Fireworks is a platform for providing endpoints for Large Language models.

​
Authentication

Set your FIREWORKS_API_KEY environment variable. Get your key from here.

export FIREWORKS_API_KEY=***

​
Prompt caching

Prompt caching will happen automatically using our Fireworks model. You can read more about how Fireworks handle caching in their docs.

​
Example

Use Fireworks with your Agent:

from agno.agent import Agent, RunResponse
from agno.models.fireworks import Fireworks

agent = Agent(
    model=Fireworks(id="accounts/fireworks/models/firefunction-v2"),
    markdown=True
)

# Print the response in the terminal
agent.print_response("Share a 2 sentence horror story.")
View more examples here.

​
Params

ParameterTypeDefaultDescription
idstr"accounts/fireworks/models/llama-v3p1-405b-instruct"The specific model ID used for generating responses.
namestr"Fireworks: {id}"The name identifier for the agent. Defaults to "Fireworks: " followed by the model ID.
providerstr"Fireworks"The provider of the model.
api_keyOptional[str]-The API key for authenticating requests to the service. Retrieved from the environment variable FIREWORKS_API_KEY.
base_urlstr"https://api.fireworks.ai/inference/v1"The base URL for making API requests to the Fireworks service.

Fireworks also supports the params of OpenAI.