At a glance
- Availability: Experimental (how to enable).
- Authentication: API key.
- Connection: The key comes from
FIREWORKS_API_KEY. - Provider documentation: Authentication reference.
Credentials
Set these per environment. See Connect an integration.Setup
- Create a Fireworks AI account: Go to https://app.fireworks.ai and sign up or sign in. New accounts include free credits for testing serverless models.
- Create an API key: Open the API Keys page under account settings (https://app.fireworks.ai/settings/users/api-keys) and create a new key.
- Store the key: Copy the key and add it to your .env file as FIREWORKS_API_KEY=…
- Verify access: Run the List Models tool to confirm the key works. A 401 means the key is wrong or revoked.
Provider notes
- The inference API is OpenAI-compatible under https://api.fireworks.ai/inference/v1
- Serverless model IDs use the accounts/fireworks/models/<name> format
- Inference is billed per token once free credits are exhausted
Tools
Verify the connection
Call a read tool such asfireworks-ai__list_models with arguments for your account. Confirm that the result comes from the intended account or workspace before enabling write tools.