AI Nazar vs Langfuse

AI Nazar provides observability for large language model API calls, with a dashboard for cost, latency, token counts, and errors. It supports OpenAI, Anthropic, and Gemini through wrappers around their official clients. The dashboard reports cost by request and model, tracks latency and errors, flags spend anomalies, and compares providers. Users can inspect prompts, responses, token counts, latency, and cost, then filter requests by model, provider, or status. Its TypeScript-first SDK offers a drop-in OpenAI client wrapper with streaming, function calling, and tool use. AI Nazar says telemetry is sent asynchronously without adding latency to API calls. The SDK and dashboard are open source under the MIT license. It can be used as a hosted service or self-hosted with SQLite, Postgres, or Postbase storage. By default, the SDK sends request metadata; prompt and response text are sent only when content logging is enabled. Hosted free-tier event data is retained for 30 days on a rolling basis. Dashboard usage and cost figures are estimates, not authoritative billing records.

Langfuse is an open-source AI engineering platform for teams debugging, analyzing, and iterating on AI agent applications. Its tracing records prompts, model responses, token use, latency, tool calls, retrieval steps, and metadata. Prompt Management stores, versions, deploys, and tests prompts, then links them to traces. Evaluation features include LLM-as-a-judge, code evaluators, user feedback, manual labeling, datasets, and experiments. Integrations include Python and JS/TS SDKs, OpenTelemetry, an API, CLI, MCP Server, and popular AI frameworks. Teams can self-host the MIT-licensed core on customer infrastructure using Docker, with options including Docker Compose, Kubernetes, AWS, and Azure. Langfuse reports annual SOC 2 Type 2 and ISO 27001 audits, external penetration tests, GDPR compliance, a DPA, and a HIPAA-ready region. Its Cloud traffic uses TLS 1.2+ and stored data uses AES-256 encryption. The free Hobby plan is free and includes 50k units per month, 30 days of data access, two users, and community support via GitHub. Core costs $29 a month, billed monthly.