---
id: fhlmi
version: "1.0.5"
license: Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for… (full text in the JSON record)
license_treatment: permissive
maintenance: active
---

# fhlmi — A client to provide LLM responses for FutureHouse applications.

License: permissive · Maintenance: active · Downloads: 174.0K/mo

## What it is and what it does

fhlmi is a Python library that abstracts away the differences between multiple large language model providers, letting you write code once and swap providers without changing your application logic. It wraps providers under a common async interface, exposing methods like `call_single()` and `call()` that accept text or structured messages.

The library handles several operational concerns automatically: it tracks token usage and cost per request, enforces rate limits (tokens per minute and requests per minute) with in-memory or Redis-backed storage, retries failed requests, and supports tool calling and structured output schemas. You configure providers and limits through a config dictionary, then call the LLM through the unified interface—no need to learn each provider's API separately.

Use it for:

- Build a multi-provider LLM application where you can switch between providers by changing config without rewriting code.
- Enforce rate limits across concurrent requests to avoid hitting provider quotas or incurring unexpected costs.
- Track token usage and cost per LLM call to monitor spending and optimize prompt efficiency.
- Implement tool calling against multiple LLM providers using a single abstraction.
- Embed LLM capabilities in async Python services that need retries, timeouts, and cross-process rate limiting.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

fhlmi provides a unified async Python interface to multiple large language models, handling authentication, rate limiting, cost tracking, and tool calling across different LLM providers.

Yes, if you need a unified interface to multiple LLM providers with built-in rate limiting and cost tracking. The library is actively maintained, has low install friction, and is permissively licensed. However, verify that all runtime dependencies fit your environment before committing; the dependency footprint is substantial.

## Install

pip install fhlmi
uv add fhlmi
poetry add fhlmi

## Installing fhlmi

Before you install: Low friction install with a pure Python wheel. Active maintenance (last commit 2026-08-12, 10 days since release) and 139 repository stars suggest ongoing development. Requires Python 3.11 or later.

License in practice: Apache License 2.0 is permissive: you can use, modify, and distribute fhlmi freely in commercial and private projects, provided you include a copy of the license and document any changes you make.

Quickstart:

pip install fhlmi

from fhlmi import LiteLLMModel

llm = LiteLLMModel()
result = await llm.call_single("What is the meaning of life?")

Requires Python 3.11 or later; async/await context required; LLM provider credentials must be set in environment.

Verify before relying:

- Whether all 10 runtime dependencies are required for basic usage or if some are optional.
- Whether fhaviary is a public package or an internal dependency that may affect installation.
- Cost estimation accuracy and which LLM providers' pricing models are supported.
- Whether Redis is required for rate limiting or if in-memory storage is sufficient for typical workloads.

## Package facts

- License: Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for… (full text in the JSON record) (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 174.0K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

unified llm interface, multi-provider language model client, llm rate limiting and cost tracking, async llm wrapper, language model abstraction layer, llm tool calling, cost tracking for language models, llm-abstraction, rate-limiting, cost-tracking

[View on SkillFed](https://skillfed.io/packages/fhlmi) · [View on PyPI](https://pypi.org/project/fhlmi/)