--- title: Account Management | Runware Docs url: https://runware.ai/docs/platform/account-management description: Retrieve account details, team members, API keys, and usage stats (spend, performance, errors) for your organization with the account management API. relatedDocuments: - https://runware.ai/docs/platform/authentication - https://runware.ai/docs/platform/rate-limits --- ## Introduction The `accountManagement` task **reads your organization's account data over the API**: the `team` and their roles, your API keys, the current `balance`, and usage statistics. Reach for it whenever a script needs account state that would otherwise mean opening the web console, like billing automation or a usage alert. Everything runs through the `operation` parameter: it selects the dataset and **shapes both the request and the response**. Each operation is documented in its own section below. | Operation | Returns | | --- | --- | | `getDetails` | Organization info, team, API keys, and rolling usage totals. | | `getUsageActivity` | Requests and spend over a date range, broken down by day, model, and/or API key. | | `getUsagePerformance` | Per-model inference-time percentiles over a date range. | | `getUsageErrors` | Client (`4xx`) and server (`5xx`) error counts over a date range. | The three usage operations share the same request parameters (a date window plus optional filters) and the same `usage` response envelope, **differing only in the metrics each row reports**. ## getDetails Everything about the account in one call, with **no date range or filters**. The response carries the organization identity, the current `balance`, the full `team` roster with roles, and every API key with its lifetime request count. The `usage` object here holds **rolling totals** rather than a time breakdown: credits and requests for `today`, `last7Days`, `last30Days`, and lifetime `total`. Use `getDetails` for a point-in-time picture of the account, and the operations below when you need consumption sliced across a date range. ### Request **TypeScript**: ```typescript import { createClient } from '@runware/sdk' const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY }) await client.connect() const result = await client.accountManagement({ operation: 'getDetails' }) ``` **Python**: ```python import asyncio import os from runware import Runware async def main(): async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client: result = await client.account_management({ "operation": "getDetails" }) asyncio.run(main()) ``` **cURL**: ```bash curl https://api.runware.ai/v1 \ -H "Authorization: Bearer $RUNWARE_API_KEY" \ -H "Content-Type: application/json" \ -d '[ { "taskType": "accountManagement", "taskUUID": "f4dd3dfe-955f-49d5-a785-7e3b633d6e7a", "operation": "getDetails" } ]' ``` **CLI**: ```bash runware account details ``` **JSON**: ```json { "taskType": "accountManagement", "taskUUID": "f4dd3dfe-955f-49d5-a785-7e3b633d6e7a", "operation": "getDetails" } ``` --- ### [taskType](#request-tasktype) - **Type**: `string` - **Required**: true - **Value**: `accountManagement` Identifier for the type of task being performed ### [taskUUID](#request-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task. ### [operation](#request-operation) - **Type**: `string` - **Required**: true - **Value**: `getDetails` The specific account management operation to perform. ### Response ```json { "data": [ { "taskType": "accountManagement", "taskUUID": "f4dd3dfe-955f-49d5-a785-7e3b633d6e7a", "operation": "getDetails", "organizationUUID": "a6379343-9ff2-46a0-996b-e4a7b3057c88", "organizationName": "Acme Corporation", "balance": { "amount": 2450.75, "freeBalance": 120.00, "currency": "USD" }, "team": [ { "name": "John Smith", "email": "john.smith@acme.com", "roles": ["Owner"], "joinedAt": "2024-01-15T10:30:00Z" } ], "apiKeys": [ { "name": "Production API Key", "apiKey": "YHluz4gk5KU4ZZWr****************", "enabled": true, "createdAt": "2024-01-20T11:00:00Z", "requests": 15420, "lastUsedAt": "2025-10-12T08:45:30Z" } ], "usage": { "today": { "credits": 35.80, "requests": 1850 }, "last7Days": { "credits": 412.25, "requests": 21400 }, "last30Days": { "credits": 1685.90, "requests": 87560 }, "total": { "credits": 48920.50, "requests": 2540318 } } } ] } ``` --- ### [taskType](#response-tasktype) - **Type**: `string` - **Required**: true - **Value**: `accountManagement` Identifier for the type of task this response belongs to. ### [taskUUID](#response-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier echoed from the original request, used to match async responses to