Staxly
ai-observability

LangSmith

LLM observability, testing & evaluation — by LangChain

LLM tracing + eval + prompt management + datasets by LangChain. Framework-agnostic (works without LangChain). Free dev tier + $39/seat Plus + Enterprise with self-host.

LangSmith websiteDocs ↗

Pricing

TierPriceNotes
Developer (Free)FreeFree forever. 5,000 traces/month. 14-day retention. 1 seat. Basic evaluations.
Plus$39/mo$39/seat/month. 10k base traces included ($2.50 per 1k overage). Full evaluations, custom dashboards, email support.
EnterpriseCustomCustom. Self-host option, SSO, custom retention, dedicated support.

Limits

TierMetricValueNotes
annotation queuesUnlimited human-in-the-loop review queues (Pro+)Annotation
evaluation enginesLLM-as-judge + custom Python + offline batchEval methods
framework agnosticWorks with any LLM stack, not just LangChainFramework support
prompt canvasPrompt Hub with versioning + collaborationPrompt management
retention base14 daysBase trace retention
retention extended400 daysExtended trace retention option
plusoverage base trace$2.50 per 1k base traces (14-day retention)Plus base trace overage
plusoverage ext trace$5.00 per 1k extended traces (400-day retention)Plus extended trace overage

Features

Developer interfaces

SlugNameKindVersion
cliLangSmith CLIcli0.x
dashboardLangSmith Dashboardother
sdk-nodelangsmith-jssdk0.x
mcpLangSmith MCPmcp
sdk-pythonlangsmith-pythonsdk0.x
rest-apiLangSmith REST APIrestv1

Compare LangSmith with

Staxly is an independent catalog of developer platforms. Outbound links to LangSmith are plain references to their official pages. Pricing is verified at publication time — reconfirm on the vendor site before buying.