Free LLM APIs

English · 简体中文

Permanent free tiers, no-card options, direct API key links, models, and verified limits — every claim points to an official source.

15 permanent provider free tiers · 15 require no credit card · 15 are OpenAI compatible · sources reviewed 2026-07-25. No keys are distributed here. A probe describes one sampled request, not provider-wide uptime.

Browse the live directory · Pick by model · Set up a coding agent · Check your own key

Star this repository to bookmark the dataset and follow releases. A star changes nothing about any provider's keys, credits, or limits, and this project gives nothing in return for one.

Pick a free API by goal

These are rule-based shortcuts, not paid placements. Open the filterable directory for all 26 providers.

Permanent free tiers

These Provider Free Tiers are the main list: they do not expire like trial credits, and none currently require a credit card.

Other access options

These entries can still be useful, but they are aggregators, trial credits, retiring tiers, or metered services — not permanent Provider Free Tiers.

Limits marked dynamic or model-dependent are intentionally not replaced with guessed numbers. Follow the linked official source for the current quota.

Quick start

After creating your own Groq API key, the OpenAI SDK needs only a different Base URL and model id:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["GROQ_API_KEY"],
    base_url="https://api.groq.com/openai/v1",
)

response = client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[{"role": "user", "content": "Say hello in one sentence."}],
)
print(response.choices[0].message.content)

For coding agents, generate a client-specific configuration that reads the key from your environment:

npx free-llm-api setup claude-code

Client guides: Claude Code · Codex CLI · Cline · all clients.

Check a key you already have

Open the browser key checker. Nothing is installed or stored: the request goes from your browser straight to the chosen provider. Its Content Security Policy allows the 26 catalog origins and no analytics or project server. 21 providers answer cross-origin browser requests; blocked providers get an equivalent curl command.

Why trust this list

• Every limit and lifecycle claim links to an official source and carries a review date.
• Trial credit, metered access, aggregators, and retiring tiers are separated from permanent free tiers.
• No working API keys are stored or distributed. Use environment variables for your own credentials.
• A probe describes one sampled request, not provider-wide uptime. A 429 does not reveal the key's remaining quota.

Run probes explicitly outside CI. Keys are read only from the provider environment variable:

GROQ_API_KEY=YOUR_API_KEY npm run probe -- --provider groq

The ignored data/probe-output.json contains only a bounded classification, status, latency, and timestamp — never the key, response body, or raw exception. Read the full methodology.

Changed this week

Week of 2026-07-25. First published catalog: 26 providers, every published number traced to an official page checked this week.

• Added (26): Google Gemini API, GroqCloud, SambaNova Cloud, Cohere, Cloudflare Workers AI, Hugging Face Inference Providers, SiliconFlow, Fireworks AI, Z.AI Open Platform, Novita AI, Mistral La Plateforme, Alibaba Cloud Model Studio, Moonshot AI (Kimi), Pollinations.AI, Ollama Cloud, Cerebras Inference, Vercel AI Gateway, IBM watsonx.ai, OpenRouter, GitHub Models, Together AI, Nebius Token Factory, Perplexity API, DeepInfra, Chutes, Scaleway Generative APIs
• Lifecycle — GitHub Models: Free tier retires 2026-07-30, so the catalog carries no signup link for it.
• Corrected — Cerebras Inference: A verified payment method is a precondition for API access, so this is not a card-free free tier.
• Corrected — Fireworks AI: The 10 RPM cap for accounts without a payment method applies account-wide, not per model.

Every entry above is dated and sourced in the catalog below. Full history: data/changelog.json.

Contributing

Corrections are the contribution this project runs on: a limit that moved, a provider that closed signups, or a link that died. See CONTRIBUTING.md and the issue templates.

Data and local development

• data/providers.json is the reviewed source dataset.
• data/changelog.json records weekly changes.
• README.md, docs/providers.json, and the static pages are generated deterministically.
• npm run validate rejects stated quotas without an official source.

Run the generated site locally:

npm run render && npm run serve

Open http://127.0.0.1:4173. Node.js 20+ is required; there are no runtime dependencies and no API keys are needed.

Security

This repository contains no working credentials. Keep probe keys in environment variables and redact Authorization headers from reports. See SECURITY.md.

Star history

Related projects

• Free Tier LLM Router combines your own provider keys behind one local endpoint with controlled failover.
• AI Coding Field Notes is a write-up collection on what coding agents actually cost, where they break, and what shipped.

Need one stable endpoint?

If rotating free-tier keys and handling different limits becomes the work, create a PekPik API account for one OpenAI-compatible hosted endpoint. The free directory above remains usable without it.