450+ free LLM models from 86 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
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 every active provider 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
- Pick a provider — see the Provider Directory below. New to this? Start with Groq (no credit card, ~30 RPM / 1,000 requests per day per model, 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).
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 usePoint your AI coding tool at a free backend instead of a paid one:
- Claude Code — speaks the Anthropic API, so use a provider with a native Anthropic endpoint (OpenRouter, Z.AI, FreeInference, Ollama) or a LiteLLM proxy. See
code-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.
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 | 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 3.x on Dec 1, 2026); Gemini 3.x Pro and Gemini 4 are paid | Free of charge | Gemini 3.8 Flash, Gemma 4 26B A4B IT, Gemma 4 31B IT, Gemini 3 Flash Preview |
| Mistral (La Plateforme) | Phone verification | 1 request/second | - | Free | Mistral Small, Mistral Large 4 (Preview), Codestral 2508, Ministral 3 8B |
| Cohere | No | 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 verification | ~40 RPM (varies per model, not published) | - | - | GLM-5.3 Flash, DiffusionGemma 26B A4B, Riva Translate 4B v2, Cosmos Reason 2 8B |
| 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 | GPT-OSS 120B, Qwen3.8 27B, 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 |
| Cloudflare Workers AI | No | Varies by model | 10,000 neurons/day | ~300,000 neurons/month | GLM-5.3 Flash, FLUX.2 Dev (image), Whisper Large v3 Turbo, EuroLLM 9B |
| OVH AI Endpoints | Registration | 2 RPM per IP per model (anonymous, free); 400 RPM with a key (pay-as-you-go) | Unspecified | Beta Access | GPT OSS 120B, BGE-M3 (embeddings), Whisper Large v3 Turbo, Qwen2.5 VL 72B Instruct |
| Kilo AI Gateway | No | 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 charge) is required to get a key - verify | StepFun Step 3.7 Flash, Reflection Beam 1.0, Upstage Solar Mini 4, Crouton Alpha (stealth, free) |
| 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 details is required and Hetzner may ask for a card or ID to verify it | Free during experimental phase, no billing system yet | Qwen3.8 27B, Qwen3.6 35B A3B |
| ModelScope | Phone verification | 500 requests/day per model | 2,000 requests/day total | Free, no billing | Qwen3.8 27B, Nex N2.5 Pro, LongCat Flash Lite, ERNIE 4.5 300B A47B |
| Ollama Cloud | No | Pay-as-you-go: 3 concurrent requests; only Beam (beam:cloud) is labelled free | No free monthly allowance any more (starter credits removed); other cloud models are billed per token | Weekly usage limit resets every 7 days | Reflection Beam (501B) |
| 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-Z1 9B, Qwen2.5 7B Instruct, Xing4.0 29B A4B, GLM-4 9B 0414 |
| Aion Labs | No | Not published (daily credit allowance) | Daily free credit allowance (amount not published by Aion Labs) | Free, no billing | Aion 2.0, Aion 3.0 Mini, Aion 3.5 Mini |
| Api.Airforce | No | 1 RPM | 1,000 requests/day | Free plan, $0/month | GPT-OSS 20B, GLM-4.7 Flash, Essential AI RNJ 1, Kimi K2.7 Code |
| Routeway | Registration | 5 RPM on :free models | 200 requests/day | Starter plan free, shared queue | DeepSeek V4.1 Flash (free), MiniMax M3.1 Flash (free), Muse Glimmer 30B |
