Free-LLM — Open Directory of Free AI & LLM APIs
210+ free LLM models from 47 providers — find, compare & configure free models in seconds, plus 9 local/self-hosted tools for unlimited private use.
🌐 Live at free-llm.com — Compare providers · Submit a provider · Guides · Hall of Fame
🌐 English · 简体中文 · 繁體中文 · 日本語 · 한국어
Why This Exists
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.
- ✅ Community-maintained — votes, submissions, and edit suggestions from real users, moderated before publishing
- ✅ Credit card transparency — every provider below is labeled with whether it needs a card, phone verification, or nothing at all
- ✅ Ready-to-run code — Python/JavaScript/curl snippets for all 33 providers in
code-examples/, plus per-tool configs for Claude Code, Cursor, Codex, and OpenCode - ✅ Side-by-side comparison — free-llm.com/compare puts two providers head-to-head on limits, models, and pricing
How to Use — 3 Steps
- Pick a provider — see the Provider Directory below. New to this? Start with Groq (no credit card, 30 RPM / 14,400 requests per day, free forever).
- Get your API key — every row links straight to the provider's key page in Quick Reference. Most only need an email address.
- Plug it in — copy the base URL + a model ID from the tables below into the snippets in Quick Start.
Full 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).
Quick Start — Use Any Free API in 30 Seconds
Most providers below expose an OpenAI-compatible endpoint. Any tool that accepts a baseURL + apiKey works — just swap the two.
Python (OpenAI SDK)
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",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
# Groq free tier: 30 RPM, 14,400 requests/day — generous for personal useCoding assistants
Point your AI coding tool at a free backend instead of a paid one:
- Claude Code — set
ANTHROPIC_BASE_URL+ANTHROPIC_AUTH_TOKEN. Seecode-examples/claude-code.md - Cursor — Settings → Models → Add Model. See
code-examples/cursor.md - Codex CLI — set
OPENAI_BASE_URL+OPENAI_API_KEY. Seecode-examples/codex.md - OpenCode — open source AI coding agent, supports multiple providers via
/connector env vars. Seecode-examples/opencode.md
Every other provider has a ready-to-copy snippet in code-examples/ — see Code Examples below.
Provider Directory
⚡ Permanent Free Tiers
Ongoing free access with rate-limited quotas that never expire.
| Provider | Credit Card? | Rate Limit | Daily Limit | Monthly Limit | Key Models |
|---|---|---|---|---|---|
| Google AI Studio | No | 5-30 RPM (varies by model) | Varies by model (Flash / Flash-Lite only; Pro models are paid) | Free of charge | Gemini 3.1 Flash-Lite, Gemini 3.5 Flash-Lite, Gemini 3.6 Flash, Gemini 3.8 Flash |
| Mistral (La Plateforme) | Phone verification | 1 request/second | - | Free | Codestral 2508, Ministral 3 8B, Ministral 3 14B, Mistral Large 3 |
| Cohere | No | 20 requests/minute | 1,000 API calls/month (trial key) | 1,000 API calls/month (trial key, non-commercial) | North Mini Code, Command A Reasoning, Command R+ (08-2024), Command R (08-2024) |
| NVIDIA NIM | Phone verification | ~40 RPM (varies per model, not published) | - | - | Nemotron 3 Ultra 550B A55B, Nemotron 3.5 Lightning 30B A3B, DeepSeek V4 Pro (0813), Kimi K3 |
| Groq | No | 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 | Qwen3.8 27B, MiniMax M2.7, Whisper Large v3, Whisper Large v3 Turbo |
| Z.AI (GLM) | Registration | ~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 |
| Coze | Registration | Varies by model | Token-based daily limits | Resets daily | GPT-4o (via Coze), Gemini 1.5 Pro (via Coze) |
