Mozilla.ai 推出 any-llm 平台公開測試版，用於監控大型語言模型效能與成本

Secure Your Keys, Track Your Costs: any-llm Managed Platform Enters Open Beta

Secure, encrypted LLM API key management across OpenAI, Anthropic, Google providers. Track costs, set budgets, avoid vendor lock-in. Free beta access now.

Over the last few weeks, we've been running a small, gated alpha of any-llm managed platform: our client-side encrypted API key vault and usage tracking service for LLM providers.

The goal was simple: learn fast, fix the rough edges, and validate the core experience with real usage.

Sign up at any-llm.ai 👈

Why any-llm Managed Platform Matters

Built on top of any-llm library, a Python library that provides a single interface to various LLM providers, this platform allows you to centralize key management and automatically capture usage analytics for both cloud-based and local LLM providers.

Stop juggling multiple API keys in your codebase. Use any-llm as your centralized encrypted key vault. A single “virtual key” works across all providers, keeping your secrets secure and off your codebase. We also handle the usage tracking and cost management so you can focus on building.

Your API keys are encrypted client-side. They are never stored in raw text on our servers. We only track metadata (token counts, model names, timestamps, performance metrics), never your prompts or responses. In addition, we also track performance data, which includes time to first token, total duration, number of chunks, and so on.

All inference happens on the client side, so the platform works with both cloud providers and local models like llamafile.

Moving to Open Beta

We're now moving from alpha to beta, and we're making the beta ungated and free. If you want to try it, you can. No waitlist.

Here's what that means:

What We're Looking for Now

Thank you to the early community who tried this and shared feedback. We want to keep that loop going. If you try it, we want to hear from you:

Submit your feedback here.

Get Started

Create your account at any-llm.ai

The core features are available in beta today. Encrypted key management, usage tracking, and cost analytics will remain free.

In the future, we plan to introduce paid tiers with advanced capabilities, but you'll always have visibility into what's changing. No surprise paywalls.

Stay in the loop. Sign up for product updates and get notified when new features are available.

Read more

mcpd Plugins: Extend Your Agent Infrastructure Without Touching Your Code

The new plugin system transforms mcpd from a tool-server manager into an extensible enforcement and transformation layer—where authentication, validation, rate limiting, and custom logic live in one governed pipeline.

Building in the Open at Mozilla.ai: 2025 Year in Review

The year 2025 has been a busy one at Mozilla.ai. From hosting live demos and speaking at conferences, to releasing our latest open-source tools, we have made a lot of progress and more exploration this year.

Polyglot AI Agents: WebAssembly Meets the Java Virtual Machine (JVM)

Leverage the JVM's polyglot capabilities to create a self-contained, enterprise-optimized server-side blueprint that combines the performance benefits of WebAssembly with the reliability and maturity of Java's ecosystem.

Introducing any-llm managed platform: A secure cloud vault and usage-tracking service for all your LLM providers

any-llm managed platform adds end-to-end encrypted API key storage and usage tracking to the any-llm ecosystem. Keys are encrypted client-side, never visible to us, while you monitor token usage, costs, and budgets in one place. Supports OpenAI, Anthropic, Google, and more.

Mozilla.ai's Blog

Subscribe to get the latest news and ideas from our team