LangSmith

AI Agent & LLM Observability Platform

Visit websiteRequest a quote
Last verified April 24, 2026

About LangSmith

LangSmith is an LLM observability platform that provides tracing, monitoring, and evaluation for AI agents and LLM applications. It offers native tracing for agent frameworks, cost and latency tracking, online LLM-as-judge evals, custom dashboards, and alerts via webhooks or PagerDuty. Framework-agnostic with SDKs for Python, TypeScript, Go, Java, and OpenTelemetry support, it works with OpenAI, Anthropic, LlamaIndex, and custom stacks. Typical buyers are engineering teams building production LLM apps needing visibility into agent behavior, debugging failures, and performance optimization. Enterprise plans include self-hosted and BYOC options for data residency.LangSmith homepage Pricing

Framework coverage

Not yet catalogued. We only list frameworks when LangSmith publicly documents coverage in their own materials. If you work at LangSmith and want to add citations, use the correction link at the bottom of this page.

Capabilities

Features LangSmith markets publicly. Inclusion means the capability is documented — not that it's best-in-class.

LLM Evaluation

Systematic testing of LLM outputs for correctness, relevance, safety, and consistency using automated scorers, rubrics, or human review.

Model Monitoring

Production monitoring for performance, drift, data quality, and fairness regressions.

Agent Tracing

End-to-end visibility into multi-step LLM agent runs: tool calls, intermediate reasoning, token usage, latency, and errors at each step.

Prompt Management

Versioning, templating, A/B testing, and deployment workflows for LLM prompts treated as production artifacts.

Drift Detection

Automated detection of distribution shift, feature drift, prediction drift, and performance degradation in deployed ML/AI models.

Industries served

Integrations

Documented by LangSmith in public product materials.

  • OpenAI API
  • Anthropic API
  • OpenTelemetry
  • LlamaIndex

Pricing

Contact for pricing

Developer free (1 seat, 5k base traces/mo); Plus $39/seat/mo (unlimited seats, 10k base traces/mo); traces $2.50/1k base (14d), $5/1k extended (400d); Enterprise custom with self-hosting.Pricing page

Pros and cons

Pros

  • Framework-agnostic tracing with multiple SDKs and OpenTelemetry support.
  • Built-in LLM evals, cost/latency monitoring, and production alerts.
  • Enterprise self-hosted/BYOC options for data control.

Cons

  • Pricing per-seat plus usage can scale quickly for large teams/high volume.
  • Primary positioning tied to LangChain ecosystem despite agnostic claims.
  • No explicit regulatory framework coverage documented on site.

Frequently asked

Is there a free tier?+

Yes, Developer plan free with 1 seat and 5k base traces/month.

Does it support self-hosting?+

Yes, Enterprise plan offers self-hosted and BYOC deployment.

What integrations are available?+

SDKs for Python/TS/Go/Java, OpenAI/Anthropic/Vercel AI/LlamaIndex, OpenTelemetry.

How are traces priced?+

Base traces $2.50/1k (14-day retention); extended $5/1k (400 days).

Sources

Keep reading

See an error or outdated detail?

Profiles carry a last-verified date. If something is out of date or wrong, send a correction and we will review it.

Submit a correction

Work at LangSmith?

Claim this listing to propose edits to the tagline, description, pricing notes, and headquarters details. Every change is still reviewed by our editorial team.

Claim this listing