| FreeInference | No | Not published ("generous quota"; HTTP 429 when rate-limited) | No published daily cap | — | GLM-5.3 Flash, DeepSeek V4 Flash, MiniMax M3, Qwen3.6 35B A3B |
| OpenTyphoon (Typhoon API) | No | 5 requests/second, 200 RPM (text models); 20 RPM for OCR | No daily cap published | — | Typhoon 2.5 30B A3B Instruct, Typhoon OCR 1.5 |
| SEA-LION API | Registration | 10 requests/minute per user (increase on request: [email protected]) | Not published | — | Qwen SEA-LION v4.5 27B Instruct, Llama SEA-LION v3.5 70B Reasoning, SEA-Guard (safety), SEA-LION Embedding 600M |
| LLM.kiwi | Registration | Baseline rate limits (figures not published) | Not published | — | Auto router, MiniMax M3, Nemotron 3 Ultra, Nemotron 3 Super |
| Agnes AI | Registration | About 30 RPM per account (video 2 RPM), per third-party listings | Not published | — | Agnes 3.0 Flash, Agnes 2.5 Flash, Agnes Image 2.1 Flash (image) |
| AI Horde (OpenAI-compatible front) | No | Queue-based; anonymous requests have the lowest priority, registered users earn kudos for priority | No fixed cap (volunteer capacity) | — | Gemma 4 E4B IT, Qwen3 4B, Llama 3.2 1B Instruct, L3 8B Stheno v3.2 |
| Arli AI | Registration | 1 request at a time; max 12K context tokens | Limited trial uses per model (about 5 requests per 2 days, per third-party list) | — | Qwen3.5 27B Derestricted |
| iFlytek Spark Lite | Phone verification | Not published on the HTTP doc | Not published (Lite is free) | — | Spark Lite |
| Zhipu BigModel (China) | Phone verification | Low concurrency on free Flash models (GLM-4.7-Flash reported at 1 concurrent request) | Not published | — | GLM-4.7-Flash, GLM-4.5-Flash, GLM-4-Flash-250414, GLM-4.6V-Flash (vision) |
| Mixlayer | Registration | Per-organization, per-model RPM/TPM (values shown in console only) | Not published | — | Qwen3.5 4B (free) |
| SenseNova (SenseTime) | Phone verification | Not published | Not published ("限时放量" during public beta) | — | SenseNova 6.8 Flash Lite |
| 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 |
| 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 |
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) | Gemma 4 31B IT, NVIDIA Nemotron 3 Ultra, Recursive Flint v1.0 (free), Nemotron 3.5 Super VL |
| Requesty | No | 20 RPM on free models (60 RPM for paying orgs) | 200 requests/day (new orgs) / 1,000/day (paying orgs), shared across free models | Gemma 4 31B IT, Ling 3.0 Tiny, Nemotron 3 Nano Omni Reasoning, Nemotron 3 Nano 30B A3B |
| Vercel AI Gateway | Registration | Lower per-model limits than the paid tier (429 on excess) | $5/month | Nemotron 3.5 Lightning (free), Llama 3.3 70B, MiniMax M3.1 Flash, GLM-4.7 Flash |
| Token Harbor | Registration | 60 requests/min and 1,800/hour per account (100/min, 3,000/hour per IP) | Free allowance, resets on a rolling 7-day period | DeepSeek V4.1 Flash, MiMo V2.6 Flash, TH-Rudder |
| BazaarLink | Registration | 10 RPM (20 RPM with any credit), 2 concurrent requests | 60 weighted units/day (120 with credit), resets 00:00 UTC | Qwen3.7 Flash, Reflection Beam (free), Nemotron 3.5 Lightning (free), DeepSeek V4 Flash 0731 (free) |
| AnyAPI | No | Limited API calls on the Free plan (exact RPM not published) | 100K ANY tokens per day, free models only | See provider |
