Why This Exists
Finding a free LLM API shouldn't mean hunting through dozens of websites, signing up on five platforms, or guessing which free tier still works.
This repo is a structured, machine-readable directory of every free LLM API — with credit card requirements, base URLs, and direct API key links. All in one place.
- ✅ No-card options first — clearly shows which providers need zero payment info
- ✅ OpenAI-compatible — every provider works as a drop-in
baseURL replacement
- ✅ 90+ providers — global, India, China, Japan, Korea, Europe, Middle East, SEA
- ✅ Machine-readable — structured JSON in
data/providers.json for scripts & tools
- ✅ Community-maintained — PRs welcome to add or update providers
⚡ How to Use — 3 Steps
1. Pick a provider — see Provider Directory below. Start with Groq (no credit card, 30 RPM free).
2. Get your API key — click any Get Key → link, sign up (most need just an email), copy your key. Takes < 1 minute.
3. Plug it in — copy the base URL + model ID into your tool.
🚀 Quick Start — Use Any Free API in 30 Seconds
All providers below expose an OpenAI-compatible endpoint. Any tool that accepts baseURL + apiKey works.
Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(
base_url="https://api.groq.com/openai/v1", # free, no credit card
api_key="YOUR_GROQ_KEY", # get at console.groq.com/keys
)
response = client.chat.completions.create(
model="llama-3.3-70b-versatile",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
# Groq free tier: 30 RPM, 14,400 RPD
Node.js (OpenAI SDK)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.groq.com/openai/v1", // free, no credit card
apiKey: process.env.GROQ_API_KEY, // get at console.groq.com/keys
});
const response = await client.chat.completions.create({
model: "llama-3.3-70b-versatile",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);
curl
curl https://api.groq.com/openai/v1/chat/completions \
-H "Authorization: Bearer $GROQ_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3.3-70b-versatile",
"messages": [{"role": "user", "content": "Hello!"}]
}'
Claude Code / Cursor / Codex
# Point any OpenAI-compatible tool at a free provider:
export OPENAI_BASE_URL="https://api.groq.com/openai/v1"
export OPENAI_API_KEY="your-groq-key" # console.groq.com/keys
Tip: Swap base_url to any provider in the tables below — same code, different provider, zero cost.
📋 Provider Directory
⚡ Permanent Free Tiers
Providers with unlimited free access (rate-limited) — no time expiry.
| Provider | Card? | Notes | Max Context | Get Key |
|---|
| Groq | ✅ No | 30 RPM · 14,400 RPD | 262K | Get Key → |
| GitHub Models | ✅ No | Requires GitHub account | 1M | Get Key → |
| Google Gemini | ✅ No | 2M context on Flash | 2M | Get Key → |
| Mistral AI | ✅ No | Rate-limited free tier | 256K | Get Key → |
| Cerebras | ✅ No | Ultrafast inference | 131K | Get Key → |
| Cohere | ✅ No | 20 calls/min | 256K | Get Key → |
| Hugging Face | ✅ No | Free inference router | 131K | Get Key → |
| Cloudflare Workers AI | ✅ No | 10,000 neurons/day | 10M | Get Key → |
| OpenRouter | 📧 Email | 100+ permanent free models | 1M | Get Key → |
| Chutes AI | ✅ No | Community free tier | 131K | Get Key → |
| LLM7.io | ✅ No | No signup for basic use | 131K | Get Key → |
| NVIDIA NIM | 📱 Phone | 75+ models | 1M | Get Key → |
| SambaNova Cloud | 📧 Email | Fast Llama inference | 128K | Get Key → |
| Parasail | 📧 Email | Free tier available | — | Get Key → |
| Zhipu AI | ✅ No | GLM-4.7-Flash & GLM-4.5-Flash free, 1 concurrent req | 128K | Get Key → |
💰 Free Credits on Signup
Providers that give trial credits at registration — no monthly renewal needed.
