Skip to content
SPECIFICTION
Get listed

LangSmith

langchain.com

From $39/mo Free plan WebWindowsmacOSLinuxAPISelf-hosted
Visit langchain.com
Spec score 9.2 #1 of 34 in LLM Gateway Software

What it is

LangSmith is a commercial agent-engineering platform for building, evaluating, deploying, monitoring, and improving AI agents. It supports offline evaluations on curated datasets and real-time scoring of production interactions. Evaluation methods include human review, heuristic checks, LLM-as-judge evaluators, pairwise comparisons, and custom Python or TypeScript evaluators. Annotation queues route runs to subject-matter experts for feedback that can calibrate evaluations, improve prompts, or augment datasets. The Playground compares prompt versions or model providers, and LangSmith chat can auto-improve prompts. Observability includes agent and retrieval tracing, token and general cost tracking, trajectory monitoring, online evaluations, and webhook or PagerDuty alerts. Traces can arrive through SDKs or an API from LangGraph, custom Python, or other stacks; SDKs are listed for Python, TypeScript, Go, and Java. Hosting ranges from cloud to hybrid and self-hosted Enterprise options. The Developer plan costs nothing, Plus costs $39 a month, and Enterprise pricing is custom.

Spec sheet

What it does
LangSmith is LangChain's framework-agnostic platform for observing, evaluating and deploying AI agents.Read 15 Oct 2026 · langchain.com
Purpose
LangSmith is a commercial agent engineering platform for building, testing, deploying, monitoring, and improving AI agents.Read 5 Oct 2026 · langchain.com
Deployment
Deployment provides managed or self-hosted agent servers with streaming, cron scheduling, authentication, MCP support and more than 30 API endpoints.Read 15 Oct 2026 · langchain.com
Integrations
Documented integrations cover OpenAI, Anthropic, Bedrock, Gemini, Mistral, LiteLLM, OpenTelemetry, CrewAI, Vercel AI SDK, PydanticAI, AutoGen and many other frameworks and providers.Read 15 Oct 2026 · docs.langchain.com
Security
LangSmith's trust center lists SOC 2 Type II, ISO 27001:2022, GDPR and HIPAA compliance.Read 15 Oct 2026 · trust.langchain.com
Support
The Developer plan includes community support, and the Enterprise plan lists a support SLA.Read 5 Oct 2026 · langchain.com
Headquarters
San Francisco, California, United StatesRead 28 Sep 2026 · langchain.com
Founded
2023Read 28 Sep 2026 · langchain.com
API and CLI
LangSmith exposes a REST API and a CLI that manages projects, traces, runs, datasets, evaluators, experiments, threads and sandboxes.Read 15 Oct 2026 · github.com
CI/CD
The evaluation workflow integrates with pytest, Vitest and GitHub workflows for automated regression checks.Read 15 Oct 2026 · langchain.com
CLI installation
The CLI provides installation paths for macOS, Linux and Windows through shell scripts, PowerShell, Homebrew, Scoop, Go or downloadable binaries.Read 15 Oct 2026 · github.com
Company origins
LangChain says the company began in early 2023 and that LangSmith launched first as a commercial observability product before expanding into evaluation and deployment.Read 15 Oct 2026 · langchain.com
Company profile
LinkedIn lists LangChain as privately held, headquartered in San Francisco, with 201–500 employees and 469 employees shown on the page.Read 15 Oct 2026 · linkedin.com
Data residency
Cloud data is hosted in GCP US or EU regions, while self-hosted data remains in the customer's VPC.Read 15 Oct 2026 · langchain.com
Data use
LangChain states that LangSmith data is not used to train models and remains owned by the customer.Read 15 Oct 2026 · langchain.com
Documentation
LangChain publishes reference documentation, integration guides, deployment instructions, a CLI guide and a REST API reference.Read 15 Oct 2026 · docs.langchain.com
Evaluation
Evaluation supports offline datasets, online production evaluations, human annotation queues and side-by-side experiment comparison.Read 15 Oct 2026 · langchain.com
Evaluator types
Evaluators can be human, heuristic, LLM-as-judge, pairwise or custom Python and TypeScript code.Read 15 Oct 2026 · langchain.com
Evaluators
Its evaluation framework supports human review, heuristic checks, LLM-as-judge evaluators, pairwise comparisons, and custom evaluators in Python or TypeScript.Read 5 Oct 2026 · langchain.com
Framework support
LangSmith is framework-agnostic and accepts traces through its SDK or API from LangGraph, custom Python, or other application stacks.Read 5 Oct 2026 · langchain.com
Funding
LangChain announced a $125 million Series B at a $1.25 billion valuation on October 20, 2025.Read 15 Oct 2026 · langchain.com
Hosting
The pricing page lists Cloud hosting for Developer and Plus, with Cloud, Hybrid, or Self-Hosted options for Enterprise.Read 5 Oct 2026 · langchain.com
Human feedback
Annotation queues let teams assign runs to subject-matter experts and use feedback to calibrate evaluations, improve prompts, or augment datasets.Read 5 Oct 2026 · langchain.com
Legal entity
Crunchbase identifies the maker as LangChain, Inc., a privately held San Francisco company founded by Harrison Chase and Ankush Gola.Read 15 Oct 2026 · crunchbase.com
Limit: deployment documentation
A LangChain forum user reported authentication failures and difficulty understanding deployment secrets, assistant IDs and setup documentation.Read 15 Oct 2026 · forum.langchain.com
Limit: large datasets
Product Hunt reviewers report that the UI becomes cumbersome with large datasets and long experiment histories, and filtered-result sharing is awkward.Read 15 Oct 2026 · producthunt.com
Limit: learning curve
Reviewers commonly describe the interface and concepts as dense or overwhelming for new users.Read 15 Oct 2026 · g2.com
Limit: outage
On May 1, 2025, a certificate and DNS configuration error caused a 28-minute US API, web and SDK outage with about 55% of requests failing.Read 15 Oct 2026 · blog.langchain.com
Limit: pricing predictability
Reviewers report that seat charges combined with trace volume, retention and usage metering make production costs difficult to forecast.Read 15 Oct 2026 · aws.amazon.com
Monitoring
Monitoring dashboards track token usage, latency percentiles, error rates, cost and feedback scores, with webhook and PagerDuty alerts.Read 15 Oct 2026 · langchain.com
Observability
Its observability features include agent tracing, cost tracking, online LLM-as-judge and code evaluations, trajectory monitoring, and webhook or PagerDuty alerts.Read 5 Oct 2026 · langchain.com
Platform license
The hosted and self-hosted LangSmith platform is proprietary and requires a LangChain license key for self-hosted use.Read 15 Oct 2026 · langchain.com
Praise: debugging
Independent reviewers repeatedly praise end-to-end traces for exposing prompts, model calls, tool steps, latency and token costs, which shortens debugging.Read 15 Oct 2026 · aws.amazon.com
Praise: evaluation
Reviewers repeatedly cite datasets, automated evaluations, human feedback and regression testing as useful for improving AI applications.Read 15 Oct 2026 · g2.com
Prompt tools
Prompt Hub and Playground provide prompt versioning, testing, comparison and AI-assisted improvement.Read 15 Oct 2026 · langchain.com
Rating on AWS Marketplace
4.4 out of 5 from 78 external ratings sourced from G2; the listing shows zero AWS-native reviews.Read 15 Oct 2026 · aws.amazon.com
Rating on G2
4.4 out of 5 from 78 reviews.Read 15 Oct 2026 · g2.com
Rating on Gartner Peer Insights
4.4 out of 5 from 25 ratings.Read 15 Oct 2026 · gartner.com
Rating on Product Hunt
4.8 out of 5 from 19 reviews.Read 15 Oct 2026 · producthunt.com
Retention
Base traces are retained for 14 days and extended traces for 180 days at an additional charge.Read 15 Oct 2026 · langchain.com
Retention limit
The pricing page states base traces have 14-day retention and extended traces have 180-day retention, with an additional fee to upgrade base traces.Read 5 Oct 2026 · langchain.com
SDK license
The public LangSmith SDK repository is released under the MIT license.Read 15 Oct 2026 · github.com
SDKs
Official SDK documentation is provided for Python, JavaScript/TypeScript, Go and Java.Read 15 Oct 2026 · docs.langchain.com
Security news
LangChain announced an unqualified SOC 2 Type II report covering security, availability and confidentiality on September 3, 2026.Read 15 Oct 2026 · trust.langchain.com
Self-hosting
Enterprise customers can run LangSmith self-hosted or hybrid on Kubernetes in AWS, Google Cloud or Azure.Read 15 Oct 2026 · docs.langchain.com
System requirements
Agent Server deployments require PostgreSQL and Redis; self-hosted installations may use customer-managed PostgreSQL and Redis.Read 15 Oct 2026 · docs.langchain.com
Tracing
Tracing records agent conversations and runs step by step, including prompts, model calls, tools, errors, latency and token usage.Read 15 Oct 2026 · langchain.com

