fhlmi
A client to provide LLM responses for FutureHouse applications.
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.11 or later; async/await context required; LLM provider credentials must be set in environment.
- 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.
License · maintenance · safety
permissive license (permissive) — 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.
last release 2026-08-04 (10 days) · last repo commit 2026-08-12 · 139 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 173,969 downloads/mo, #10,294 on PyPI
Alternatives
Verify before relying
pip install fhlmi
from fhlmi import LiteLLMModel
llm = LiteLLMModel()
result = await llm.call_single("What is the meaning of life?")- 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.
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 on this page. Verify before relying on it.
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
fhlmi on PyPI
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.
Requires Python 3.11 or later; async/await context required; LLM provider credentials must be set in environment.
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?")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 | permissive license permissive |
| Python support | Supports the current Python release >=3.11 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 10 packagesaiohttpcoredisfhaviarylimitslitellmopenaiorjsonpydantictenacitytiktoken |
| Maintenance | Actively maintained 10 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 173,969 / month, #10,294 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Intended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: PythonProgramming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: fhlmi-1.0.5-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “llm rate limiting and cost tracking”
- fhlmifhlmi provides a unified async Python interface to multiple large…
- mlflowMLflow is an open-source platform for managing the complete lifecycle…
- upstash-ratelimitProvides connectionless rate limiting for Python applications in…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also unclecode-litellm · lexisnexisapi · litellm-enterprise · tokencost · any-llm-sdk · g4f · llmlingua · llm-github-models · llm-openai-plugin