How to Get a Requesty API Key for Free

In short: Requesty's Free plan is $0 with no credit card: one API key reaches its free models, up to 200 requests a day. Sign up at app.requesty.ai, open API Keys and create a key. Free models show Free/M as their price in the Model Library; Gemma 4 31B, NVIDIA Nemotron 3 Ultra and Mistral's Leanstral answered on a free key. The base URL https://router.requesty.ai/v1 works in apps made for OpenAI.

What you need

• A Requesty account at app.requesty.ai. New accounts start on the Free plan with a $0.00 balance.
• A computer. Windows, Mac or Linux all work.
• Nothing to pay. Requesty's pricing page lists the Free plan at $0 with "No credit card required".

Step 1: Find the free models

Click Model Library in the left menu and search for a model. A free model shows Free/M for input and output (box 2). In the example, gemma-4-31b-it is free (box 1), while gemma-4-31b from another provider is paid.

Free models on 27 October 2026, by model name:

Two models priced free that day, poolside/laguna-m.1 and nvidia/nemotron-3-super-120b-a12b, answered with a 404 from their provider.

Step 2: Create a key

Open API Keys and click Create key (box 1). Give it a name, then copy the key when it appears. The new key is listed with its usage, which stays at $0.00 on free models (box 2).

Keep the key private:

• Anyone who has your key can use your daily free requests.
• Never paste it into a website, a public code repository or a screenshot.
• If it leaks, delete it from the ... menu next to it and create a new one.

Step 3: Know your free limits

Paid models need the pay-as-you-go plan: the provider's price plus 5%.

Step 4: Send your first request (no programming)

Open a command window. On Windows, press the Start key, type PowerShell and open it. On a Mac, open Terminal. Put your key in place of YOUR_API_KEY.

Windows (PowerShell):

$env:REQUESTY_API_KEY = "YOUR_API_KEY"
$body = '{"model":"google/gemma-4-31b-it","messages":[{"role":"user","content":"Explain how AI works in a few words"}]}'
$r = Invoke-RestMethod -Method Post -Uri "https://router.requesty.ai/v1/chat/completions" -Headers @{ Authorization = "Bearer $env:REQUESTY_API_KEY" } -ContentType "application/json" -Body $body
$r.choices[0].message.content

Mac or Linux (Terminal):

export REQUESTY_API_KEY="YOUR_API_KEY"
curl https://router.requesty.ai/v1/chat/completions \
  -H "Authorization: Bearer $REQUESTY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-31b-it",
    "messages": [{"role": "user", "content": "Explain how AI works in a few words"}]
  }'

Step 5: Use it in an app made for OpenAI

OpenAI's Python library works the same way, with base_url="https://router.requesty.ai/v1".

When something goes wrong

Words to know

• API key: the password an app uses to call a model. See what is an API key.
• Free/M: Requesty's label for a model with no charge per million tokens.
• Router: a service that sends each request to a model provider through one key.
• Third-party API key: a key from a service that runs models made by other companies.

More free AI API keys

How to get AI API keys for free lists every free tier with its limit and source.