Access GPT-4, Claude, Gemini, DeepSeek & 90+ AI models — completely free. OpenAI-compatible API. Keys refresh every 24–48 hours with fresh budget.
Fetching latest keys…
FreeLLMKeys provides free API keys for the world's top large language models (LLMs), updated multiple times daily. Every key is OpenAI-compatible — meaning you only need to change the base URL in your existing code or application.
Keys carry a $20–$100 budget each, expire in 24–48 hours, and support 3–20 requests per minute depending on the model. Ideal for personal projects, rapid prototyping, research, and development testing without spending a single cent.
Use GPT-4o, GPT-4 Turbo, o1, o3, o4-mini & more. Drop-in replacement for the official OpenAI API. Works with Cursor, VS Code Copilot alternatives, and any SDK.
Access Claude Opus 4, Claude Sonnet 4, and the latest Anthropic models through the same unified endpoint. No API account needed.
Gemini 2.5 Flash, Gemini 3.1, and Google's newest models available instantly. Best for fast, cost-efficient inference tasks.
DeepSeek V3, DeepSeek R1, and DeepSeek Coder — top-ranked open-weight models, free via this endpoint. Great for coding tasks.
xAI's Grok-4, Mistral Medium, Qwen, Llama 4, and 80+ additional models all accessible from a single base URL with one unified key format.
This page updates in real time. The keys you see are always the latest batch — no stale data, no manual refresh needed.
https://aiapiv2.pekpik.com/v1 in your app, SDK, or tool. It's OpenAI-compatible, so existing code works without changes — just swap the base URL and key.These keys are fully OpenAI-compatible — just change the base_url in your existing code. No other changes needed.
from openai import OpenAI client = OpenAI( base_url="https://aiapiv2.pekpik.com/v1", api_key="sk-your-key-here" ) response = client.chat.completions.create( model="gpt-4o", messages=[{"role": "user", "content": "Hello!"}] ) print(response.choices[0].message.content)
import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://aiapiv2.pekpik.com/v1", apiKey: "sk-your-key-here" }); const response = await client.chat.completions.create({ model: "gpt-4o", messages: [{ role: "user", content: "Hello!" }] }); console.log(response.choices[0].message.content);
curl https://aiapiv2.pekpik.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-your-key-here" \ -d '{ "model": "gpt-4o", "messages": [{"role":"user","content":"Hello!"}] }'
Compatible tools & apps: