Quickstart - Fireworks AI Docs

Fireworks AI is the best platform for building AI product experiences with open source AI models. You can run and customize AI models with just a few lines of code!

Using the API, you can access popular open-source models like Llama, DeepSeek, etc. The example below generates text output through an OpenAI-compatible chat completions API endpoint.

In this guide, you will get an API key, set up your development environment, and call the Fireworks API with an API Key.

Get an API key

Sign up or login to your Fireworks account. Generate an API key by navigating to the API Keys page and click on ‘Create API key’. Store the API Key in a safe location.

Set up your developer environment & call the Fireworks API

Install SDK

Before installing, ensure that you have the right version of Python installed. Optionally you might want to setup a virtual environment too.

pip install --upgrade fireworks-ai

The Fireworks Build SDK provides a declarative way to work with Fireworks resources and is OpenAI API Compatible.

Configure API Key

Step-by-step instructions for setting an environment variable for respective OS platforms:

MacOS/Linux

Depending on your shell, you’ll need to edit either ~/.bash_profile for Bash or ~/.zshrc for Zsh. You can do this by running the command:

vim ~/.bash_profile

Add a new line to the file with the following:

export FIREWORKS_API_KEY="<API_KEY>"

After saving the file, you’ll need to apply the changes by either restarting your terminal session or running depending on the file you edited.

source ~/.bash_profile

You can verify that the variable has been set correctly by running echo $FIREWORKS_API_KEY

Windows

You can open Command Prompt by searching for it in the Windows search bar or by pressing Win + R, typing cmd, and pressing Enter.

setx FIREWORKS_API_KEY "<API_KEY>"

To verify that the variable has been set correctly, you can close and reopen Command Prompt and type:

echo %FIREWORKS_API_KEY%

Sending the first API Request

You can quickly instantiate the LLM class and call the Fireworks API. The Build SDK handles deployment management automatically.

from fireworks import LLM

# Basic usage - SDK automatically selects optimal deployment type
llm = LLM(model="llama4-maverick-instruct-basic", deployment_type="auto")

response = llm.chat.completions.create(
    messages=[{"role": "user", "content": "Say this is a test"}]
)

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

You can also pass the API key directly to the LLM constructor: LLM(model="llama4-maverick-instruct-basic", deployment_type="auto", api_key="<FIREWORKS_API_KEY>")

Install SDK

Before installing, ensure that you have the right version of Python installed. Optionally you might want to setup a virtual environment too.

pip install --upgrade fireworks-ai

The Fireworks Build SDK provides a declarative way to work with Fireworks resources and is OpenAI API Compatible.

Configure API Key

Step-by-step instructions for setting an environment variable for respective OS platforms:

MacOS/Linux

Depending on your shell, you’ll need to edit either ~/.bash_profile for Bash or ~/.zshrc for Zsh. You can do this by running the command:

vim ~/.bash_profile

Add a new line to the file with the following:

export FIREWORKS_API_KEY="<API_KEY>"

After saving the file, you’ll need to apply the changes by either restarting your terminal session or running depending on the file you edited.

source ~/.bash_profile

You can verify that the variable has been set correctly by running echo $FIREWORKS_API_KEY

Windows

You can open Command Prompt by searching for it in the Windows search bar or by pressing Win + R, typing cmd, and pressing Enter.

setx FIREWORKS_API_KEY "<API_KEY>"

To verify that the variable has been set correctly, you can close and reopen Command Prompt and type:

echo %FIREWORKS_API_KEY%

Sending the first API Request

You can quickly instantiate the LLM class and call the Fireworks API. The Build SDK handles deployment management automatically.

from fireworks import LLM

# Basic usage - SDK automatically selects optimal deployment type
llm = LLM(model="llama4-maverick-instruct-basic", deployment_type="auto")

response = llm.chat.completions.create(
    messages=[{"role": "user", "content": "Say this is a test"}]
)

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

You can also pass the API key directly to the LLM constructor: LLM(model="llama4-maverick-instruct-basic", deployment_type="auto", api_key="<FIREWORKS_API_KEY>")

Install SDK

Before installing, ensure that you have the right version of Python installed. Optionally you might want to setup a virtual environment too.

pip install --upgrade openai

Fireworks AI platform offers drop-in replacement with OpenAI Python Client.

Configure API Key

Step-by-step instructions for setting an environment variable for respective OS platforms:

MacOS/Linux

Depending on your shell, you’ll need to edit either ~/.bash_profile for Bash or ~/.zshrc for Zsh. You can do this by running the command:

vim ~/.bash_profile

Add a new line to the file with the following:

export OPENAI_API_BASE="https://api.fireworks.ai/inference/v1"
export OPENAI_API_KEY="<YOUR_FIREWORKS_API_KEY>"

After saving the file, you’ll need to apply the changes by either restarting your terminal session or running depending on the file you edited.

source ~/.bash_profile

You can verify that the variable has been set correctly by running

echo $OPENAI_API_KEY

Windows

You can open Command Prompt by searching for it in the Windows search bar or by pressing Win + R, typing cmd, and pressing Enter.