Plans and prices

Developer Free $0 per seat per month; usage pay-as-you-go 1 seat · 5,000 base traces/month · community support Read 15 Oct 2026 · langchain.com
Plus $39 a month $39 per seat per month; usage pay-as-you-go 10,000 base traces/month · unlimited seats · 1 free small serverless deployment Read 15 Oct 2026 · langchain.com
Enterprise Priced on request invoiced annually upfront; usage pay-as-you-go self-hosted or hybrid deployment · custom SSO, ABAC and RBAC · support SLA Read 15 Oct 2026 · langchain.com

Every LangSmith plan and price →

Strong points and limits

Strong points

  • Offline and real-time agent evaluations
  • Human, heuristic, model-based, and custom evaluators
  • Agent, retrieval, and token-cost tracing
  • Integrates with pytest, Vitest, and GitHub workflows
  • Cloud, hybrid, and self-hosted options

Limits

  • Base traces have 14-day retention
  • Extended trace retention costs extra
  • Enterprise pricing is custom
  • Developer support is community-based

Who it suits

LangSmith suits teams engineering AI agents that need evaluation, tracing, prompt work, deployment, and production monitoring. Its hosting and access options also address organizations requiring hybrid or self-hosted deployment.

Verdict

LangSmith brings evaluation, prompt development, observability, and deployment into one agent-engineering platform. A free Developer plan is available, while Plus costs $39 a month and Enterprise adds custom hosting, access, and support arrangements.

Where Specifiction places it

Alternatives to LangSmithAll alternatives →