Requesty

LLM gateway with 12 models at $0. 200 requests a day, no card, OpenAI-compatible.

Requesty is an OpenAI-compatible gateway: one key from app.requesty.ai/api-keys, base URL router.requesty.ai/v1. The free slice is 12 models priced $0 — Nemotron 3 Ultra, Super, Nano and Lightning, Laguna XS and M, Gemma 4 31B, Leanstral 1.5, Muse Glimmer and Ling 3.0 Tiny. Super, Ultra and Lightning go to 1M of context.

New organisations get 200 requests a day and 20 a minute, shared across every free model, reset daily, no card. Paying organisations jump to 1,000 a day. The rest of the 600+ catalogue is pay-as-you-go plus 5%. EU traffic can use router.eu.requesty.ai/v1.

Free models: 12
Max context: 1M
Free tier: 200 requests per day
Requirement: Email account, no card

Endpoint

Base URLhttps://router.requesty.ai/v1

Env varREQUESTY_API_KEY

Rate limit20 requests/minute, 200 requests/day

OpenAI-compatible
text
image
vision
reasoning

Code examples

npm install openai

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://router.requesty.ai/v1',
  apiKey: process.env.REQUESTY_API_KEY
})

const response = await client.chat.completions.create({
  model: 'nvidia/nemotron-3-super-120b-a12b',
  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://router.requesty.ai/v1",
    api_key=os.environ["REQUESTY_API_KEY"],
)

response = client.chat.completions.create(
    model="nvidia/nemotron-3-super-120b-a12b",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

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

curl https://router.requesty.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $REQUESTY_API_KEY" \
  -d '{
    "model": "nvidia/nemotron-3-super-120b-a12b",
    "messages": [{"role": "user", "content": "Explain closures in one paragraph."}]
  }'

Worth knowing

Only the $0 ids are free. The rest of the 600+ catalogue is pay-as-you-go plus 5%.
The 200 requests/day and 20/minute caps are shared across every free model. Paying orgs get 1,000/day and 60/minute.
The docs table lists 9 free ids; live /v1/models has 12 at $0. Laguna here is 33K, not the 256K NIM window. nemotron-3.5-content-safety is a classifier.

Models you get for free12

Laguna M.1poolside/laguna-m.1
Laguna XS.2poolside/laguna-xs.2
Ling 3.0 Tinynovita/inclusionai/ling-3.0-tiny
Gemma 4 31Bgoogle/gemma-4-31b-it
Leanstral 1.5mistral/leanstral-1-5
Nemotron 3 Super 120B A12Bnvidia/nemotron-3-super-120b-a12b
Nemotron 3 Nano Omni 30B A3B Reasoningnvidia/nemotron-3-nano-omni-30b-a3b-reasoning
Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b
Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safety
Nemotron 3 Ultra 550B A55Bnvidia/nemotron-3-ultra-550b-a55b
Muse Glimmer 30Bnvidia/muse-glimmer-30b
Nemotron 3.5 Lightning 30B A3Bnvidia/nemotron-3.5-lightning-30b-a3b