| OVH AI Endpoints | Registration | 2 RPM per IP per model (anonymous, free); 400 RPM with a key (pay-as-you-go) | Unspecified | Beta Access | Llama 3.3 70B Instruct, GPT OSS 20B, GPT OSS 120B, Qwen3.5 9B |
| Cloudflare Workers AI | No | Varies by model | 10,000 neurons/day | ~300,000 neurons/month | GLM 4.7 Flash, Mistral Small 3.1 24B, Qwen3 30B A3B, Gemma 4 26B A4B |
| Nous Portal | No | 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 charge) is required to get a key - verify | Poolside Laguna S 2.1, StepFun Step 3.7 Flash, Upstage Solar Mini 4, Meituan LongCat 2.0 |
| Hetzner Inference API | No | 10 requests, 4M input / 100K output tokens per 60s (per API key) | No daily cap published (free while the API is experimental) | Free during experimental phase, no billing system yet | Qwen3.6 35B A3B |
| Pollinations.ai | No | API key required (anonymous access removed); no card | Free usage paid from Quest Pollen earned in the dashboard | Free, no billing system | GPT-OSS 20B, Mistral Large 3, Kimi K2.6, GLM 5.3 Flash |
| ModelScope | Phone verification | 500 requests/day per model | 2,000 requests/day total | Free, no billing | See provider |
| Ollama Cloud | No | 1 concurrent request; starter models only | Monthly starter allowance (resets monthly from sign-up date) | Weekly usage limit resets every 7 days | Gemma 4, DeepSeek V4.1 Flash, GPT-OSS 120B (Cloud), GPT-OSS 20B (Cloud) |
| SiliconFlow | Phone verification | Fixed limits for free models — exact figures require login, verify on cloud.siliconflow.cn/models | Not fully published — verify on docs.siliconflow.cn | Free models available after identity verification | GLM-4 9B 0414, DeepSeek R1 0528 Qwen3 8B, Qwen3.5 4B, GLM 5.3 Flash |
| Aion Labs | No | 15 RPM, 20K TPM (free tier) | 20,000 tokens/day (daily credit allowance, no card) | Free, no billing | See provider |
| Kilo AI Gateway | No | 200 requests/hour per IP on free models (anonymous use allowed) | Default free models only | Free plan, no expiry | inclusionAI Ling 3.1 Flash, Cohere North Mini Code, Thinking Machines Inkling Small, Nemotron 3.5 Lightning |
| Api.Airforce | No | 1 RPM | 1,000 requests/day | Free plan, $0/month | See provider |
| Routeway | Registration | 5 RPM on :free models | 200 requests/day | Starter plan free, shared queue | Muse Glimmer 30B, MiniMax M2.7, DeepSeek V4 Flash, Step 3.7 Flash |
| LLM7.io | No | 1 req/s, 60/min, 250/hour (free token from dash.llm7.io) | 100,000 tokens per 24h (free token; may be reduced without notice) | Free, no billing | Nemotron 3 Nano 30B, GLM 5.3 Flash, Mistral Nemo Instruct 2407, Codestral Latest |
💰 Renewable Credits
Free access that renews periodically, no one-time expiry.
| Provider | Credit Card? | Rate Limit | Free Offer | Key Models |
|---|---|---|---|---|
| OpenRouter | No | 20 requests/minute | 50 requests/day (up to 1000 with $10 topup) | Liquid LFM 2.5 2.6B, Nemotron 3 Nano Omni 30B A3B Reasoning, Gemma 4 26B A4B IT, Gemma 4 31B IT |
| Requesty | No | Concurrency-limited (no RPM cap published) | 200 requests/day (new orgs) / 1,000/day (paying orgs), shared across free models | Mistral Leanstral 1.5, Meta Muse Glimmer 30B, inclusionAI Ling 3.1 Flash, Gemma 4 31B IT |
| Token Harbor | Registration | Not published | Free allowance, resets on a rolling 7-day period | DeepSeek V4.1 Flash, MiMo V2.6 Flash, TH-Rudder |
| Vercel AI Gateway | Registration | Rate limited per model (lower than paid tier) | Monthly free credit (~$5, verify) | See provider |
| Onomeo | Registration | 12 requests/minute per key | 30 free-model calls every 5 hours per account | Auto (best free model), DeepSeek V4 Flash, DeepSeek V4 Pro, GLM 5.3 Flash |
🎁 One-Time Trial Credits
Sign up and receive credits to use until depleted.
