repowiseopen-free-llm-api/awesome-freellm-apis

open-free-llm-api / awesome-freellm-apis

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.

★ 3,820
Use in your agentAsk this codebase

github.com/open-free-llm-api/awesome-freellm-apisIndexed at eb455a7Up to date with upstream

What is awesome-freellm-apis?

awesome-freellm-apis is a structured directory for finding, comparing, and configuring free LLM APIs and models. It provides provider details, model information, API key links, rate limits, context windows, and configuration snippets for AI development tools. The repository uses Markdown and includes Python code examples.

Written by a model from the README and the source

13 files and 0 symbols in 0 modules.

Start reading

Code health

Health scores land with the first index: complexity, duplication, coverage, churn and ownership across every file.

Use open-free-llm-api/awesome-freellm-apis in your agent

Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.

  1. 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
  2. 2.Paste the server URL below as the Remote MCP server URL, then click Add.
  3. 3.Click Connect. A Repowise sign-in window opens. Approve access.
  4. 4.Repowise's tools are now available in your Claude chats.

Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.

Docs
bash
https://api.repowise.dev/mcp/open-free-llm-api/awesome-freellm-apis
Editors need an API key: sign in to create one.Sign in to connect

This repo is public, so anyone with a Repowise account and an API key can connect.

Try asking

  • get_overview()
  • get_answer("how is awesome-freellm-apis put together?")
  • get_why("why is awesome-freellm-apis structured this way?")

Explore awesome-freellm-apis

Key features of awesome-freellm-apis

  • awesome-freellm-apis lists free LLM APIs with provider details, model information, rate limits, context windows, and API key links.
  • awesome-freellm-apis provides side-by-side comparisons of context windows, rate limits, and modalities across providers.
  • awesome-freellm-apis includes ready-to-copy configuration snippets for Claude Code, Cursor, Codex, Aider, and other tools.
  • awesome-freellm-apis documents OpenAI-compatible endpoints that accept a base URL and API key.
  • awesome-freellm-apis provides a Python OpenAI SDK example for sending a chat completion request.

How open-free-llm-api/awesome-freellm-apis works

awesome-freellm-apis organizes provider and model information as a machine-readable directory in the repository root. Users choose a provider, obtain an API key through the listed key link, and use the provider's base URL and model ID in a compatible tool. The code-examples directory demonstrates API usage with the OpenAI SDK and configuration through environment variables. The Python example creates an OpenAI client, sends a chat completion request, and prints the returned message. The .github directory contains repository automation files.

The codebase has 13 files and 0 symbols in 0 modules.

Getting started with awesome-freellm-apis

  1. Install the OpenAI Python package before running the Python example.
    from openai import OpenAI
  2. Create an OpenAI client with a provider base URL and API key.
    client = OpenAI(
  3. Run Codex CLI with a provider endpoint, API key, and model.
    codex --model "llama-3.3-70b-versatile"
  4. Configure Cursor by adding the model, base URL, and API key in Settings.
    Settings → Models → Add Model

Commands copied from the README

open-free-llm-api/awesome-freellm-apis FAQ

What is awesome-freellm-apis?

awesome-freellm-apis is a structured directory of free LLM APIs and models. It helps users find, compare, and configure providers with API key links and model details.

How does awesome-freellm-apis work?

awesome-freellm-apis connects provider listings with base URLs, model IDs, API keys, and tool configuration examples. Its Python example sends a chat completion request through an OpenAI-compatible endpoint.

How do I install awesome-freellm-apis?

awesome-freellm-apis uses the OpenAI Python SDK in its Python example. The example starts with from openai import OpenAI and configures a client with a base URL and API key.

What language is awesome-freellm-apis written in?

awesome-freellm-apis uses Markdown for its directory and Python for its OpenAI SDK example. Its repository also includes shell-style configuration commands.

How is the awesome-freellm-apis code organized?

awesome-freellm-apis has repository-root files, .github automation files, and code-examples files. The code examples show Python SDK usage and configuration for Codex CLI, Cursor, and Claude Code.

Who is awesome-freellm-apis for?

awesome-freellm-apis is for people who need to find and configure free LLM APIs. It supports workflows involving Claude Code, Cursor, Codex, Aider, and other AI development tools.

What license does awesome-freellm-apis use?

awesome-freellm-apis uses the MIT license.

The summary, features and answers on this page are written by a model from the README and the source, and refreshed with each index.

About this page

Get a page like this for your own codebase

Repowise built this map of open-free-llm-api/awesome-freellm-apis from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Index your repo freeSee how Repowise worksFree for 2 public repos, with a page like this one.

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.