Quickstart: Your First i14 API Call in Five Minutes

The i14 API is OpenAI-compatible, so if you have ever called /v1/chat/completions before, everything here will feel familiar. This guide walks you from zero to your first successful response in under five minutes.

Tip

The i14 API follows the OpenAI request and response schema. Any SDK or tool that already targets the OpenAI API works with i14 - just point base_url at https://api.i14.ai/v1 and swap in your i14 key.

The shell examples in these docs are for macOS and Linux (bash or zsh). On Windows, run them in WSL or Git Bash, or use the PowerShell versions on this page.

1. Create your account

   Log in or create an account on the i14 Platform with your email address or Google account.

2. Get your API key

   Open API Keys. If you have a referral code, click Redeem a code and enter it. Then click Create key and copy the key. The dashboard shows the full key only once.

   No referral code? Join the waitlist. See Get your API key.

   Caution

   Treat your API key like a password. Never paste it into source code or commit it to a repository. Store it in an environment variable or a secrets manager instead.

3. Make a test request

   Export your key as an environment variable, then send a POST request to /v1/chat/completions:

   macOS and Linux

   bash or zsh

   export I14_API_KEY="your_api_key_here"
   
   curl https://api.i14.ai/v1/chat/completions \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer $I14_API_KEY" \
     -d '{
       "model": "i14-sugarglider-nemotron3-super-120B-v1",
       "messages": [
         {
           "role": "user",
           "content": "Explain the difference between a process and a thread in one paragraph."
         }
       ],
       "max_tokens": 2048
     }'

   Windows

   PowerShell

   $env:I14_API_KEY = "your_api_key_here"
   
   $body = @{
     model = "i14-sugarglider-nemotron3-super-120B-v1"
     messages = @(
       @{
         role = "user"
         content = "Explain the difference between a process and a thread in one paragraph."
       }
     )
     max_tokens = 2048
   } | ConvertTo-Json -Depth 5
   
   $response = Invoke-RestMethod https://api.i14.ai/v1/chat/completions `
     -Method Post `
     -ContentType "application/json" `
     -Headers @{ Authorization = "Bearer $env:I14_API_KEY" } `
     -Body $body
   
   $response.choices[0].message.content

   You should receive a JSON response with a choices array containing the model’s reply. In PowerShell, the last line prints the reply.

   Note

   Set max_tokens on every request. If you omit it, the API stops after 100 tokens and returns "finish_reason": "length".

4. List the models your key can use

   Call /v1/models to confirm that i14-sugarglider-nemotron3-super-120B-v1 is available to your key:

   macOS and Linux

   bash or zsh

   curl https://api.i14.ai/v1/models \
     -H "Authorization: Bearer $I14_API_KEY"

   Windows

   PowerShell

   (Invoke-RestMethod https://api.i14.ai/v1/models `
     -Headers @{ Authorization = "Bearer $env:I14_API_KEY" }).data.id

Python Example

The openai Python SDK works with i14 out of the box. Install it with pip install openai if you have not already, then run:

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.i14.ai/v1",
    api_key=os.environ["I14_API_KEY"],
)

response = client.chat.completions.create(
    model="i14-sugarglider-nemotron3-super-120B-v1",
    messages=[
        {
            "role": "user",
            "content": "Explain the difference between a process and a thread in one paragraph.",
        }
    ],
    max_tokens=2048,
)

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

Note

For TypeScript, streaming, and more SDK examples, see the OpenAI SDK guide and the Streaming guide.