Client SDKs

We give you the option to use the Prem AI API, the PremAI SDK, or the OpenAI SDK.For API usage documentation, refer to the API Reference.

Create an API Key 🔑

Click the API Key button on the sidebar. Then click the + Create API Key button. Afterwards, copy the API key and save it in a secure location. Create an API Key

Use with PremAI SDK

Install the PremAI SDK

npm install premai

pip install premai

List Models

import PremAI from 'premai';

const client = new PremAI({
  apiKey: process.env['PREMAI_API_KEY'], // This is the default and can be omitted
});

const response = await client.models.list();

console.log(response.data);

import os
from premai import PremAI

client = PremAI(
    api_key=os.environ.get("PREMAI_API_KEY"),  # This is the default and can be omitted
)
response = client.models.list()
print(response.data)

Check Model Status

This is useful to check if a model is running or not. If it is not running, you can load it up using the load method.

The model name can be replaced with the name of your fine-tuned models as well.

import PremAI from 'premai';

const client = new PremAI({
  apiKey: process.env['PREMAI_API_KEY'] // This is the default and can be omitted
});

const response = await client.models.check_status(model="llama3.2-3b");

console.log(response);

import os
from premai import PremAI

client = PremAI(
    api_key=os.environ.get("PREMAI_API_KEY")  # This is the default and can be omitted
)
response = client.models.check_status(model="llama3.2-3b")
print(response)

Load Model

This is useful to load up a model for inference.

The model name can be replaced with the name of your fine-tuned models as well.

import PremAI from 'premai';

const client = new PremAI({
  apiKey: process.env['PREMAI_API_KEY'] // This is the default and can be omitted
});

const response = await client.models.load(model="llama3.2-3b"); // Or any other model you want to load up

const modelStatus = await client.models.check_status(model="llama3.2-3b");

console.log(modelStatus);

import os
from premai import PremAI

client = PremAI(
    api_key=os.environ.get("PREMAI_API_KEY")  # This is the default and can be omitted
)
response = client.models.load(
    model="llama3.2-3b", # Or any other model you want to load up
)
modelStatus = client.models.check_status(model="llama3.2-3b")
print(modelStatus.data)

Unload Model

This is useful to unload a model from the server.

The model name can be replaced with the name of your fine-tuned models as well.

import PremAI from 'premai';

const client = new PremAI({
  apiKey: process.env['PREMAI_API_KEY'] // This is the default and can be omitted
});

const response = await client.models.unload(model="llama3.2-3b"); // Or any other model you want to load up

console.log(response);

import os
from premai import PremAI

client = PremAI(
    api_key=os.environ.get("PREMAI_API_KEY")  # This is the default and can be omitted
)
response = client.models.unload(
    model="llama3.2-3b", # Or any other model you want to load up
)
print(response)

Chat Completions

import PremAI from 'premai';

const client = new PremAI({
  apiKey: process.env['PREMAI_API_KEY'], // This is the default and can be omitted
});

const response = await client.chat.completions({
    messages: [{
        role: 'user',
        content: 'Write a one-sentence bedtime story about a unicorn.'
    }],
    model: 'llama3.2-3b'
});

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

import os
from premai import PremAI

client = PremAI(
    api_key=os.environ.get("PREMAI_API_KEY"),  # This is the default and can be omitted
)
response = client.chat.completions(
    messages=[{
        "role": "user",
        "content": "Write a one-sentence bedtime story about a unicorn."
    }],
    model="llama3.2-3b",
)
print(response.choices[0].message.content)

import os
from premai import AsyncPremAI

client = AsyncPremAI(
    api_key=os.environ.get("PREMAI_API_KEY"),  # This is the default and can be omitted
)

# Create a chat completion
response = await client.chat.completions(
    messages=[{
        "role": "user",
        "content": "Write a one-sentence bedtime story about a unicorn."
    }],
    model="llama3.2-3b", # Or any other model you want to use
)

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

Chat Completion with Streaming

Streaming is not supported for the PremAI SDK. Will be supported in the future.

