Reading the repo
Reading the repo
How to install on Windows
134+ free LLM APIs & AI API keys from 40+ providers. Google Gemini, NVIDIA NIM, Groq, OpenRouter & more. One-click setup for Claude Code, Cursor and Codex.
Saved setup from 2 h ago
Will it work on Windows?
Never used an API before? Here's the simplest path: go to <a href="https://console.groq.com/keys" target="_blank" rel="noopener">console.groq.com/keys</a>, sign up with just an email (no credit card), copy your free key, and paste it into any example below. You'll be running in under a minute.
All providers below expose an OpenAI-compatible endpoint. Any tool that accepts baseURL + apiKey works — just swap the base URL and key.
from openai import OpenAI
client = OpenAI(
base_url="https://api.groq.com/openai/v1", # free, no credit card
api_key="GROQ_API_KEY", # get at console.groq.com/keys
)
response = client.chat.completions.create(
model="llama-3.3-70b-versatile", # see Best Models table below
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
# Groq free tier: 30 RPM, 14,400 RPD — generous for personal use
export OPENAI_BASE_URL="https://api.groq.com/openai/v1"
export OPENAI_API_KEY="your-groq-key" # get at console.groq.com/keys
codex --model "llama-3.3-70b-versatile"
Settings → Models → Add Model
Model name: llama-3.3-70b-versatile
Base URL: https://api.groq.com/openai/v1
API key: your-groq-key # get at console.groq.com/keys
# Claude Code needs an Anthropic-compatible API — use OpenRouter
export ANTHROPIC_BASE_URL="https://openrouter.ai/api"
export ANTHROPIC_AUTH_TOKEN="sk-or-v1-your-key" # openrouter.ai/keys
export ANTHROPIC_API_KEY="" # must be empty
# Note: OpenRouter Anthropic models need $10 top-up (one-time)
Most AI dev tools accept custom API endpoints — just point them at any provider above. Grab your free key, then:
ANTHROPIC_BASE_URL + ANTHROPIC_AUTH_TOKEN. <a href="https://freellm.net/config/#claude-code" target="_blank" rel="noopener">Step-by-step →</a>OPENAI_BASE_URL + OPENAI_API_KEY. <a href="https://freellm.net/config/#codex" target="_blank" rel="noopener">Step-by-step →</a>config.toml. <a href="https://freellm.net/config/#openhuman" target="_blank" rel="noopener">Step-by-step →</a>.aider.conf.yml. <a href="https://freellm.net/config/#aider" target="_blank" rel="noopener">Step-by-step →</a>More ready-to-copy configs at <a href="https://freellm.net/config/" target="_blank" rel="noopener"><strong>freellm.net/config/</strong></a>.
All providers, base URLs, and API key links are in the Quick Reference below.
Then run powershell -ExecutionPolicy Bypass -File .\setup.ps1. It stops at the first error and is safe to run again. Servers and tests aren't started; it lists them at the end. Read it first.
Needs Git: winget install Git.Git
git clone https://github.com/open-free-llm-api/awesome-freellm-apis.git cd awesome-freellm-apis
In the maintainers' order. Do the README instructions above first — they cover steps outside the terminal.
export OPENAI_BASE_URL="https://api.groq.com/openai/v1" export OPENAI_API_KEY="your-groq-key" # get at console.groq.com/keys codex --model "llama-3.3-70b-versatile" Settings → Models → Add Model Model name: llama-3.3-70b-versatile Base URL: https://api.groq.com/openai/v1 API key: your-groq-key # get at console.groq.com/keys export ANTHROPIC_BASE_URL="https://openrouter.ai/api" export ANTHROPIC_AUTH_TOKEN="sk-or-v1-your-key" # openrouter.ai/keys export ANTHROPIC_API_KEY="" # must be empty
No reports for Windows yet.
Opens a chat with this manual already filled in, for Windows. It uses your own account; gitmanual sends nothing.