---
title: "Get Accelerator Usage"
method: GET
path: "/v1/accounts/{account_id}/acceleratorUsage"
tags: ["gateway.openapi_Gateway"]
---

# Get Accelerator Usage

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

## Request

- Base URL: `https://api.fireworks.ai`
- URL: `https://api.fireworks.ai/v1/accounts/{account_id}/acceleratorUsage`
- Auth: HTTP bearer

Gets the account's reserved accelerator capacity, allocated accelerators,
and pending accelerator demand across deployments and training jobs,
grouped by accelerator type.

## Path parameters

- `account_id` string, required

## Response `200`

A successful response.

- GatewayGetAccountAcceleratorUsageResponse: Response with the account's reserved accelerator capacity, allocated accelerators, and pending accelerator demand across deployments and training jobs.
  - `usageByType` GetAccountAcceleratorUsageResponseAcceleratorUsageByType[]: Accelerator counts by accelerator type. Groups with no reserved, allocated, or pending accelerators are omitted.
    - `acceleratorType` 'ACCELERATOR_TYPE_UNSPECIFIED' | 'NVIDIA_A100_80GB' | 'NVIDIA_H100_80GB' | 'AMD_MI300X_192GB' | 'NVIDIA_A10G_24GB' | 'NVIDIA_A100_40GB' | 'NVIDIA_L4_24GB' | 'NVIDIA_H200_141GB' | 'NVIDIA_B200_180GB' | 'AMD_MI325X_256GB' | 'AMD_MI350X_288GB' | 'NVIDIA_B300_288GB' | 'NVIDIA_GB200' | 'NVIDIA_GB300'
    - `downloadingModelAcceleratorCount` string, int64: Accelerators held by deployment replicas downloading model weights.
    - `initializingAcceleratorCount` string, int64: Accelerators held by deployment replicas starting up, including replicas that are restarting or retrying.
    - `readyAcceleratorCount` string, int64: Accelerators held by deployment replicas that are ready and serving traffic.
    - `pendingSchedulingAcceleratorCount` string, int64: Accelerators requested by deployment replicas still waiting for capacity.
    - `allocatedAcceleratorCount` string, int64: Total accelerators currently allocated across deployments and training jobs.
    - `pendingAcceleratorCount` string, int64: Total accelerators requested by deployments and training jobs that are not allocated yet.
    - `reservedAcceleratorCount` string, int64: Accelerators reserved by the account's reservations that are in effect.
    - `reservedAllocatedAcceleratorCount` string, int64: Allocated accelerators that count toward the account's reservations.
    - `onDemandAllocatedAcceleratorCount` string, int64: Allocated accelerators that do not count toward the account's reservations.

## Changes

- **2026-11-18** `0afef807f84b`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/fw-ai-external/apis/gateway-rest-api/changes/v1/accounts/:account_id/acceleratorUsage/get.md)

---

[API](https://skmtc.dev/fw-ai-external/apis/gateway-rest-api.md) - [All operations](https://skmtc.dev/fw-ai-external/apis/gateway-rest-api/llms.txt) - [OpenAPI document](https://skmtc.dev/fw-ai-external/apis/gateway-rest-api/revisions/0afef807f84b?raw)
