PricingFree (self-hosted OSS)Free cloud (10k metrics)$29/mo ProCustom Enterprise
Free (100k requests)$20/mo GrowthCustom Enterprise
SDK Languagespythonjavascripttypescript
Frameworkslangchainllamaindexvercel-aiopenai-agents
Best ForInfrastructure dashboards and alerting — best paired with Prometheus/Loki/Tempo for a fully open-source observability stack
Lightweight LLM proxy with cost tracking, caching, and rate limiting — minimal integration effort
LimitationsNo native LLM tracing; requires additional tooling (Langfuse, OpenTelemetry) for AI-specific observability; steep learning curve for the full LGTM stack
Proxy-based architecture adds a network hop; less deep tracing than Langfuse; evaluation features are basic