by nejib1
74 free LLM API providers & 450+ free models (limits, no-card options) + Free-LLM Router: all of them behind one OpenAI/Anthropic-compatible endpoint with instant failover. Run Claude Code, Codex, Cursor, Aider on free models. Gemini, Groq, Mistral, DeepSeek, Qwen & more. Synced daily.
# Add to your Claude Code skills
git clone https://github.com/nejib1/Free-LLMGuides for using ai agents skills like Free-LLM.
See how Free-LLM compares with popular alternatives.
Free-LLM is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by nejib1. 74 free LLM API providers & 450+ free models (limits, no-card options) + Free-LLM Router: all of them behind one OpenAI/Anthropic-compatible endpoint with instant failover. Run Claude Code, Codex, Cursor, Aider on free models. Gemini, Groq, Mistral, DeepSeek, Qwen & more. Synced daily. It has 1,065 GitHub stars.
Free-LLM's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/nejib1/Free-LLM" and add it to your Claude Code skills directory (see the Installation section above).
Free-LLM is primarily written in JavaScript. It is open-source under nejib1 on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Free-LLM against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM lists this project for discovery and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
The idea: every provider below gives a small free plan, each with its own key and limits. The router stacks them: your app (Claude Code, Codex, Cursor, your own code…) talks to one OpenAI/Anthropic-compatible address, and the router always sends the request to a free model that is up — switching instantly when one is busy or out of quota.
The big advantage: many small free plans behave like one big free plan that never goes down — and the list of providers updates itself the same day from free-llm.com, for everyone, free.
npm install -g github:nejib1/Free-LLM # installs the `free-llm` command
free-llm # guided setup, then http://localhost:4000
free-llm setup claude # Claude Code now runs on free models (also: codex, opencode, aider)
Works with zero keys to try (guest mode) · one-command setup for coding agents · OpenAI, Anthropic, Codex Responses, Ollama & MCP APIs · zero dependencies · keys stay encrypted on your computer.
🔒 100% local and private: the router runs on your computer, your API keys never leave it (stored encrypted), each key is only ever sent to its own provider — no account, no telemetry, open source.
→ Read how it works · free-llm.com/router
Finding a free LLM API shouldn't mean hunting through a dozen changelogs, signing up for five platforms just to compare rate limits, or guessing which provider still has a free tier this month.
This repo — backed by the live directory at free-llm.com — is a structured, community-maintained reference covering every provider that lets you use LLMs at zero cost.
code-examples/, plus per-tool configs for Claude Code, Cursor, Codex, and OpenCodeFull details, live status, and community notes for each provider live on its page at free-llm.com/provider/<slug> (e.g. free-llm.com/provider/groq).
Most providers below expose an OpenAI-compatible endpoint. Any tool that accepts a baseURL + apiKey works — just swap the two.
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="openai/gpt-oss-120b",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
# Groq free tier: ~30 RPM, 1,000 requests/day per chat model — plenty for personal use
Point your AI coding tool at a free backend instead of a paid one:
code-examples/claude-code.mdcode-examples/cursor.mdOPENAI_BASE_URL + OPENAI_API_KEY. See code-examples/codex.md/connect or env vars. See code-examples/opencode.mdEvery other provider has a ready-to-copy snippet in code-examples/ — see Code Examples below.
Ongoing free access with rate-limited quotas that never expire.
| Provider · sign-up | Free limits | Key models |
|---|---|---|
| Google AI Studio🟢 No card | ⏱️ Varies by model (per-model limits are now shown only inside AI Studio)📅 Varies by model. Free: Gemini 3.x Flash / Flash-Lite and Gemini 2.5 Pro/Flash (2.5 redirect to…🗓️ Free of chargedetails → | Gemini 3.8 Flash, Gemma 4 26B A4B IT, Gemma 4 31B IT, Gemini 3 Flash Preview |
| Mistral (La Plateforme)📱 Phone check | ⏱️ 1 request/second🗓️ Free | Mistral Small, Mistral Large 4 (Preview), Codestral 2508, Ministral 3 8B |
| Cohere🟢 No card | ⏱️ 20 requests/minute📅 1,000 API calls/month (trial key)🗓️ 1,000 API calls/month (trial key, non-commercial) | Command A (111B), Command A Translate, Command A Vision, North Mini Code |
| NVIDIA NIM📱 Phone check | ⏱️ ~40 RPM (varies per model, not published) | GLM-5.3 Flash, Riva Translate 4B v2, Cosmos Reason 2 8B, Muse Glimmer 30B |
| Groq🟢 No card | ⏱️ 30 RPM; 8K TPM on most chat models (varies by model)📅 1,000 requests/day and 200K tokens/day on gpt-oss / Qwen (varies by model)🗓️ Free Forever | GPT-OSS 120B, Qwen3.8 27B, Whisper Large v3, Whisper Large v3 Turbo |
| Z.AI (GLM)✉️ Email sign-up | ⏱️ ~1 request/second (Flash models)📅 ~1,000 requests/day (Flash tier)🗓️ Free tier ongoing, subject to change | GLM-4.6V-Flash (vision), GLM-4.5-Flash, GLM-4.7-Flash |
| OVH AI Endpoints✉️ Email sign-up | ⏱️ 2 RPM per IP per model (anonymous, free); 400 RPM with a key (pay-as-you-go)🗓️ Beta Access | GPT OSS 120B, BGE-M3 (embeddings), Whisper Large v3 Turbo, Qwen2.5 VL 72B Instruct |
| Cloudflare Workers AI🟢 No card | ⏱️ Varies by model📅 10,000 neurons/day🗓️ ~300,000 neurons/month | FLUX.2 Dev (image), Whisper Large v3 Turbo, EuroLLM 9B, Apertus v1.5 8B |
| Hetzner Inference API💳 Card required | ⏱️ 10 requests, 4M input / 100K output tokens per 60s (per API key)📅 No daily cap published (free while the API is experimental); a Hetzner account with billing de…🗓️ Free during experimental phase, no billing system yetdetails → | Qwen3.8 27B, Qwen3.6 35B A3B |
| Kilo AI Gateway🟢 No card | ⏱️ 200 requests/hour per IP on free models (anonymous use allowed)📅 Default free models only🗓️ Free plan, no expiry | Nemotron 3.5 Lightning, Nemotron 3 Nano Omni Reasoning, Dots3-Note Preview, Reflection Beam 1.0 |
| Nous Portal💳 Card required | ⏱️ Standard rate limits (figures not published)📅 Free models only (no monthly credit)🗓️ Free tier: $0/month. A GitHub user reported (14 Sep 2026) that a payment method (Stripe, $0 ch…details → | StepFun Step 3.7 Fl |