Quickstart

Fireworks.ai is a lightning-fast inference platform that serves generative AI models. All the models are exposed over completions and a chat completions API. Using the API, you can build on popular open-source models and custom fine-tuned models like FireFunction, Hermes 2 Pro, etc.

Quickstart helps you to get started in minutes. However, if you want to explore more, please refer to the guides section or the API reference.

In this guide, you will:

• Set up your development environment
• Choose an SDK
• Call the Fireworks API with an API Key

​

Account Creation

Create a Fireworks AI account. Under Account Settings, click on API Keys to generate one. Please keep the API Key in a secure location.

​

Set up developer environment

• Python (Fireworks)
• Python (OpenAI)
• cURL

pip install --upgrade fireworks-ai

vim ~/.bash_profile

export FIREWORKS_API_KEY="<API_KEY>"

source ~/.bash_profile

setx FIREWORKS_API_KEY "<API_KEY>"

echo %FIREWORKS_API_KEY%

from fireworks.client import Fireworks

client = Fireworks(api_key="<FIREWORKS_API_KEY>")
response = client.chat.completions.create(
model="accounts/fireworks/models/llama-v2-7b-chat",
messages=[{
   "role": "user",
   "content": "Say this is a test",
}],
)

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

​

Dive in further

Have fun!

If you have any questions, please reach out to us on Discord or Twitter.