Datadog LLM Observability vs LangSmith

Side-by-side comparison from the Agent Observability Index: licensing, self-hosting, pricing model and integrations — no vendor copy, primary sources linked.

Datadog LLM ObservabilityLangSmith
One-linerLLM and agent tracing inside the Datadog APM suite, attractive to teams already standardized on Datadog for infrastructure monitoring.Closed-source tracing, evals and monitoring platform from the LangChain team, deepest integration with LangChain/LangGraph but usable via OTel from any stack.
CategoryObservability & TracingObservability & Tracing
Open sourceNoNo
Self-hostableNoYes
Pricing modelpaidfreemium
Pricing notesFree up to 40k LLM spans/mo; Pro from ~$160/mo incl. 100k LLM spans, billed per span thereafterFree developer seat; Plus ~$39/seat/mo plus usage-based trace billing; self-hosting is enterprise-only
Frameworksopenai-sdk, anthropic, langchain, amazon-bedrock, opentelemetrylangchain, langgraph, openai-sdk, opentelemetry
Funding / ownershipPublic company (NASDAQ: DDOG)LangChain raised $125M Series B (2025) at ~$1.25B valuation

How to choose

Sources: Datadog LLM Observability · LangSmith