| Zro (MoonMath) | Registration | Daily usage allowance (amount not published) | Resets every day (Flash models only) | GLM-5.3 Flash, DeepSeek V4.1 Flash |
| Inferbase | No | 100 managed requests per day | $0.50 of managed model usage per day; 5,000 requests per month | GPT-OSS 120B, DeepSeek V4 Flash, Qwen3.6 27B, Gemma 4 31B IT |
| Gonka Broker | Phone verification | Network limits (see docs.gonkabroker.com Limits & Quotas) | Monthly free token grant after SMS verification (does not accumulate) | GLM-5.3 Flash, DeepSeek V4 Flash 0731, MiniMax M2.7 |
| AIHubMix (free models) | Registration | 5 RPM per account on most *-free routes | 100 requests/day and 1M tokens/day per account (500 RPD on some, e.g. glm-4.7-flash-free, coding-minimax-m3-free) | Coding GLM 5.3 (free), Coding GLM 5.3 Flash (free), Coding Kimi K3 (free), Coding MiniMax M3 (free) |
| IBM watsonx.ai (Lite plan) | Card required | About 2 requests/second (Lite) | 300,000 tokens/month + 20 CUH/month | Granite 4 H Small, Llama 3.3 70B Instruct, Llama 4 Maverick, GPT-OSS 120B |
| Bytez | Registration | 1 concurrent request (open models); 10 requests/second (closed models) | $1 free credits, refreshed every 4 weeks | See provider |
| Moark (Gitee AI) | Phone verification | Not published | 100 free calls/day per user (free experience access token) | DeepSeek V4 Flash 0731, GLM 5.3 Flash, Qwen3.8 27B |
| MegaNova AI | No | Tier 1 (free): 20-200 RPM | Tier 1: 50-500 free-model requests/day (varies by model) | Manta Pro 1.0, Manta Flash 1.0, Manta Mini 1.0, Mistral Small 3.2 24B |
| SimpleLLM | Registration | Account-specific (read via GET /v1/rate-limit) | Free-model hourly/daily request and token allowances (values per account, not published) | Llama 3.1 8B Free, Gemma E4B Free, Mistral 7B (tier free, $0), Kode 14B (tier free, $0) |
| Experiential Labs | Card required | 10 RPM and 250K TPM per free core model | 1M input+output tokens/day shared across free core models, reset 00:00 UTC | GPT-6 Luna, DeepSeek V4.1 Flash 1017, Clef Flash (decision endpoint, free promo) |
| Sail Research | Card required | Not published for Free plan (most relaxed on flex window) | $5 free credits every month (payment method attached) | Kimi K3, GLM 5.3, GLM 5.3 Flash, DeepSeek V4.1 Flash 1017 |
| LLMTR | Registration | Not published; lower allowance in an account's first 24h | Per-model daily allowance (e.g. 200K tokens/day on dated previews) | Nemotron 3 Ultra 550B, Nemotron 3.5 Super VL (free), Qwen3.8 27B (free), Agnes 3.0 Flash |
| Kiosapi.id | Registration | 5 requests/minute (free models) | 50 requests/day per account shared across free models, reset 07:00 WIB | GLM 4.7 Flash, Qwen3 30B, Gemma 4 26B, Llama 3.1 8B |
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 | Free starter credit for new accounts (amount no longer stated by Fireworks; historically $1) | One-time | Nemotron 3.5 Lightning 30B A3B, MiniMax M3, GPT-OSS 120B, GLM 5.3 Flash |
| Hyperbolic | Phone verification | $1 after phone verification (Free Tier) | One-time | DeepSeek V4 Flash 0731, Qwen3.8 27B, MiMo V2.6 Flash, GLM-5.3 Flash |
| Cerebras | Card required | $5 after adding a verified payment method (expires after 30 days) | 30 days | GPT OSS 120B, Qwen 3.8 27B |
| 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 (+60 min audio transcription), all serverless models | One-time | GPT-OSS 120B, Whisper Large v3, Voxtral Small 24B, Holo2 30B A3B |
