Skip to main content
GET
/
v1
/
accounts
/
{account_id}
/
billingUsage
Get account usage (serverless and dedicated deployments). Optionally filter by usage type via the usage_type field. If not specified, returns all usage types. TODO: rename this to /accountUsage
curl --request GET \
  --url https://api.fireworks.ai/v1/accounts/{account_id}/billingUsage \
  --header 'Authorization: Bearer <token>'
{
  "serverlessCosts": [
    {
      "modelName": "<string>",
      "promptTokens": "<string>",
      "completionTokens": "<string>",
      "startTime": "2023-11-07T05:31:56Z",
      "endTime": "2023-11-07T05:31:56Z",
      "audioInputSeconds": 123,
      "usageType": "<string>",
      "apiKeyId": "<string>",
      "group": {}
    }
  ],
  "dedicatedCosts": [
    {
      "deploymentId": "<string>",
      "acceleratorType": "<string>",
      "acceleratorSeconds": "<string>",
      "startTime": "2023-11-07T05:31:56Z",
      "endTime": "2023-11-07T05:31:56Z",
      "baseModel": "<string>",
      "usageType": "<string>",
      "placement": "<string>",
      "group": {}
    }
  ]
}

Documentation Index

Fetch the complete documentation index at: https://docs.fireworks.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

Bearer authentication using your Fireworks API key. Format: Bearer <API_KEY>

Path Parameters

​
account_id
string
required

The Account Id

Query Parameters

​
startTime
string<date-time>
required

Costs returned are inclusive of start_time. start_time must be before end_time.

​
endTime
string<date-time>
required

Costs returned are exclusive of end_time. end_time must not be more than 31 days after start_time.

​
usageType
enum<string>
default:USAGE_TYPE_UNSPECIFIED

Usage type to query usage for. If not specified, returns all usage types (serverless, dedicated deployments, and training).

  • USAGE_TYPE_UNSPECIFIED: Default value. When specified (or when usage_type field is not set), returns usage data for all deployment types: serverless requests, dedicated deployments, and training jobs.
  • SERVERLESS: Returns only serverless usage data. Filters the response to include only usage from serverless API requests.
  • DEDICATED_DEPLOYMENT: Returns only dedicated deployment usage data. Filters the response to include only usage from dedicated deployments.
  • TRAINING: Returns only training job usage data (SFT/DPO token usage and RFT / service-mode trainer GPU-seconds usage). Inference deployments serving rollouts for RFT / online RL are reported under DEDICATED_DEPLOYMENT (not TRAINING) to avoid double counting GPU time.
Available options:
USAGE_TYPE_UNSPECIFIED,
SERVERLESS,
DEDICATED_DEPLOYMENT,
TRAINING
​
timezone
string

IANA timezone identifier for daily aggregation (e.g., "America/Los_Angeles", "Europe/London"). When specified, the returned data will be aggregated into daily buckets based on this timezone. If not specified or empty, defaults to "UTC". See: https://en.wikipedia.org/wiki/List_of_tz_database_time_zones

​
groupBy
string[]

Dimensions to group usage by (multiple values allowed; each is a separate GROUP BY column). Each returned bucket carries the requested dimension values in the group map on the response item. Serverless: "model_name", "api_key_id", "api_key_name", "annotations.team", "annotations.project", "annotations.environment". Dedicated: "deployment_name", "accelerator_type", and the same annotation keys. Training: "job_id", "job_type", "usage_type", "accelerator_type", "base_model", and the same annotation keys. When usage_type is unspecified, dimensions that apply only to one stream are ignored on the others (e.g. "deployment_name" is ignored for serverless and training; "model_name" / "api_key_id" / "api_key_name" are ignored for dedicated and training; "job_id" / "job_type" are ignored for serverless and dedicated). Example: ["annotations.team", "model_name"] or ["api_key_id", "api_key_name"]. If empty: serverless aggregates by model name; dedicated defaults to deployment and accelerator type; training aggregates by job_id, job_type, usage_type, accelerator_type and base_model.

Maximum array length: 5
​
filter
object

Filter usage by dimension. Map query parameter — encode each entry as filter[<dimension>][values]=<value>, repeating the same key to OR multiple values for a single dimension. Serverless: "model_name", "api_key_id", "api_key_name", "annotations.team", "annotations.project", "annotations.environment". Dedicated: "deployment_name", "accelerator_type", and the same annotation keys. Training: "job_id", "job_type", "usage_type", "accelerator_type", "base_model", and the same annotation keys. Example: filter[api_key_name][values]=prod-key&filter[api_key_name][values]=staging-key.

Response

200 - application/json

A successful response.

​
serverlessCosts
List of serverless cost data · object[]
​
dedicatedCosts
List of dedicated deployment cost data · object[]