| Provider | Credits | Expiry | Card? | Get Key |
|---|
| xAI (Grok) | $25 | Monthly | 📧 Email | Get Key → |
| Modal | $30 | Monthly | ✅ No | Get Key → |
| Hyperbolic | $10 | Never | ✅ No | Get Key → |
| Lambda AI | $10 | Never | ✅ No | Get Key → |
| AI21 Labs | $10 | Never | ✅ No | Get Key → |
| DeepSeek | $5 | On signup | 📧 Email | Get Key → |
| Anthropic | $5 | Never | 💳 Yes | Get Key → |
| Perplexity AI | $5 | Never | 💳 Yes | Get Key → |
| SiliconFlow | $2 | Never | 📧 Email | Get Key → |
| Together AI | $1 | Never | ✅ No | Get Key → |
| Fireworks AI | $1 | Never | ✅ No | Get Key → |
| Nscale | $1 | Never | 📧 Email | Get Key → |
| DeepInfra | $1 | Never | ✅ No | Get Key → |
| Novita AI | $1 | Never | ✅ No | Get Key → |
🔗 Quick Reference — Base URLs
| Provider | Base URL | Get Key |
|---|
| Groq | https://api.groq.com/openai/v1 | → |
| GitHub Models | https://models.github.ai/inference | → |
| Google Gemini | https://generativelanguage.googleapis.com/v1beta | → |
| Mistral AI | https://api.mistral.ai/v1 | → |
| Cerebras | https://api.cerebras.ai/v1 | → |
| Cohere | https://api.cohere.com/v2 | → |
| Hugging Face | https://router.huggingface.co/v1 | → |
| Cloudflare Workers AI | https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run | → |
| OpenRouter | https://openrouter.ai/api/v1 | → |
| Chutes AI | https://llm.chutes.ai/v1 | → |
| LLM7.io | https://api.llm7.io/v1 | → |
| NVIDIA NIM | https://integrate.api.nvidia.com/v1 | → |
| SambaNova | https://api.sambanova.ai/v1 | → |
| xAI (Grok) | https://api.x.ai/v1 | → |
| Hyperbolic | https://api.hyperbolic.xyz/v1 | → |
| Lambda AI | https://api.lambdalabs.com/v1 | → |
| Together AI | https://api.together.xyz/v1 | → |
| Fireworks AI | https://api.fireworks.ai/inference/v1 | → |
| DeepSeek | https://api.deepseek.com/v1 | → |
| Perplexity AI | https://api.perplexity.ai | → |
| Anthropic | https://api.anthropic.com/v1 | → |
| SiliconFlow | https://api.siliconflow.cn/v1 |
🎨 Free Image Generation APIs
Text-to-image APIs you can call for free, with the limits that actually apply. Full details: freellm.site/free-image-generation-apis · data: image_apis.json
| Provider | Free allowance | Card? | Recurring? | OpenAI-compatible | Get Key |
|---|
| Cloudflare Workers AI | 10,000 neurons/day, resets 00:00 UTC | ✅ No | Yes | No | Get Key → |
| Zhipu AI (CogView-3-Flash) | Free model; concurrency limited by account tier | ✅ No | Yes | Yes | Get Key → |
| NVIDIA NIM | Trial credits on signup (prototyping only) | 📱 Phone | No | No | Get Key → |
| Pollinations.ai | Free "Quest Pollen" balance; amount not published | 📧 Email | No | Yes | Get Key → |
| ModelScope API-Inference | Daily free Magicube balance (shared with LLM calls) | 📧 Email | Yes | Yes | Get Key → |
| SiliconFlow | $1 signup credit (international platform) | 📧 Email | No | Yes | Get Key → |
| Stability AI | 25 credits on signup (1 credit = $0.01) | ✅ No | No | No | Get Key → |
No longer free: Google Gemini (Nano Banana), Together AI, Hugging Face Inference Providers.
