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 selects a live target, falls back on failure, 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)          # e.g. "ch-at/gpt-4o"
print(r.provider, r.model, round(r.latency, 3), r.usage)

Install

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

pip show llmf (example fields)

Name: llmf
Version: <installed version>
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: (none)

Python API

Short form → Reply

import llmf

r = llmf.chat("Hello!")
assert isinstance(r, str)
r.text            # == str(r)
r.source          # "provider/model"
r.provider
r.model
r.latency         # seconds
r.usage           # dict or None
r.finish_reason
r.reasoning       # optional
r.attempts        # [Attempt(provider, model, ok, latency, error), ...]

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

llmf.chat("hi", model="best")
llmf.chat("hi", model=["best", "fast"])
llmf.chat("hi", provider="ch-at")
llmf.chat("hi", provider="nottrack")   # opt-in provider (not in auto chain)
llmf.chat("Describe this", images=["photo.jpg"], model="vision")

for piece in llmf.stream("Count 1 to 5"):
    print(piece, end="", flush=True)

Also: llmf.achat, llmf.astream, llmf.session(system=...).

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)
print(c.model, c.provider, c.usage, c.latency, c.attempts)

Streaming: stream=True yields chunks with choices[0].delta.content.

Catalog & configuration

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("best")
llmf.models.check()                               # live one-shot probe; ~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)
llmf.discover()                                   # opt-in external keyless catalog

Environment: LLMF_TIMEOUT, LLMF_PROXY, LLMF_MODEL, LLMF_ROUTING
Proxy: http://, https://, socks5://, socks5h://, socks4:// (stdlib)

Built-in providers (0.5.x)

Exact model lists change; use llmf models / llmf providers.

CLI

usage: llmf [options] "question"              ask once (also reads stdin)
       llmf chat                              interactive chat (/reset, /exit)
       llmf models [list|check|resolve NAME]
       llmf doctor [--all] [--include-non-chat] [--include-limited]
       llmf providers | health
       llmf serve [--port N]
       llmf version

Flags: -m/--model, -p/--provider, -s/--system, -i/--interactive, --image, --max-tokens, -t/--temperature, --stream, --json, -v, --routing ranked|adaptive, --race N, --timeout, --proxy, --live, --all, --include-limited, --include-non-chat, --no-save, --host, --port, --api-key, --cors, --strict-models, --no-fallback.

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

Behaviour

• Automatic fallback with cooldowns: rate-limit vs capacity vs “paid model” messages differ (see CHANGELOG 0.4.x).
• routing="adaptive" (latency EWMA), race=N (parallel hedge).
• Live catalog / doctor default to chat + free models only.
• Dynamic fast tag from measured latency; vision_timeout (default 90s) for image calls.
• Providers with auto=False (e.g. nottrack) never join the default chain.
• Total failure → llmf.AllProvidersFailed with .errors.

Safety

• Endpoints are unofficial and free; they may change or vanish.
• Do not send secrets or personal data.
• Opt-in providers and discover() are explicit.
• llmf serve defaults to 127.0.0.1, no CORS, unless you pass --cors / --api-key.

Development

git clone https://github.com/MoonLite-Br/llmfree.git
cd llmfree
python -m unittest discover -s tests -v
python -m build && twine check dist/*

Full history: CHANGELOG.md.

License

MIT © 2026 Html / MoonLite-Br