Overview

Spanlens is an open-source LLM observability and monitoring platform. It provides a simple way to track and analyze the performance of large language models (LLMs) and their integrations with other tools and services.

Key Features

• Cost per model, live: Spend, tokens, and cache savings resolved per model and project, with prices refreshed for you.
• It pages you first: Spikes, error bursts, and latency drift come with the model and project that caused them.
• Pinned prompt versions: Pin a version per request, then compare cost and score on real traffic.
• Repeat calls cost zero: One header turns on exact-match caching. Hits skip the provider and bill zero.
• Evals run inside CI: Grade with an API key, gate the merge, queue the unsure cases for a human.

How It Works

Spanlens works by swapping the provider SDK for a drop-in replacement. This allows for the recording of full requests and responses on the wire, with no extra round-trip and no sampling by default.

Benefits

• Reduced costs: Spanlens helps you optimize your LLM usage and reduce costs by identifying areas of inefficiency.
• Improved performance: Spanlens provides detailed analytics and monitoring, allowing you to identify and fix performance issues.
• Simplified management: Spanlens provides a simple and intuitive interface for managing your LLM integrations and monitoring their performance.

Use Cases

• Monitoring and optimizing LLM performance in production environments.
• Identifying and fixing performance issues in LLM integrations.
• Comparing the performance of different LLM models and providers.

Integrations

• OpenAI
• Anthropic
• Gemini

Pricing Overview

Spanlens offers a freemium pricing model, with a free tier and several paid tiers. The free tier includes 50K requests per month, while the paid tiers offer additional features and higher request limits.