Build with AI Suite - SambaNova Integration Guide

Installation and setup

Install the package

pip install aisuite

Set your API key

export SAMBANOVA_API_KEY="your-api-key"

Make a request

Prefix any SambaNova model name with sambanova: in your code (e.g., sambanova:Llama-4-Maverick-17B-128E-Instruct). See the Example code section below and the full list of supported models.

Example code

import aisuite as ai
client = ai.Client()

models = ["sambanova:Llama-4-Maverick-17B-128E-Instruct", "sambanova:DeepSeek-V3.1"]

messages = [
    {"role": "system", "content": "Respond in Pirate English."},
    {"role": "user", "content": "Tell me a joke."},
]

for model in models:
    response = client.chat.completions.create(
        model=model,
        messages=messages,
        temperature=0.75
    )
    print(response.choices[0].message.content)

This is helpful because it allows you to compare speed and accuracy across different providers using the same codebase. For instance, you can include openai:gpt-4o alongside other models in your list.

For more information, see the AI Suite README on GitHub.

Troubleshooting

AuthenticationError or missing API key

Confirm SAMBANOVA_API_KEY is exported: echo $SAMBANOVA_API_KEY
Re-export and restart your terminal or script

Model not found or invalid prefix

Ensure model name uses the sambanova: prefix (e.g., sambanova:Llama-4-Maverick-17B-128E-Instruct)
Check available models on the SambaCloud models page

Python version error

AI Suite requires Python 3.9+. Check with python --version

Overview

Developer tools

Frameworks

Interfaces and low-code

Data and infrastructure

Multimodal

Evaluation and monitoring

AI Suite integration guide

Prerequisites

Installation and setup

Example code

Troubleshooting

​Prerequisites

​Installation and setup

​Example code

​Troubleshooting

Prerequisites

Installation and setup

Example code

Troubleshooting