AI Tool
Datadog LLM Observability pricing, features, company info, and alternatives
A factual product page for Datadog's LLM observability product.
Last updated April 2026 · Pricing and features verified against official documentation
Pricing
Current public pricing tiers on file for Datadog LLM Observability, last verified Apr 26, 2026.
Free
$0 / month
For individuals and small teams; includes up to 40K LLM spans, 15-day retention, unlimited context and evals, and full feature access. Pricing is effective starting May 1, 2026 and varies by region.
Pro
$240 / month
For teams running in production; includes starting at 100K LLM spans, 15-day retention, unlimited context and evals, and full feature access. Pricing is effective starting May 1, 2026 and varies by region.
What You Can Do With It
The main capabilities that shape how people use Datadog LLM Observability today.
Traces prompts, model responses, retrieval steps, tool calls, latency, token usage, and errors across AI agent workflows.
Generates datasets from production traces and uses Playground to compare prompt tweaks, model swaps, and parameter changes.
Runs built-in evaluations for quality and safety, including hallucination checks and prompt-injection detection, with Sensitive Data Scanner support.
Correlates LLM behavior with APM and RUM data so application performance and user impact can be reviewed in the same platform.
Best For
Who Datadog LLM Observability is most clearly built for.
Teams already running Datadog APM or RUM that want LLM telemetry in the same observability stack.
Teams shipping production AI agents that need trace-level debugging, quality checks, and cost monitoring.
Organizations that want Datadog's LLM observability, experiments, and security scanning in one product surface.
Platforms
Where you can use Datadog LLM Observability today.
Web
API
Python SDK
Node.js SDK
Integrations
Notable connected tools and ecosystem hooks for Datadog LLM Observability.
OpenAI
Anthropic
LangChain
AWS Bedrock
Privacy Notes
Publicly stated data-handling notes that matter when evaluating Datadog LLM Observability.
Datadog says customers control the quantity and types of data sent through the Agent, APIs, and integrations.
The privacy page says customer data is hosted in a pre-specified country and may be accessed outside that country as part of follow-the-sun support.
Datadog says it provides a DPA and, depending on the data shared, additional supplemental terms for sensitive data workflows.
Compliance
Public compliance or enterprise-governance signals we found for Datadog LLM Observability.
SOC 2 Type II
ISO/IEC 27001
GDPR
HIPAA
Access
How to integrate or build around Datadog LLM Observability.
Public API
Yes
Docs
Available
Alternatives
Other tools worth considering alongside Datadog LLM Observability.
Open-source LLM engineering platform for tracing, prompt management, evaluations, and analytics.
Framework-agnostic platform for observability, evaluation, and deployment of AI agents and LLM apps.
Open-source AI observability and evaluation platform for tracing, prompt iteration, and experiments.
LLM gateway and observability platform for routing, debugging, and cost tracking across model providers.
Product Snapshot
Datadog LLM Observability is Datadog’s product for tracing, evaluating, and monitoring LLM applications inside the Datadog platform. It connects LLM telemetry with adjacent observability and security products.
What You Can Do With It
- Trace prompts, model responses, retrieval steps, tool calls, latency, token usage, and errors across AI agent workflows.
- Generate datasets from production traces and use Playground to compare prompt tweaks, model swaps, and parameter changes.
- Run built-in evaluations for quality and safety, including hallucination checks and prompt-injection detection, with Sensitive Data Scanner support.
- Correlate LLM behavior with APM and RUM data so application performance and user impact can be reviewed in the same platform.
Why It Stands Out
It combines LLM observability, structured experiments, evaluations, and Datadog’s broader platform visibility in one product surface.
Tradeoffs To Know
- The public pricing page says the current pricing takes effect on May 1, 2026 and varies by region.
- The product sits inside the broader Datadog platform, so LLM observability is delivered alongside APM, RUM, and security products rather than as a standalone point tool.
Sources
- datadoghq.com/product/ai/llm-observability/2
- datadoghq.com/about/latest-news/press-releases/datadog-llm-observability-is-now-generally-available-to-help-businesses-monitor-improve-and-secure-generative-ai-applications
- datadoghq.com/product/ai/llm-observability
- docs.datadoghq.com/llm_observability
- datadoghq.com/privacy
- trust.datadoghq.com