mcpField
F
free-llm-apis

free-llm-apis

github.com/mnfstDevelopment11.5k425 installsUpdated today
Repository

About free-llm-apis

free-llm-apis is a skill that helps users choose a free LLM API provider and configure credentials. It is for developers seeking a free-tier service, with recommendations based on model, rate-limit, and other stated priorities plus setup and verification guidance.

Key features

  1. 01Compare free API providers by stated needs
  2. 02Recommend options based on model and rate preferences
  3. 03Guide API key and environment variable setup
  4. 04Verify configuration with a sample script or curl

Use cases

  1. 01Choose a provider that fits a project's rate needs
  2. 02Configure a provider's API key and endpoint
  3. 03Test whether API credentials work

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/mnfst/awesome-free-llm-apis --skill free-llm-apis

After installing, type/free-llm-apisin Claude Code to confirm it loaded.

Bundled filesreferences/inference-providers.mdreferences/provider-apis.md

Details

From the project README

Free LLM API Setup

Help users pick a free LLM provider and configure their API key. Every provider here has a permanent free tier, no credit card needed.

Provider Selection

Ask the user what matters most, then recommend accordingly:

PriorityBest picks
Highest rate limitsGroq (30 RPM, 14.4K RPD), Cerebras (30 RPM, 14.4K RPD)
Largest model selectionCloudflare Workers AI (49+ models), OpenRouter (32+ models)
Strongest proprietary modelsGoogle Gemini (Gemini 2.5 Pro), GitHub Models (GPT-4o)
Fastest inferenceGroq, Cerebras (both optimized for speed)
Highest token budgetMistral AI (1B tokens/month)
European providerMistral AI (EU), LLM7.io (UK)
No signup requiredLLM7.io (basic tier works without token)
Provider categories

Provider APIs -- run by the companies that train the models:

Inference providers -- third-party platforms hosting open-weight models:

  • GitHub Models, Gonka Broker, NVIDIA NIM, Groq, Cerebras, Cloudflare Workers AI, LLM7.io, Kluster AI, OpenRouter, Hugging Face
  • See references/inference-providers.md for setup instructions.

Workflow

  1. Ask what models, rate limits, or features the user cares about. If they already know which provider they want, skip to step 3.
  2. Match their priorities against the table above. Suggest 1-2 options with a short reason.
  3. Load the right reference file and walk through the setup steps for that provider (API key, code example, env var).
  4. Offer a quick test script or curl command so they can confirm the key works.

Quick Test Template

After setup, use this to verify any provider:

from openai import OpenAI

client = OpenAI(api_key="KEY", base_url="BASE_URL")

response = client.chat.completions.create(
    model="MODEL_NAME",
    messages=[{"role": "user", "content": "Say hello in one sentence."}],
    max_tokens=50
)
print(response.choices[0].message.content)

Replace KEY, BASE_URL, and MODEL_NAME with values from the provider's setup guide.

Key Notes

  • All endpoints work with the OpenAI SDK unless noted.
  • RPM = requests per minute. RPD = requests per day.
  • Google Gemini's free tier is blocked in the EEA, UK, and Switzerland.
  • "Limits undocumented" = the provider doesn't publish rate limits.
  • Don't hardcode API keys. Use environment variables or a secrets manager.

Comments

Markdown supported