Use with OpenAI SDK

Install the OpenAI SDK

npm install openai

pip install openai

List Models

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: "https://studio.premai.io/api/v1/",
  apiKey: process.env['PREMAI_API_KEY'], // This is the default and can be omitted
});

const response = await client.models.list();

console.log(response.data);

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://studio.premai.io/api/v1/",
    api_key=os.environ.get("PREMAI_API_KEY"),  # This is the default and can be omitted
)
response = client.models.list()
print(response.data)

Chat Completions

The model name can be replaced with the name of your fine-tuned models as well.

import OpenAI from "openai";

const client = new OpenAI({
    baseURL: "https://studio.premai.io/api/v1/",
    apiKey: process.env.PREMAI_API_KEY,
});

//Create a chat completion
const response = await client.chat.completions.create({
    model: "llama3.2-3b", //Or any other model you want to use
    messages: [{ role: "user", content: "Write a one-sentence bedtime story about a unicorn." }]
});

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

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://studio.premai.io/api/v1/",
    api_key=os.environ.get("PREMAI_API_KEY"),
)

# Create a chat completion
response = client.chat.completions.create(
    messages=[{"role": "user", "content": "Who won the world series in 2020?"}],
    model="llama3.2-3b", # Or any other model you want to use
)

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

import os
from openai import AsyncOpenAI

client = AsyncOpenAI(
    base_url="https://studio.premai.io/api/v1/",
    api_key=os.environ.get("PREMAI_API_KEY"),
)

# Create a chat completion
response = await client.chat.completions.create(
    messages=[{"role": "user", "content": "Who won the world series in 2020?"}],
    model="llama3.2-3b", # Or any other model you want to use
)

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

Chat Completion with Streaming

import OpenAI from "openai";

const client = new OpenAI({
    baseURL: "https://studio.premai.io/api/v1/",
    apiKey: process.env.PREMAI_API_KEY,
});

//Create a chat completion
const response = await client.chat.completions.create({
    model: "llama3.2-3b", //Or any other model you want to use
    messages: [{ role: "user", content: "Write a one-sentence bedtime story about a unicorn." }],
    stream: true,
});

for await (const chunk of response) {
    process.stdout.write(chunk.choices[0].delta.content);
}

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://studio.premai.io/api/v1/",
    api_key=os.environ.get("PREMAI_API_KEY"),
)

# Create completion
response = client.chat.completions.create(
    messages=[{"role": "user", "content": "Who won the world series in 2020?"}],
    model="llama3.2-3b", # Or any other model you want to use
    stream=True,
)

for chunk in response:
    print(chunk.choices[0].delta.content, end='', flush=True)

import os
from openai import AsyncOpenAI

client = AsyncOpenAI(
    base_url="https://studio.premai.io/api/v1/",
    api_key=os.environ.get("PREMAI_API_KEY"),
)

# Create completion
response = await client.chat.completions.create(
    messages=[{"role": "user", "content": "Who won the world series in 2020?"}],
    model="llama3.2-3b", # Or any other model you want to use
    stream=True,
)

async for chunk in response:
    print(chunk.choices[0].delta.content, end='', flush=True)

Get started

Projects 🚀

Datasets 🗃️

Fine-Tuning 🛠️

Inference 🏃‍♂️

Agentic Evaluations 📈

User Guides 📚

Resources 🧰

Client SDKs

Create an API Key 🔑

Use with PremAI SDK

Install the PremAI SDK

List Models

Check Model Status

Load Model

Unload Model

Chat Completions

Chat Completion with Streaming

Use with OpenAI SDK

Install the OpenAI SDK

List Models

Chat Completions

Chat Completion with Streaming

​Create an API Key 🔑

​Use with PremAI SDK

​Install the PremAI SDK

​List Models

​Check Model Status

​Load Model

​Unload Model

​Chat Completions

​Chat Completion with Streaming

​Use with OpenAI SDK

​Install the OpenAI SDK

​List Models

​Chat Completions

​Chat Completion with Streaming

Create an API Key 🔑

Use with PremAI SDK

Install the PremAI SDK

List Models

Check Model Status

Load Model

Unload Model

Chat Completions

Chat Completion with Streaming

Use with OpenAI SDK

Install the OpenAI SDK

List Models

Chat Completions

Chat Completion with Streaming