Skip to main content
Use Fireworks AI models in the prompt playground and evals.
By adding this integration, your data may be sent to Fireworks AI for certain actions within Arize AX (e.g., prompt playground) and your account may be billed for usage.

​
Add the Integration Using the Arize Skills

Add a Fireworks AI integration from your coding agent using the Arize Skills:

Create a Fireworks AI integration named 'my-fireworks' with my API key fw_...

​
Add the Integration from Arize AX

​
Select Fireworks AI from the Providers List

Navigate to Settings -> AI Providers and select Fireworks AI.
The AI Provider integrations tab with the Fireworks AI tile highlighted

The AI Provider integrations tab

​
Fill Out Your Integration Details

The Fireworks AI integration details pane

The Fireworks AI integration configuration pane

Enter a name and your Fireworks AI API key.

​
Advanced Settings

The AI integration details tab

The Advanced Settings configuration pane

Expand the Advanced Settings section to configure the following:
  • Supports Function Calling - Turn this on to allow the integration to use function calling features. This is on by default.
  • Authorized Orgs - Configure which organizations have access to this integration.
  • Authorized Spaces - Configure which spaces have access to this integration.

​
Add the Integration

Finally check the box to agree to the terms and conditions, then select the Add Integration button to create the integration.

​
Choose a Fireworks Model

The model picker groups Fireworks models:
  • Serverless — ready to use with just your API key.
  • Your deployments — your dedicated deployments and fine-tunes, billed per GPU-hour.
  • Requires a deployment — create a deployment in Fireworks first.
A “model not found, inaccessible, and/or not deployed” error means the model isn’t served on demand. Pick a Serverless model or deploy it in Fireworks.