setx OPENAI_API_BASE "https://api.fireworks.ai/inference/v1"
setx OPENAI_API_KEY "<API_KEY>"

To verify that the variable has been set correctly, you can close and reopen Command Prompt and type:

echo %OPENAI_API_KEY%

Sending the first API Request

You can quickly instantiate with the generated API Key and call the Fireworks API through OpenAI Python SDK.

from openai import OpenAI

client = OpenAI(
 api_key=os.environ.get("OPENAI_API_KEY"),
 base_url="https://api.fireworks.ai/inference/v1",
)

response = client.chat.completions.create(
 messages=[
     {
         "role": "user",
         "content": "Say this is a test",
     }
 ],
 # notice the change in the model name
 model="accounts/fireworks/models/llama-v3p3-70b-instruct",
)

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

Install SDK

Before installing, ensure that you have the right version of Node. Please make sure you have the npm installed or a package manager of your choice.

npm install openai

Fireworks AI platform offers drop-in replacement with OpenAI JavaScript Client.

Configure API Key

Step-by-step instructions for setting an environment variable for respective OS platforms:

MacOS/Linux

Depending on your shell, you’ll need to edit either ~/.bash_profile for Bash or ~/.zshrc for Zsh. You can do this by running the command:

vim ~/.bash_profile

Add a new line to the file with the following:

export FIREWORKS_API_KEY="<YOUR_FIREWORKS_API_KEY>"

After saving the file, you’ll need to apply the changes by either restarting your terminal session or running depending on the file you edited.

source ~/.bash_profile

You can verify that the variable has been set correctly by running

echo $FIREWORKS_API_KEY

Windows

You can open Command Prompt by searching for it in the Windows search bar or by pressing Win + R, typing cmd, and pressing Enter.

setx FIREWORKS_API_KEY "<API_KEY>"

To verify that the variable has been set correctly, you can close and reopen Command Prompt and type:

echo %FIREWORKS_API_KEY%

Sending the first API Request

You can quickly instantiate with the generated API Key and call the Fireworks API through OpenAI JavaScript SDK.

 import OpenAI from 'openai';

 const openai = new OpenAI({
   baseURL: 'https://api.fireworks.ai/inference/v1',
   apiKey: process.env['FIREWORKS_API_KEY']
 });

 const completion = await openai.chat.completions.create({
   messages: [{ role: "user", content: "Say this is a test" }],
   model: "accounts/fireworks/models/llama-v3p3-70b-instruct",
 });

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

cURL is a popular open-source command line tool to send HTTP requests. Most Operating systems ship cURL by default. However, if you are not sure, you can follow the first two steps of this guide to setup cURL. If not, we recommend skipping to Step Three.

Check if your operating system has cURL installed by running curl https://api.fireworks.ai

Setup cURL

MacOS

macOS comes with the cURL tool bundled with the operating system. If you want to upgrade to the latest version shipped by the cURL project, we recommend installing homebrew:

Homebrew

  brew install curl

Linux

Windows

Configure API Key

Step-by-step instructions for setting an environment variable for respective OS platforms:

MacOS/Linux

Depending on your shell, you’ll need to edit either ~/.bash_profile for Bash or ~/.zshrc for Zsh. You can do this by running the command:

vim ~/.bash_profile

Add a new line to the file with the following:

export FIREWORKS_API_KEY="<API_KEY>"

After saving the file, you’ll need to apply the changes by either restarting your terminal session or running depending on the file you edited.

source ~/.bash_profile

You can verify that the variable has been set correctly by running echo $FIREWORKS_API_KEY

Windows

You can open Command Prompt by searching for it in the Windows search bar or by pressing Win + R, typing cmd, and pressing Enter.

setx FIREWORKS_API_KEY "<API_KEY>"

To verify that the variable has been set correctly, you can close and reopen Command Prompt and type:

echo %FIREWORKS_API_KEY%

Sending the first API Request

Making your first API request with cURL. Notice the use of $FIREWORKS_API_KEY.

curl \
--header 'Authorization: Bearer '$FIREWORKS_API_KEY \
--header 'Content-Type: application/json' \
--data '{
"model": "accounts/fireworks/models/llama-v3p3-70b-instruct",
"messages": [{
  "role": "user",
  "content": "Say this is a test"
}]
}' \
--url https://api.fireworks.ai/inference/v1/chat/completions

More details on calling various APIs can be found at our API Reference

Explore further

Build with text models

Learn more about prompting text models

Explore API reference

View the full API reference

Fine Tune a Model

Customize a model for your specific use case

Use Dedicated Deployments

Get the best speed, reliability, & scalability

Query Vision Language Models

Query vision language models

Transcribe Audio

Convert speech to text async or in realtime

​Get an API key

​Set up your developer environment & call the Fireworks API

​Explore further

Build with text models

Explore API reference

Fine Tune a Model

Use Dedicated Deployments

Query Vision Language Models

Transcribe Audio

Get an API key

Set up your developer environment & call the Fireworks API

Explore further