# Prune
> Prune is a managed AI gateway. Change one base URL in your OpenAI, Anthropic, Gemini, Bedrock, or OpenRouter client to cut your AI bill and protect your team from runaway spend, leaked keys and dangerous calls. Every response carries a signed cost receipt.

## One-line definition
With a single line of code, Prune cuts your AI bill and protects your team from runaway spend, leaked keys and dangerous calls.

## What Prune is
- A managed control plane between your app and LLM providers (OpenAI-compatible and Anthropic-compatible endpoints)
- Not a new model. Not "just a cache." Not a self-hosted gateway you operate yourself (see [Prune vs LiteLLM](https://www.withprune.com/docs/vs-litellm))

## What Prune does
- Save: exact and semantic caching for repeated prompts, plus cheaper-model routing, output caps, and prompt cleanup on first-time (unique) traffic
- Shield: provider keys locked in an AES-256-GCM encrypted vault, PII and secret checks, loop and anomaly detection, per-key spend caps
- Prove: every response returns a signed receipt (prune_metadata) with cost, model, cache status, and tokens saved, verifiable at /verify

## Citeable facts
- Integrate in under 5 minutes (one base URL + Prune API key)
- The one published savings number: In our 26 Sep lab, new questions cost about 94% less than sending everything to gpt-4o, and repeats were free. Lab result, not a customer bill.
- Shield checks run before the provider is called, so a blocked call costs nothing upstream
- Works with OpenAI, Anthropic (Claude), Google Gemini, AWS Bedrock, and OpenRouter; Ollama for local development
- Works with coding agents such as Cline, Kilo Code, OpenCode, and Claude Code
- Provider keys encrypted at rest and isolated per account; no SOC 2 report yet, so evaluate the architecture (vault, Shield, signed receipts)

## Who it's for
Founders and small teams shipping AI products with real OpenAI / Anthropic / Gemini / Bedrock spend who want a lower bill, safer keys, and proof of what each request cost, without running their own gateway.

## Pricing
Free plan: 15,000 proxied requests/month or 14 days from your first Optimize receipt, whichever comes first; no card. Paid plans: Starter $15/mo (250k requests) and Pro $49/mo (1M requests), billed monthly via Polar and cancelable anytime. Team $149/mo (5M requests) is coming soon. Flat fees by proxied requests, not model-based and not a cut of savings. You still pay your LLM provider for model usage; Prune reduces that bill.

## Key pages
- [Home](https://www.withprune.com/)
- [Docs](https://www.withprune.com/docs)
- [How it works](https://www.withprune.com/docs/how-it-works)
- [Security model](https://www.withprune.com/docs/security)
- [Prune vs LiteLLM](https://www.withprune.com/docs/vs-litellm)
- [Prune vs Portkey](https://www.withprune.com/docs/vs-portkey)
- [Prune vs Helicone](https://www.withprune.com/docs/vs-helicone)
- [Prune vs Cloudflare AI Gateway](https://www.withprune.com/docs/vs-cloudflare-ai-gateway)
- [Prune vs cache-first gateways](https://www.withprune.com/docs/vs-cache-gateways)
- [How to reduce your OpenAI API cost](https://www.withprune.com/guides/reduce-openai-api-cost)
- [How to stop an AI agent loop from running up your API bill](https://www.withprune.com/guides/stop-ai-agent-runaway-bill)
- [Gemini API key leaked: what to do in the first hour](https://www.withprune.com/guides/gemini-api-key-leaked)
- [Prompt caching vs semantic caching](https://www.withprune.com/guides/prompt-caching-vs-semantic-caching)
- [OpenAI API key spending limit: what exists and how to cap one key](https://www.withprune.com/guides/openai-api-key-spending-limit)
- [OpenAI or Claude API key leaked: what to do now](https://www.withprune.com/guides/openai-api-key-leaked)
- [How to limit OpenAI usage per user](https://www.withprune.com/guides/limit-openai-usage-per-user)
- [Why is my Gemini API bill so high?](https://www.withprune.com/guides/gemini-api-bill-too-high)
- [LLM model routing: when it saves money and when it breaks](https://www.withprune.com/guides/llm-model-routing)
- [Is OpenRouter safe for production?](https://www.withprune.com/guides/is-openrouter-safe-for-production)
- [How to reduce Claude Code cost with your own API key](https://www.withprune.com/guides/reduce-claude-code-cost)
- [LangChain OpenAI base URL](https://www.withprune.com/guides/langchain-openai-base-url)
- [Coding agents (Claude Code, Cline, Cursor on your own key)](https://www.withprune.com/coding-agents)
- [Prune Check: free prompt cost and security check](https://www.withprune.com/check)
- [Verify a receipt](https://www.withprune.com/verify)
- [FAQ](https://www.withprune.com/faq)
- [About](https://www.withprune.com/about)
- [Changelog](https://www.withprune.com/changelog)
- [Longer LLM summary](https://www.withprune.com/llms-full.txt)

## Contact
[hello@withprune.com](mailto:hello@withprune.com)