🌍 Regional Providers
| Provider | Specialty | Signup |
|---|
| Sarvam AI | Indian language models | → |
| Krutrim AI | Ola's Indian LLM | → |
| AI4Bharat | IIT Madras — research APIs | → |
| BharatGen | IIT Bombay — research APIs | → |
| Hanooman AI | Multilingual Indian LLM | → |
| Soket AI | Indian LLM API | → |
| Neysa AI | AI cloud platform | → |
| CoRover BharatGPT | Enterprise conversational AI | → |
| Gnani.ai | Speech & language API | → |
| Provider | Base URL | Signup |
|---|
| DeepSeek | https://api.deepseek.com/v1 | → |
| Alibaba DashScope | https://dashscope.aliyuncs.com/compatible-mode/v1 | → |
| Alibaba Model Studio | https://dashscope-intl.aliyuncs.com/compatible-mode/v1 | → |
| Moonshot AI (Kimi) | https://api.moonshot.cn/v1 | → |
| Zhipu AI | https://open.bigmodel.cn/api/paas/v4 | → |
| MiniMax | https://api.minimax.chat/v1 | → |
| StepFun | https://api.stepfun.com/v1 | → |
| Baichuan AI | https://api.baichuan-ai.com/v1 | → |
| SiliconFlow | https://api.siliconflow.cn/v1 | → |
| SenseNova | https://api.sensenova.cn/v1 | → |
| iFlytek Spark | https://spark-api-open.xf-yun.com/v1 | → |
| Volcengine Ark | https://ark.cn-beijing.volces.com/api/v3 | → |
| Tencent Hunyuan | https://hunyuan.tencentcloudapi.com | → |
| Baidu ERNIE | https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop | → |
| 01.AI (Yi) | https://api.lingyiwanwu.com/v1 | → |
| ModelScope | https://api-inference.modelscope.cn/v1 | → |
| Huawei Cloud Pangu | — | → |
Japan
| Provider | Notes | Signup |
|---|
| Sakana AI | Japanese AI research lab | → |
| Preferred Networks | PLaMo models | → |
| Fujitsu Kozuchi | Enterprise AI platform | → |
| SB Intuitions | SoftBank Japanese LLMs | → |
| Rakuten AI | RakutenAI models | → |
Korea
| Provider | Notes | Signup |
|---|
| Naver HyperCLOVA X | Korea's leading LLM | → |
| Upstage AI | Solar LLM, free credits | → |
| LG EXAONE | LG AI research lab | → |
| Wrtn Technologies | Korean AI assistant | → |
| Provider | Country | Specialty | Signup |
|---|
| Mistral AI | France | Leading European LLM | → |
| Aleph Alpha | Germany | Luminous models | → |
| DeepL API | Germany | Translation — 500K chars/month free | → |
| ElevenLabs | Poland | Voice synthesis | → |
| Stability AI | UK | Image/audio/video models | → |
| Scaleway AI | France | Llama & Mistral on EU cloud | → |
| OVHcloud AI | France | Open-source model hosting | → |
| LightOn | France | Alfred models | → |
| Silo AI | Finland | Poro Finnish LLMs | → |
| PolyAI | UK | Conversational AI | → |
| H Company | France | French AI startup | → |
Middle East
| Provider | Notes | Signup |
|---|
| Falcon (TII) | UAE open-source models — free via HuggingFace | → |
| AI71 | Falcon-based API, UAE | → |
| Inception AI | UAE AI startup | → |
| Core42 | JAIS Arabic LLM | → |
Southeast Asia
| Provider | Notes | Signup |
|---|
| AI Singapore (SEA-LION) | Multilingual SEA models, open-source | → |
| GMI Cloud | Singapore GPU cloud | → |
| NCS AI | Singapore enterprise AI | → |
🗄️ Data Structure
All provider data lives in data/providers.json. Schema:
{
"id": "groq", // unique slug
"name": "Groq", // display name
"region": "global", // global | india | china | japan | korea | europe | middle_east | sea
"base_url": "https://api.groq.com/openai/v1",
"signup_url": "https://console.groq.com/keys",
"credit_card_required": "no", // no | registration | phone | yes
"free_type": "permanent", // permanent | credits
"credit_amount_usd": null, // null for permanent tiers
"credit_expiry": null, // null | "never" | "monthly" | "on signup"
"notes": "30 RPM free tier",
"last_verified": "2026-06-28"
}
🤝 Contributing
Contributions are welcome! To add or update a provider:
- Fork this repository
- Edit
data/providers.json following the schema
- Submit a PR with a brief description
Please verify provider details on their official websites before submitting. See CONTRIBUTING.md for full guidelines.
📊 Stats
📄 License
MIT License — see LICENSE for details.
⚠️ Disclaimer
This repository is community-maintained and information may become outdated. Always verify provider details on their official websites before using their APIs. Free tier limitations and offerings are subject to change without notice.
