Spanlens logo

Spanlens Breakdown

Open-source LLM observability: log cost, latency, tokens

2 community upvotes

Visit Spanlens website →

About Spanlens

Spanlens is an open-source (MIT) LLM observability platform that lets developers monitor every call their application makes to OpenAI, Anthropic, Gemini, Mistral, OpenRouter, Azure OpenAI, or a local Ollama model. Integration takes one line: swap your client's baseURL to the Spanlens proxy, or run "npx @spanlens/cli init" and the wizard rewrites your code automatically. From that moment, every request is recorded with its model, token counts, latency, cost, and full prompt and response body, with streaming responses reconstructed automatically. The dashboard turns that raw log into operational insight. Cost tracking breaks spend down per request, per model, and per end user, and parses prompt-cache tokens separately so you see real cache savings rather than sticker price. Agent tracing visualizes multi-step workflows as Gantt waterfalls and node-and-edge graphs, highlighting the critical path so you can find the slowest dependency chain in a fan-out. Anomaly detection flags 3-sigma deviations in latency, cost, or error rate against a rolling 7-day baseline with root-cause hints. Alerts on budget, error rate, and p95 latency are delivered to Email, Slack, or Discord. Spanlens goes beyond passive logging. A regex-based PII and prompt-injection scanner inspects request and response bodies and can block injections at the proxy. The savings engine spots calls that match a cheaper model's profile (for example, a gpt-4o call that looks like a classification task) and estimates the monthly saving from switching. Prompt versioning with A/B experiments compares versions on latency, cost, and error rate using Welch's t-test for statistical significance, and an LLM-as-judge evaluation framework (judge with OpenAI, Anthropic, or Gemini) scores outputs against rubric anchors, with human agreement measured by Pearson r or Cohen's kappa. Reusable datasets power offline evals and regression checks.

Who Is Spanlens For?

Spanlens is designed for a range of users, including:

  • indie hackers and solo founders
  • early-stage startup teams

How Founders Can Use Spanlens

  • Automate your email outreach to nurture leads while you sleep
  • Make smarter decisions by turning raw data into clear, actionable dashboards
  • Create product demos and explainer videos that convert visitors into users
  • Integrate into your existing workflow with minimal setup time
  • Reduce manual work so your team can focus on high-impact tasks

Spanlens vs Alternatives

    Spanlens Features

    Spanlens offers a focused set of capabilities designed for founders and growing teams. It provides features tailored to help you open-source llm observability: log cost, latency, tokens.

    • Spanlens is an open-source (MIT) LLM observability platform that lets developers monitor every call their application makes to OpenAI, Anthropic, Gemini, Mistral, OpenRouter, Azure OpenAI, or a local Ollama model
    • Integration takes one line: swap your client's baseURL to the Spanlens proxy, or run "npx @spanlens/cli init" and the wizard rewrites your code automatically
    • From that moment, every request is recorded with its model, token counts, latency, cost, and full prompt and response body, with streaming responses reconstructed automatically
    • Core functionality built around productivity
    • Designed for speed and ease of use — minimal setup required
    • Works for solo founders and small teams alike

    Pricing

    Pricing details for Spanlens are available on their official website. Many tools in the startup category offer free tiers or trials, so it's worth checking if Spanlens has one that fits your needs.

    Verdict

    Spanlens is a solid option for founders looking for a reliable tool. It's gaining traction among founders who value simplicity and results. Spanlens is an open-source (MIT) LLM observability platform that lets developers monitor every call their application makes to OpenAI, Anthropic, Gemini, Mistral, OpenRouter, Azure OpenAI, or a local Ollama model. If open-source llm observability: log cost, latency, tokens is a priority for your team, it's worth giving Spanlens a closer look.

    Frequently Asked Questions

    What is Spanlens?

    Open-source LLM observability: log cost, latency, tokens

    Who is Spanlens for?

    Spanlens is designed for founders, makers, and teams looking for solutions in Startup Tools. Spanlens is an open-source (MIT) LLM observability platform that lets developers monitor every call their application makes to OpenAI, Anthropic, Gemi...

    How much does Spanlens cost?

    Visit the Spanlens website for the latest pricing details. You can discover and review Spanlens for free on Launch Llama.

    What category does Spanlens belong to?

    Spanlens is listed under Startup Tools on Launch Llama.

    How do I get started with Spanlens?

    Click the "Visit Website" button on this page to go directly to Spanlens. You can also upvote and leave a review to help other founders discover it.

    ← Browse all products · Launch Llama home