| Qwen (Alibaba) | Registration | ~1M tokens per model, 90 days (Singapore; newer models only since Oct 29, 2026) | One-time per model | Qwen3.8 Flash, Qwen3.7 Plus, Qwen3.8 Max, Qwen3.7 Max |
| Upstage | Registration | $10 sign-up credit (announced by Upstage; not shown on the pricing page, verify) | 3 months | See provider |
| Cerebrium | Registration | No sign-up credit shown on the pricing page (Hobby plan: free platform, compute billed per second) | One-time | See provider |
| Friendli AI | Registration | Trial credits at onboarding (amount not published) | One-time | GLM-5.1, Gemma 4 31B, GLM 5.2, GLM 5.3 Flash |
| Grokified | No | $5 | One-time | Grok 4.7, grok-4.6, grok-4.3, grok-build-0.1 |
| IteraCompute | Registration | 30M tokens/month on Qwen3.8-27B (promotion, no card) | Until Nov 24, 2026 00:00 PT | Qwen3.8 27B |
| Dahl Inference | Registration | — | — | GLM-5.3 Flash, MiniMax M2.7, DeepSeek V4 Flash 0731 |
| Regolo.ai | No | 30-day trial, 1M tokens/day, no card | 30 days | GPT-OSS 120B, Qwen3.8 27B, Gemma 4 31B, GLM-5.2 |
| GonkaRouter | No | 1M free tokens for new users | One-time | GLM-5.3 Flash, DeepSeek V4 Flash, MiniMax M2.7 |
| NovAI | No | $2 welcome credit, no card | One-time | GLM-4.7 Flash, GLM-4.6V Flash, GLM-4.1V Thinking Flash |
| Vectoree | No | $5 welcome credit after CLI login | One-time | Vectoree Auto (router) |
| Sarvam AI | Phone verification | INR 100 free credits on signup | One-time; credits do not expire (per third-party list) | Sarvam 105B, Sarvam 105B Conversations |
| HPC-AI Model APIs | Registration | $2 free voucher on signup ($4 with an invite code, per third-party list) | One-time | Kimi K2.7 Code |
| VLM Run Gateway | No | 100 free credits on sign-up (~$1, at $0.01/credit) | One-time, then pay-as-you-go | Qwen3.8 27B, Gemma 4 26B A4B IT, Qwen3.5 0.8B, DiffusionGemma 26B A4B |
| Tencent Cloud TokenHub | Card required | 1M free tokens per language model, once per account per model | 90 days after claim (intl promo page; docs say 1 year); campaign ends 2026-12-31" - DeepSeek-V4-Pro | See provider |
| Google Vertex AI express mode (Gemini Enterprise Agent Platform) | Registration | Free-tier quota access, no billing account | Up to 90 days for new Google Cloud users | Gemini 3.1 Pro Preview, Gemini 3 Flash Preview, Gemini 2.5 Pro, Gemini 2.5 Flash |
| Jina AI (Embeddings / Reader API) | No | Free tokens on an auto-generated key (amount not stated on page) | Keys do not expire | Jina Embeddings v5 Text Small, Jina Embeddings v5 Text Nano, Jina Embeddings v5 Omni Small, Jina Embeddings v3 |
| Voyage AI (embeddings & rerankers) | Registration | First 200M tokens free per model (voyage-4 family, rerank-2.5); 50M on domain models | One-time per account per model | Voyage 4 Large, Voyage 4, Voyage 4 Lite, Voyage Code 3 |
| Inception Labs | No | 100M tokens | One-time (new accounts) | Mercury 3, Mercury 2.5, Mercury 2 |
| 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 (no release since Feb 2025) |
| 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 |
| 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 → |
| Hyperbolic | https://api.hyperbolic.ai/inference/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 → |
| Upstage | https://api.upstage.ai/v1/solar |