| Provider | Credit Card? | Credit Amount | Expiry | Key Models |
|---|---|---|---|---|
| Replicate | Registration | Limited free runs on select models | One-time | See provider |
| Fireworks AI | Registration | $1 | One-time | GLM 5.3, DeepSeek V4.1 Flash, Kimi K3 |
| Nebius (Token Factory) | Registration | $1 trial credit, valid 30 days (bank card required) | One-time | Qwen3 235B A22B Instruct 2507, GLM 5.3, GPT OSS 120B, Qwen3.8 27B |
| Cerebras | Registration | $5 after adding a verified payment method (expires after 30 days) | 30 days | Qwen 3.8 27B, GPT OSS 120B |
| Novita AI | Registration | No automatic sign-up credit; $10 per referral (both sides) | One-time | GLM 5.3, Kimi K3, DeepSeek V4.1 Flash, Qwen3.8 27B |
| Scaleway Generative APIs | Registration | 1M tokens | One-time | Gemma 4 26B A4B IT, GPT-OSS 120B, Qwen3.6 35B A3B, DeepSeek V4 Flash (0731) |
| Qwen (Alibaba) | Registration | 1M tokens/model | One-time per model | Qwen3.8 Flash, Qwen3.7 Plus, Qwen3.8 Max, Qwen3.7 Max |
| AI21 Labs | Registration | $10 (valid 7 days, no card) | 3 months | Jamba Large, Jamba Mini |
| Upstage | Registration | $10 | 3 months | See provider |
| Cerebrium | Registration | $30 | One-time | See provider |
| Nscale | No | Minimum $5 top-up to start (no sign-up credit) | One-time | See provider |
| Friendli AI | Registration | Trial credits at onboarding (amount not published) | One-time | DeepSeek V3.2, Gemma 4 31B, GLM 5.2, GLM 5.3 Flash |
| Grokified | No | $5 | One-time | grok-4.6, grok-4.3, grok-build-0.1 |
🖥️ Local / Self-Hosted (Unlimited, Private, Free Forever)
| Tool | Type | Highlights |
|---|---|---|
| Ollama | CLI + API | 100+ models, GPU acceleration, OpenAI-compatible endpoint |
| LM Studio | Desktop GUI | Any GGUF model, built-in model browser, offline |
| llama.cpp | C/C++ engine | Runs any GGUF, minimal dependencies |
| GPT4All | Desktop app | CPU-only, no GPU required, open source |
| Jan.ai | Desktop app | Privacy-focused, 100% offline ChatGPT alternative |
| KoboldCpp | Single executable | Optimized for creative writing, GGUF |
| llamafile | Single executable | Multi-platform, combines llama.cpp + Cosmopolitan Libc |
| Text Generation WebUI | Gradio UI | Highly customizable, advanced local experimentation |
| BentoML | Inference platform | Deploy any AI/ML model anywhere, production-grade |
Quick Reference — Base URLs & API Keys
| Provider | Base URL | Get API Key |
|---|---|---|
| OpenRouter | https://openrouter.ai/api/v1 | Get Key → |
| Google AI Studio | https://generativelanguage.googleapis.com/v1beta | Get Key → |
| Mistral (La Plateforme) | https://api.mistral.ai/v1 | Get Key → |
| Cohere | https://api.cohere.ai/v1 | Get Key → |
| Replicate | https://api.replicate.com/v1 | Get Key → |
| Fireworks AI | https://api.fireworks.ai/inference/v1 | Get Key → |
| NVIDIA NIM | https://integrate.api.nvidia.com/v1 | Get Key → |
| Nebius (Token Factory) | https://api.tokenfactory.nebius.com/v1 | Get Key → |
| Cerebras | https://api.cerebras.ai/v1 | Get Key → |
| Groq | https://api.groq.com/openai/v1 | Get Key → |
| Novita AI | https://api.novita.ai/v3/openai | Get Key → |
| Scaleway Generative APIs | https://api.scaleway.ai/v1 | Get Key → |
| Qwen (Alibaba) | https://dashscope-intl.aliyuncs.com/api/v1 | Get Key → |
| AI21 Labs | https://api.ai21.com/studio/v1 | Get Key → |
| Upstage | https://api.upstage.ai/v1/solar | Get Key → |
| Z.AI (GLM) | https://api.z.ai/api/paas/v4 | Get Key → |
| Coze | https://api.coze.com/v1 | Get Key → |
| OVH AI Endpoints | https://oai.endpoints.kepler.ai.cloud.ovh.net/v1 | Get Key → |
| Cloudflare Workers AI | https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/ | Get Key → |
| Nous Portal | https://inference-api.nousresearch.com/v1 | Get Key → |
| Hetzner Inference API | https://inference.hetzner.com/api/v1 | Get Key → |
| Pollinations.ai | https://text.pollinations.ai | Get Key → |
| Requesty | https://router.requesty.ai/v1 | Get Key → |
