21 providers · verified Nov 2026 · most need no credit card

Free LLM API Keys
& Free-Tier AI APIs

A curated directory of 21 providers giving away free, OpenAI-compatible access to Gemini, Llama, DeepSeek, Qwen, Mistral and GPT-4o. Create your own key — no shady shared keys, no surprise bills.

21
Providers
13
Free Tiers
19
No Card
$0
To Start
Browse free APIs ↓

All free LLM API providers

Search and filter 21 providers. Click any card for setup, limits and code.

Compare in a table →
Access:
Tag:

Showing 21 of 21 providers

Google AI Studio (Gemini) logo

Google AI Studio (Gemini)

aistudio.google.com

The most generous permanent free tier for a frontier model.

Free tier No card OpenAI-compatible
Free models
Gemini 2.5 FlashGemini 2.5 ProGemini 2.0 Flash
Groq logo

Groq

groq.com

The fastest free inference on the planet — 500+ tokens/sec.

Free tier No card OpenAI-compatible
Free models
Llama 3.3 70BDeepSeek R1 DistillQwen 3 32B
OpenRouter logo

OpenRouter

openrouter.ai

One key, 300+ models — dozens are completely free.

Free tier No card OpenAI-compatible
Free models
DeepSeek V3 (free)Llama 4 Maverick (free)Gemini 2.0 Flash (free)
Cerebras logo

Cerebras

cerebras.ai

Wafer-scale inference — frontier open models at record speed, free.

Free tier No card OpenAI-compatible
Free models
Llama 3.3 70BLlama 4 ScoutQwen 3 235B
GitHub Models logo

GitHub Models

github.com

Free access to GPT-4o, o-series and more — just a GitHub account.

Free tier No card OpenAI-compatible
Free models
GPT-4oGPT-4o minio3-mini
Mistral AI logo

Mistral AI

mistral.ai

European frontier models with a free “Experiment” tier.

Free tier No card OpenAI-compatible
Free models
Mistral Small 3.2CodestralPixtral
Cloudflare Workers AI logo

Cloudflare Workers AI

cloudflare.com

Serverless inference with a free daily allocation on the edge.

Free tier No card OpenAI-compatible
Free models
Llama 3.3 70BLlama 4 ScoutDeepSeek R1 Distill
SambaNova Cloud logo

SambaNova Cloud

sambanova.ai

High-speed inference for large open models, free to start.

Free tier No card OpenAI-compatible
Free models
Llama 3.3 70BDeepSeek R1Qwen 3 32B
NVIDIA NIM logo

NVIDIA NIM

nvidia.com

Free credits across a huge catalog of hosted open models.

Free credits No card OpenAI-compatible
Free models
Llama 3.3 70BDeepSeek R1Nemotron 70B
Together AI logo

Together AI

together.ai

Free signup credit plus a free Llama endpoint.

Free credits No card OpenAI-compatible
Free models
Llama 3.3 70B Turbo (free)DeepSeek R1Qwen 3
Alibaba Qwen (DashScope) logo

Alibaba Qwen (DashScope)

alibabacloud.com

First-party Qwen models with a free token quota.

Free tier No card OpenAI-compatible
Free models
Qwen 3 MaxQwen 3 CoderQwen 3 235B
Hugging Face logo

Hugging Face

huggingface.co

Monthly free inference credits across many providers.

Free credits No card OpenAI-compatible
Free models
Llama 3.3 70BDeepSeek V3Qwen 3
Hyperbolic logo

Hyperbolic

hyperbolic.xyz

Low-cost open-model inference with free starter credit.

Free credits No card OpenAI-compatible
Free models
Llama 3.3 70BDeepSeek V3Qwen 3
Zhipu AI (GLM) logo

Zhipu AI (GLM)

z.ai

Free GLM-4 Flash — a capable always-free chat model.

Free tier No card OpenAI-compatible
Free models
GLM-4-FlashGLM-4.6GLM-4V-Flash
Cohere logo

Cohere

cohere.com

Free trial keys for Command models, embeddings and rerank.

Free tier No card OpenAI-compatible
Free models
Command ACommand R+Embed v4
Fireworks AI logo

Fireworks AI

fireworks.ai

Fast open-model serving with free starter credit.

Free credits No card OpenAI-compatible
Free models
Llama 4 MaverickDeepSeek V3Qwen 3
DeepSeek logo

DeepSeek

deepseek.com

Frontier reasoning at rock-bottom prices (free starter credit).

Low cost No card OpenAI-compatible
Free models
DeepSeek V3.2DeepSeek R1
Pollinations AI logo

Pollinations AI

pollinations.ai

Text and image generation with no key and no signup.

No key needed No card OpenAI-compatible
Free models
OpenAI-compatible (text)FLUX (images)Various open models
xAI (Grok) logo

xAI (Grok)

x.ai

Grok models with recurring free API credits.

Free credits OpenAI-compatible
Free models
Grok 4Grok 4 FastGrok 3 Mini
Scaleway Generative APIs logo

Scaleway Generative APIs

scaleway.com

EU-hosted open models with a free beta allowance.

Free tier OpenAI-compatible
Free models
Llama 3.3 70BMistral SmallQwen 3
OVHcloud AI Endpoints logo

OVHcloud AI Endpoints

ovhcloud.com

European sovereign-cloud inference, free in beta.

Free tier No card OpenAI-compatible
Free models
Llama 3.3 70BMistralQwen 2.5

How free LLM APIs work

Nearly every provider in this directory is OpenAI-compatible. That means you keep your existing code and change only two things: the base_url and the API key you created on the provider’s own site. The same snippet below works for Gemini, Groq, Cerebras, OpenRouter and more — just swap the base URL.

Python · any provider
from openai import OpenAI

# Works with almost every provider in this directory —
# just change base_url + the free key you created.
client = OpenAI(
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
    api_key="YOUR_FREE_KEY"
)

resp = client.chat.completions.create(
    model="gemini-2.5-flash",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(resp.choices[0].message.content)

1. Pick a provider

Choose any card above. Free tiers (Gemini, Groq) reset daily; free credits (NVIDIA, Together) give a balance to spend.

2. Create your own key

Click through to the provider’s official key page and generate a key. It is yours — we never see or store it.

3. Swap the base URL

Point the OpenAI SDK at the provider’s base URL (listed on each provider page) and paste your key.

4. Call a model

Use any model the provider offers. Need more scale? Move to their cheap paid tier later with zero code changes.

Works with your favourite tools

Cursor IDE
Open WebUI
LobeChat
NextChat
Continue.dev
LangChain
LlamaIndex
AutoGen
CrewAI
Cline
Roo Code
Any OpenAI SDK

Frequently asked questions