Get Key → |
| Z.AI (GLM) | https://api.z.ai/api/paas/v4 |
Get Key → |
| Cloudflare Workers AI | https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/ |
Get Key → |
| OVH AI Endpoints | https://oai.endpoints.kepler.ai.cloud.ovh.net/v1 |
Get Key → |
| Kilo AI Gateway | https://ai-gateway.kilo.ai/api/v1 |
Get Key → |
| Nous Portal | https://inference-api.nousresearch.com/v1 |
Get Key → |
| Hetzner Inference API | https://inference.hetzner.com/api/v1 |
Get Key → |
| ModelScope | https://api-inference.modelscope.cn/v1 |
Get Key → |
| Cerebrium | https://api.cortex.cerebrium.ai/v4 |
Get Key → |
| Friendli AI | https://inference.friendli.ai/v1 |
Get Key → |
| Ollama Cloud | https://ollama.com/v1 |
Get Key → |
| Requesty | https://router.requesty.ai/v1 |
Get Key → |
| SiliconFlow | https://api.siliconflow.cn/v1 |
Get Key → |
| Aion Labs | https://api.aionlabs.ai/v1 |
Get Key → |
| Grokified | https://api.grokified.com/v1 |
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 → |
| Token Harbor | https://tokenharbor.ai/v1 |
Get Key → |
| IteraCompute | https://api.iteracompute.com/v1 |
Get Key → |
| BazaarLink | https://api.bazaarlink.ai/v1 |
Get Key → |
| Dahl Inference | https://inference.dahl.global/v1 |
Get Key → |
| FreeInference | https://freeinference.org/v1 |
Get Key → |
| AnyAPI | https://api.anyapi.ai/v1 |
Get Key → |
| Zro (MoonMath) | https://zro.moonmath.ai/v1 |
Get Key → |
| Inferbase | https://api.inferbase.ai/v1 |
Get Key → |
| OpenTyphoon (Typhoon API) | https://api.opentyphoon.ai/v1 |
Get Key → |
| Gonka Broker | https://proxy.gonkabroker.com/v1 |
Get Key → |
| Regolo.ai | https://api.regolo.ai/v1 |
Get Key → |
| GonkaRouter | https://api.gonkarouter.io/v1 |
Get Key → |
| NovAI | https://aiapi-pro.com/v1 |
Get Key → |
| Vectoree | https://vectoree.ai/api/v1 |
Get Key → |
| SEA-LION API | https://api.sea-lion.ai/v1 |
Get Key → |
| AIHubMix (free models) | https://aihubmix.com/v1 |
Get Key → |
| LLM.kiwi | https://api.llm.kiwi/v1 |
Get Key → |
| Agnes AI | https://apihub.agnes-ai.com/v1 |
Get Key → |
| AI Horde (OpenAI-compatible front) | https://oai.aihorde.net/v1 |
Get Key → |
| Arli AI | https://api.arliai.com/v1 |
Get Key → |
| Sarvam AI | https://api.sarvam.ai/v1 |
Get Key → |
| HPC-AI Model APIs | https://api.hpc-ai.com/inference/v1 |
Get Key → |
| VLM Run Gateway | https://gateway.vlm.run/v1/openai |
Get Key → |
| Tencent Cloud TokenHub | https://tokenhub-intl.tencentmaas.com/v1 |
Get Key → |
| iFlytek Spark Lite | https://spark-api-open.xf-yun.com/v1 |
Get Key → |
| Zhipu BigModel (China) | https://open.bigmodel.cn/api/paas/v4 |
Get Key → |
| IBM watsonx.ai (Lite plan) | https://us-south.ml.cloud.ibm.com/ml/v1/text/chat?version=2025-02-11 |
Get Key → |
| Bytez | https://api.bytez.com/models/v2/openai/v1 |
Get Key → |
| Mixlayer | https://models.mixlayer.ai/v1 |
Get Key → |
| Moark (Gitee AI) | https://api.moark.com/v1 |
Get Key → |
| MegaNova AI | https://api.meganova.ai/v1 |
Get Key → |
| SimpleLLM | https://api.simplellm.eu/v1 |
Get Key → |
| Experiential Labs | https://api.experientiallabs.ai/v1 |
Get Key → |
| Sail Research | https://api.sailresearch.com/v1 |
Get Key → |
| Google Vertex AI express mode (Gemini Enterprise Agent Platform) | https://aiplatform.googleapis.com/v1/publishers/google/models/MODEL_ID:generateContent |
Get Key → |
| Jina AI (Embeddings / Reader API) | https://api.jina.ai/v1/embeddings |
