llmf

Free, keyless LLM access in one call — with automatic multi-provider fallback.

llmf (llmfree) is a stdlib-only Python library and CLI for public, no-API-key OpenAI-compatible endpoints. It picks a live target, falls back on errors, and runs on desktop and Termux.

import llmf

r = llmf.chat("Explain the CAP theorem in two sentences.")
print(r)              # Reply is a str subclass
print(r.source)       # "provider/model"
print(r.provider, r.model, round(r.latency, 3), r.usage)

Package metadata (pip show llmf)

Name: llmf
Version: 0.4.1
Summary: llmf (llmfree): free, keyless LLM chat with automatic multi-provider fallback — stdlib only.
Home-page: https://github.com/MoonLite-Br/llmfree
Author: Html
License: MIT
Requires-Python: >=3.8
Requires:

pip install -U llmf
pip show llmf

Install

pip install -U llmf
python -c "import llmf; print(llmf.__version__)"
llmf version

Python API

Short form → Reply

import llmf

r = llmf.chat("Hello!")
r.text, r.source, r.provider, r.model, r.latency, r.usage, r.attempts

model= aliases: fast | best | code | vision | reasoning
Also fuzzy names, full provider/id, or a list tried in order.

llmf.chat("hi", model="code", max_tokens=256)
llmf.chat("Describe this", images=["photo.jpg"], model="vision")
for piece in llmf.stream("Count 1 to 5"):
    print(piece, end="", flush=True)

OpenAI-shaped form

from llmf import LLMF

llm = LLMF()
c = llm.chat.completions.create(
    model="best",
    messages=[{"role": "user", "content": "Hello"}],
)
print(c.choices[0].message.content)

Catalog & config

llmf.models.list()
llmf.models.list(live=True)                 # chat/free only by default
llmf.models.list(live=True, include_non_chat=True)
llmf.models.resolve("fast")
llmf.models.check()                         # doctor; ~24h cache
llmf.providers.list()
llmf.health.check()
llmf.configure(timeout=30, vision_timeout=90, routing="adaptive", race=2)
llmf.register("lab", "http://localhost:11434/v1", ["llama3"], front=True)

Env: LLMF_TIMEOUT, LLMF_PROXY, LLMF_MODEL, LLMF_ROUTING.

CLI

llmf "question" | llmf ask "…"
llmf chat
llmf models [list|check|resolve NAME]
llmf doctor [--all] [--include-non-chat] [--include-limited] [--no-save]
llmf providers | health | version
llmf serve [--host 127.0.0.1] [--port 8000] [--api-key …] [--cors]

Flags: -m/--model, -p/--provider, -s/--system, --image, --max-tokens, -t/--temperature, --stream, --json, -v, --routing ranked|adaptive, --race N, --timeout, --proxy, --live, --all, --include-limited, --include-non-chat, --no-save, serve options (--strict-models, --no-fallback, …).

$ llmf -v "2+2=?"
$ llmf models
$ llmf doctor
$ llmf serve --port 8000

What’s new in 0.4.1

• Capacity vs “paid model” messages on BlockRun: capacity wins (≈10 min sleep), not hours.
• Retry after N seconds → cooldown ≈ 3×N (not flat 60s); llm7 min_interval=1.1.
• OVH default model → gpt-oss-120b (faster anonymous tier).
• Live-id filter drops more freeai utility models (madlad, realesrgan, rmbg, …).

See CHANGELOG.md for 0.4.0 behaviour (429 classes, chat/free live catalog, dynamic fast, vision_timeout).

Safety

Unofficial free endpoints may change or rate-limit. Do not send secrets. discover() is opt-in. llmf serve defaults to localhost.

License

MIT © 2026 Html / MoonLite-Br