LLM7.io

No sign-up: grab the base URL and start calling the model.

LLM7.io is an independent gateway: grab https://api.llm7.io/v1 and you can call it with the placeholder key “unused” — no account, no email. That is the point.

Anonymous traffic is 10 requests a minute on the turbo set: gpt-oss, Gemma 4 31B, MiniMax M2.7, Codestral and Mistral Nemo. A free token from token.llm7.io lifts it to 40 a minute and opens more ids. Fine for a first test.

Free models: 5
Max context: 1M
Free tier: 10 requests/minute (40 with a token)
Requirement: Nothing — no account

Endpoint

Base URLhttps://api.llm7.io/v1

Env varLLM7_API_KEY

Rate limit10 requests/minute anonymous, 40 requests/minute with a token

OpenAI-compatible
text
image
audio
video
pdf
code
vision
reasoning

Code examples

npm install openai

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.llm7.io/v1',
  apiKey: process.env.LLM7_API_KEY
})

const response = await client.chat.completions.create({
  model: 'gpt-oss',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.choices[0].message.content)

pip install openai

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.llm7.io/v1",
    api_key=os.environ["LLM7_API_KEY"],
)

response = client.chat.completions.create(
    model="gpt-oss",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response.choices[0].message.content)

curl https://api.llm7.io/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LLM7_API_KEY" \
  -d '{
    "model": "gpt-oss",
    "messages": [{"role": "user", "content": "Explain closures in one paragraph."}]
  }'

Worth knowing

Works with the placeholder key "unused" if you never grab a token.
Anonymous traffic is the turbo set only: codestral-latest, gemma4:31b, gpt-oss (GPT-OSS 120B), minimax-m2.7, mistral-Nemo-Instruct-2407.

Models you get for free5

GPT-OSS 120Bgpt-oss
Gemma 4 31Bgemma4:31b
MiniMax M2.7minimax-m2.7
Codestralcodestral-latest
Mistral Nemomistral-Nemo-Instruct-2407