serverless: true. You load and unload adapters with the control-plane API and call them with the inference API.
All requests use
Authorization: Bearer $FIREWORKS_API_KEY. The examples on these pages use the same variables as the Get started guide:
my-lora as the adapter ID. Replace it with your adapter’s ID.
Endpoints
Two IDs are involved. The adapter ID (for example
my-lora) names the LoRA model you trained. The deployed model ID names one loaded copy of it. Load and call use the adapter ID. Get and unload over REST use the deployed model ID.The deployed model object
string
Resource name:
accounts/{account_id}/deployedModels/{deployed_model_id}. The last segment is the deployed_model_id.string
The LoRA model being served:
accounts/{account_id}/models/{adapter_id}.boolean
true for adapters loaded on serverless. Set by Fireworks from where the adapter is placed.boolean
true if this copy answers requests to the bare model name, without a # suffix.enum
One of
DEPLOYING, DEPLOYED, UPDATING or UNDEPLOYING. Send traffic once it’s DEPLOYED.object
Details about the last load or unload, including any error.
string
Optional display name.
string
Optional description.
timestamp
When the adapter was loaded.
timestamp
When the record last changed.