---
title: "Get Account Usage"
method: GET
path: "/v1/accounts/{account_id}/billingUsage"
tags: ["Gateway"]
---

# Get Account Usage

`GET /v1/accounts/{account_id}/billingUsage`

## Path parameters

- `account_id` string, required

## Query parameters

- `startTime` string, date-time, required
- `endTime` string, date-time, required
- `usageType` 'USAGE_TYPE_UNSPECIFIED' | 'SERVERLESS' | 'DEDICATED_DEPLOYMENT' | 'TRAINING'
- `timezone` string
- `groupBy` string[]
- `filter` string

## Response `200`

A successful response.

- GatewayAccountUsage
  - `serverlessCosts` AccountUsageServerlessUsage[]
    - `modelName` string — Deprecated: use group["model_name"] instead.
    - `promptTokens` string, int64
    - `completionTokens` string, int64
    - `cachedPromptTokens` string, int64 — Number of prompt tokens served from cache (for text inference). Subset of prompt_tokens.
    - `uncachedPromptTokens` string, int64 — Number of prompt tokens not served from cache (for text inference). prompt_tokens - cached_prompt_tokens.
    - `startTime` string, date-time
    - `endTime` string, date-time
    - `audioInputSeconds` number, double
    - `usageType` string
    - `apiKeyId` string — Deprecated: use group["api_key_id"] instead.
    - `group` object — Group-by dimension key-values (model_name, api_key_id, api_key_name, user_id, session_id, team, project, environment). session_id is present only for buckets that had an opaque client session; no-session usage omits the key (all such usage collapses into a single "no session" bucket).
    - `costNanoUsd` number, double — Cost in nano-USD (1e-9 USD), summed from properties.cost. 0 when absent (not "free"). Only huggingface currently stamps authoritative cost.
  - `dedicatedCosts` AccountUsageDedicatedDeploymentUsage[]
    - `deploymentId` string
    - `acceleratorType` string
    - `acceleratorSeconds` string, int64
    - `startTime` string, date-time — Start timestamp of the usage. Note: Dedicated deployment usage events are aggregated daily. Only the date portion (YYYY-MM-DD) is used; the time portion is ignored.
    - `endTime` string, date-time — End timestamp of the usage. Note: Dedicated deployment usage events are aggregated daily. Only the date portion (YYYY-MM-DD) is used; the time portion is ignored.
    - `baseModel` string
    - `usageType` string
    - `placement` string — Deployment placement as a string (e.g. US_IOWA_1, GLOBAL, US, EUROPE). Set to REGION_UNSPECIFIED when unknown.
    - `group` object — Group-by dimension key-values (deployment_name, accelerator_type, team, project, environment).
  - `trainingCosts` AccountUsageTrainingUsage[] — List of training costs (SFT / DPO token usage and RFT / service-mode accelerator-second usage). Empty when training usage was not requested or when the account has training usage hidden.
    - `jobId` string — The managed training job id (e.g. supervised_fine_tuning_job id, rlor_trainer_job id). Empty for serverless training token rows; use `training_session_id` for those. Best-effort: extracted from billing event_id for legacy records that did not emit it as an explicit property.
    - `trainingSessionId` string — The serverless training session id. Populated for SERVERLESS_TRAINING_TOKENS rows and empty for managed training jobs.
    - `jobType` string — High-level training job kind: "sft", "dpo", "rft", "trainer", etc. Best-effort for legacy records.
    - `usageType` string — The underlying billing usage_type as emitted to the billing pipeline, e.g. "SUPERVISED_FINE_TUNING_USAGE", "REINFORCEMENT_FINE_TUNING_GPU_SECONDS", "FULL_PARAM_FINE_TUNING_GPU_HOURS". Frontends can use this to pick the right metric to display (tokens vs. accelerator_seconds).
    - `tokens` string, int64 — Total tokens billed for this bucket. Populated for SFT / DPO usage; 0 for accelerator-second usage types.
    - `acceleratorType` string — Accelerator type for accelerator-second usage (e.g. "NVIDIA_H100_80GB"). Empty for token-based usage.
    - `acceleratorSeconds` string, int64 — Total accelerator seconds billed for this bucket. Frontends typically display this as GPU hours (seconds / 3600). 0 for token-based usage.
    - `baseModel` string — Base model for the training job, when known.
    - `startTime` string, date-time — Start timestamp of the usage bucket. Note: Training usage events are aggregated daily. Only the date portion (YYYY-MM-DD) is used; the time portion is ignored.
    - `endTime` string, date-time — End timestamp of the usage bucket. Note: Training usage events are aggregated daily. Only the date portion (YYYY-MM-DD) is used; the time portion is ignored.
    - `group` object — Group-by dimension key-values for the requested group_by. May include any of: job_id, training_session_id, job_type, usage_type, accelerator_type, base_model, annotations.team, annotations.project, annotations.environment. Empty values are omitted. Annotation values will typically be empty for training usage until billing emitters propagate annotations.
    - `annotations` object — Annotation key-values associated with this bucket (team, project, environment). Mirrors the annotation entries in `group` for API symmetry with future per-stream consumers. Typically empty for training usage today until trainer-side billing emitters populate properties.annotation_* on every record.

---

[API](https://skmtc.net/fireworks/apis/fireworks-ai-anthropic-compatible-messages-api.md) · [All operations](https://skmtc.net/fireworks/apis/fireworks-ai-anthropic-compatible-messages-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/fireworks/fireworks-ai-anthropic-compatible-messages-api/revisions/954d6bc5d922/schema)