date given.
Sources
Last verified from each vendor's own pricing pages, docs, READMEs and license files; every quote was string-matched against the page that day. This is not a ranking. Prices are shown in the vendor's own unit and change without notice, so check the linked source before you commit.
Newsletter
Know when a tracing tool changes hands
One email per week. New model releases, agent tooling changes and what they mean for what you build.