Get Key → |
| Voyage AI (embeddings & rerankers) | https://api.voyageai.com/v1/embeddings |
Get Key → |
| SenseNova (SenseTime) | https://token.sensenova.cn/v1 |
Get Key → |
| LLMTR | https://llmtr.com/v1 |
Get Key → |
| Kiosapi.id | https://api.kiosapi.id/v1 |
Get Key → |
| Pollinations.ai | https://gen.pollinations.ai/v1 |
Get Key → |
| Inception Labs | https://api.inceptionlabs.ai/v1 |
Get Key → |
| LLM7.io | https://api.llm7.io/v1 |
Get Key → |
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
- Best Free LLMs for Coding — free coding models + Claude Code, Codex & Cursor setup
- Free OpenRouter Alternatives — gateways and APIs with bigger free tiers
- Free LLM Fallback System — chain providers so you never hit a rate limit
- Monthly report: November 2026 — new free providers, shutdowns, model changes
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.
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 (74): Agnes AI · AI Horde (OpenAI-compatible front) · AIHubMix (free models) · Aion Labs · AnyAPI · Api.Airforce · Arli AI · BazaarLink · Bytez · Cerebras · Cerebrium · Cloudflare Workers AI · Cohere · Dahl Inference · Experiential Labs · Fireworks AI · FreeInference · Friendli AI · Gonka Broker · GonkaRouter · Google AI Studio · Google Vertex AI express mode (Gemini Enterprise Agent Platform) · Grokified · Groq · Hetzner Inference API · HPC-AI Model APIs · Hyperbolic · IBM watsonx.ai (Lite plan) · iFlytek Spark Lite · Inception Labs · Inferbase · IteraCompute · Jina AI (Embeddings / Reader API) · Kilo AI Gateway · Kiosapi.id · LLM.kiwi · LLM7.io · LLMTR · MegaNova AI · Mistral (La Plateforme) · Mixlayer · Moark (Gitee AI) · ModelScope · Nous Portal · NovAI · Novita AI · NVIDIA NIM · Ollama Cloud · OpenRouter · OpenTyphoon (Typhoon API) · OVH AI Endpoints · Pollinations.ai · Qwen (Alibaba) · Regolo.ai · Replicate · Requesty · Routeway · Sail Research · Sarvam AI · Scaleway Generative APIs · SEA-LION API · SenseNova (SenseTime) · SiliconFlow · SimpleLLM · Tencent Cloud TokenHub · Token Harbor · Upstage · Vectoree · Vercel AI Gateway · VLM Run Gateway · Voyage AI (embeddings & rerankers) · Z.AI (GLM) · Zhipu BigModel (China) · Zro (MoonMath)
Local / Self-Hosted: BentoML · GPT4All · Jan.ai · KoboldCpp · llama.cpp · llamafile · LM Studio · Ollama · Text Gen WebUI
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
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. Open an issue with a link to the official source (the tables below are regenerated daily from the live database, so table edits in PRs get overwritten).
- 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.
A provider belongs in this list if:
- It offers a free tier, a renewable free allowance, or a clearly labelled trial credit — 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)
- It is the provider's own service: no resold, pooled or shared keys for other companies' models ("free Claude/GPT" key pools are rejected)
- Every row is checked against the provider's official pricing page, docs or public
/v1/modelslist before it goes live
- 🌐 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
- 🧩 JSON catalog: free-llm.com/catalog.json
- ➕ Submit a provider: free-llm.com/submit
MIT — see LICENSE for details.
Data synced automatically from the live directory — last updated: 2026-11-11