| ModelScope | https://api-inference.modelscope.cn/v1 | Get Key → |
| Token Harbor | https://tokenharbor.ai/v1 | Get Key → |
| Cerebrium | https://api.cortex.cerebrium.ai/v4 | Get Key → |
| Ollama Cloud | https://ollama.com/v1 | Get Key → |
| SiliconFlow | https://api.siliconflow.com/v1 | Get Key → |
| Aion Labs | https://api.aionlabs.ai/v1 | Get Key → |
| Nscale | https://inference.api.nscale.com/v1 | Get Key → |
| Kilo AI Gateway | https://api.kilo.ai/api/gateway | Get Key → |
| Vercel AI Gateway | https://ai-gateway.vercel.sh/v1 | Get Key → |
| Api.Airforce | https://api.airforce/v1 | Get Key → |
| Routeway | https://api.routeway.ai/v1 | Get Key → |
| Onomeo | https://onomeo.com/v1 | Get Key → |
| Friendli AI | https://inference.friendli.ai/v1 | Get Key → |
| Grokified | https://api.grokified.com/v1 | Get Key → |
| LLM7.io | https://api.llm7.io/v1 | Get Key → |
Guides & Tutorials
Published at free-llm.com/guides:
- Best Free LLM APIs in 2026 — side-by-side comparison of top picks
- Gemini vs ChatGPT (Free Tier) — what you actually get for $0
- How to Use OpenRouter — setup walkthrough with code
- OpenRouter Alternatives — other aggregators worth trying
- Local LLMs with Ollama — get started in under 5 minutes
- Ultimate Free LLM API Guide — the comprehensive deep-dive
Community Features
Free-LLM is community-driven. The website at free-llm.com lets visitors:
- Vote on providers to surface the most useful ones
- Submit new providers and models
- Propose edits to existing provider data (admin-reviewed)
- Report models that have gone from free to paid
- Earn recognition on the Hall of Fame leaderboard
Data syncs back to this repository.
Code Examples
The code-examples/ directory has ready-to-run Python, JavaScript, and curl snippets — just add your API key.
By coding assistant: Claude Code · Cursor · Codex CLI · OpenCode
By provider (31): AI21 Labs · Aion Labs · Cerebras · Cerebrium · Cloudflare Workers AI · Cohere · Coze · Fireworks AI · Friendli AI · Google AI Studio · Groq · Hetzner Inference API · LLM7.io · Mistral (La Plateforme) · ModelScope · Nebius (Token Factory) · Nous Portal · Novita AI · Nscale · NVIDIA NIM · Ollama Cloud · OpenRouter · OVH AI Endpoints · Pollinations.ai · Qwen (Alibaba) · Replicate · Requesty · Scaleway Generative APIs · SiliconFlow · Upstage · Z.AI (GLM)
Local / Self-Hosted: BentoML · GPT4All · Jan.ai · KoboldCpp · llama.cpp · llamafile · LM Studio · Ollama · Text Gen WebUI
Repository Structure
Free-LLM/
├── README.md ← You are here (English)
├── README.zh-CN.md ← 简体中文
├── README.zh-TW.md ← 繁體中文
├── README.ja.md ← 日本語
├── README.ko.md ← 한국어
├── CONTRIBUTING.md ← Contribution guidelines
├── code-examples/ ← Ready-to-use snippets (per-provider + per-tool)
├── .github/ ← Issue/PR templates
└── LICENSE ← MIT
Contributing
See CONTRIBUTING.md for the full guide. Quick version:
- Add a provider — use the submit form on the website, or open an issue/PR here.
- Fix inaccurate data — rate limits change, providers graduate or shut down. PRs welcome.
- Add a config snippet — have a working config for a tool we don't cover? Add it to
code-examples/. - Vote & discuss — help the community surface the best options at free-llm.com.
Criteria for inclusion
A provider belongs in this list if:
- It explicitly offers a free tier (not just a trial credit with no free-forever option) — see Provider Directory for how we split permanent tiers from one-time credits
- The API is publicly accessible (no waitlist, closed beta, or reverse-engineering)
- For trial credits: clearly labeled and the free-forever alternative (if any) is called out
Links
- 🌐 Live site: free-llm.com — directory, voting, submissions
- 🆚 Compare providers: free-llm.com/compare
- 📚 Guides: free-llm.com/guides
- 🏆 Hall of Fame: free-llm.com/hall-of-fame
- ➕ Submit a provider: free-llm.com/submit
Star History
License
MIT — see LICENSE for details.
Data synced automatically from the live directory — last updated: 2026-10-15