their tasks. ### [operation](#response-operation) - **Type**: `string` - **Required**: true - **Value**: `getDetails` The account management operation that produced this response. ### [organizationName](#response-organizationname) - **Type**: `string` The name of the organization. ### [organizationUUID](#response-organizationuuid) - **Type**: `string` - **Format**: `UUID v4` Unique identifier for the organization. ### [balance](#response-balance) - **Path**: `balance.amount` - **Type**: `object (3 properties)` Current account balance and currency. #### [amount](#response-balance-amount) - **Path**: `balance.amount` - **Type**: `float` - **Required**: true Current balance amount. #### [freeBalance](#response-balance-freebalance) - **Path**: `balance.freeBalance` - **Type**: `float` Available free credit balance. #### [currency](#response-balance-currency) - **Path**: `balance.currency` - **Type**: `string` - **Required**: true Currency code. ### [team](#response-team) - **Path**: `team.name` - **Type**: `array of objects (4 properties)` List of team members. #### [name](#response-team-name) - **Path**: `team.name` - **Type**: `string` - **Required**: true Full name of the team member. #### [email](#response-team-email) - **Path**: `team.email` - **Type**: `string` - **Required**: true - **Format**: `email` Email address of the team member. #### [roles](#response-team-roles) - **Path**: `team.roles` - **Type**: `array of strings` - **Required**: true Each team member is assigned a role that determines their level of access within the organization. | Capability | Owner | Admin | Developer | | --- | --- | --- | --- | | API generation and Playground | ✓ | ✓ | ✓ | | Manage Playground workflows | ✓ | ✓ | ✓ | | Create and manage API keys | ✓ | ✓ | | | View API logs and usage analytics | ✓ | ✓ | | | Manage billing and payment methods | ✓ | ✓ | | | Invite and remove team members | ✓ | ✓ | | | Assign Admin and Developer roles | ✓ | ✓ | | | Assign Owner role | ✓ | | | | Delete organization | ✓ | | | #### [joinedAt](#response-team-joinedat) - **Path**: `team.joinedAt` - **Type**: `string` - **Format**: `date-time` Date and time when the member joined. ### [apiKeys](#response-apikeys) - **Path**: `apiKeys.apiKey` - **Type**: `array of objects (7 properties)` List of API keys associated with the account. #### [apiKey](#response-apikeys-apikey) - **Path**: `apiKeys.apiKey` - **Type**: `string` - **Required**: true The API key string (partially masked). #### [name](#response-apikeys-name) - **Path**: `apiKeys.name` - **Type**: `string` - **Required**: true Name or label for the API key. #### [description](#response-apikeys-description) - **Path**: `apiKeys.description` - **Type**: `string` Description of the API key. #### [enabled](#response-apikeys-enabled) - **Path**: `apiKeys.enabled` - **Type**: `boolean` - **Required**: true Whether the API key is active. #### [createdAt](#response-apikeys-createdat) - **Path**: `apiKeys.createdAt` - **Type**: `string` - **Required**: true - **Format**: `date-time` Date and time when the key was created. #### [lastUsedAt](#response-apikeys-lastusedat) - **Path**: `apiKeys.lastUsedAt` - **Type**: `string` - **Format**: `date-time` Date and time when the key was last used. #### [requests](#response-apikeys-requests) - **Path**: `apiKeys.requests` - **Type**: `integer` Total number of requests made with this key. ### [usage](#response-usage) - **Path**: `usage.today` - **Type**: `object (12 properties)` Account usage statistics. #### [today](#response-usage-today) - **Path**: `usage.today` - **Type**: `object (2 properties)` Usage stats for today. ##### [credits](#response-usage-today-credits) - **Path**: `usage.today.credits` - **Type**: `float` - **Required**: true Total credits consumed. ##### [requests](#response-usage-today-requests) - **Path**: `usage.today.requests` - **Type**: `integer` - **Required**: true Total API requests made. #### [last7Days](#response-usage-last7days) - **Path**: `usage.last7Days` - **Type**: `object (2 properties)` Usage stats for the last 7 days. ##### [credits](#response-usage-last7days-credits) - **Path**: `usage.last7Days.credits` - **Type**: `float` - **Required**: true Total credits consumed. ##### [requests](#response-usage-last7days-requests) - **Path**: `usage.last7Days.requests` - **Type**: `integer` - **Required**: true Total API requests made. #### [last30Days](#response-usage-last30days) - **Path**: `usage.last30Days` - **Type**: `object (2 properties)` Usage stats for the last 30 days. ##### [credits](#response-usage-last30days-credits) - **Path**: `usage.last30Days.credits` - **Type**: `float` - **Required**: true Total credits consumed. ##### [requests](#response-usage-last30days-requests) - **Path**: `usage.last30Days.requests` - **Type**: `integer` - **Required**: true Total API requests made. #### [total](#response-usage-total) - **Path**: `usage.total` - **Type**: `object (2 properties)` Total lifetime usage stats. ##### [credits](#response-usage-total-credits) - **Path**: `usage.total.credits` - **Type**: `float` - **Required**: true Total credits consumed. ##### [requests](#response-usage-total-requests) - **Path**: `usage.total.requests` - **Type**: `integer` - **Required**: true Total API requests made. ## getUsageActivity How much the account spent and how many requests it ran, over the window you set with `startDate` and `endDate`. This is the call behind a **usage dashboard** or a **monthly billing report**. `groupBy` controls how the totals are sliced. Ask for `date` and you get a `timeseries` of per-day rows. Ask for `model` or `apiKey` and the same totals come back **split by that dimension**, and you can request several at once. Each slice lands under `usage` as its own breakdown: a `data` array with one row per bucket (`count` and `spend`), plus a `meta` roll-up that totals the window and projects a 30-day spend. ### Request **TypeScript**: ```typescript import { createClient } from '@runware/sdk' const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY }) await client.connect() const result = await client.accountManagement({ operation: 'getUsageActivity', startDate: '2026-07-01', endDate: '2026-07-06', groupBy: [ 'date', 'model' ], timezone: 'America/New_York' }) ``` **Python**: ```python import asyncio import os from runware import Runware async def main(): async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client: result = await client.account_management({ "operation": "getUsageActivity", "startDate": "2026-07-01", "endDate": "2026-07-06", "groupBy": [ "date", "model" ], "timezone": "America/New_York" }) asyncio.run(main()) ``` **cURL**: ```bash curl https://api.runware.ai/v1 \ -H "Authorization: Bearer $RUNWARE_API_KEY" \ -H "Content-Type: application/json" \ -d '[ { "taskType": "accountManagement", "taskUUID": "b7e0a3f2-3c1a-4d9e-8f2b-1a2c3d4e5f60", "operation": "getUsageActivity", "startDate": "2026-07-01", "endDate": "2026-07-06", "groupBy": [ "date", "model" ], "timezone": "America/New_York" } ]' ``` **CLI**: ```bash runware account getUsageActivity ``` **JSON**: ```json { "taskType": "accountManagement", "taskUUID": "b7e0a3f2-3c1a-4d9e-8f2b-1a2c3d4e5f60", "operation": "getUsageActivity", "startDate": "2026-07-01", "endDate": "2026-07-06", "groupBy": [ "date", "model" ], "timezone": "America/New_York" } ``` --- ### [taskType](#request-tasktype) - **Type**: `string` - **Required**: true - **Value**: `accountManagement` Identifier for the type of task being performed ### [taskUUID](#request-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task. ### [operation](#request-operation) - **Type**: `string` - **Required**: true - **Value**: `getUsageActivity` The specific account management operation to perform. ### [startDate](#request-startdate) - **Type**: `string` - **Format**: `date` Start of the usage window (inclusive). ### [endDate](#request-enddate) - **Type**: `string` - **Format**: `date` End of the usage window (inclusive). Must be on or after startDate, and the span must not exceed 30 days. ### [models](#request-models) - **Type**: `array of strings` - **Max items**: `100` Restrict usage to these model AIRs. Defaults to all models. ### [apiKeys](#request-apikeys) - **Type**: `array of strings` - **Max items**: `100` Restrict usage to these API key UUIDs. Defaults to all keys. ### [groupBy](#request-groupby) - **Type**: `array of strings` - **Default**: `date,model` Breakdowns to return. ### [timezone](#request-timezone) - **Type**: `string` - **Default**: `UTC` IANA timezone name used for day-bucketing. ### Response ```json { "data": [ { "taskType": "accountManagement", "taskUUID": "b7e0a3f2-3c1a-4d9e-8f2b-1a2c3d4e5f60", "operation": "getUsageActivity", "startDate": "2026-07-01", "endDate": "2026-07-06", "usage": { "timeseries": { "data": [{ "date": "2026-07-01", "count": 340, "spend": 120.05154 }], "meta": { "totalRequests": 1197, "totalResults": 1197, "totalSpend": 493.7819, "avgDailySpend": 87.37, "projectedSpend": 2708.55 } }, "model": { "data": [{ "date": "2026-07-01", "model": "google:gemini@omni-flash", "modelName": "Gemini Omni Flash", "count": 207, "spend": 101.457393 }], "meta": { "totalRequests": 1197, "totalResults": 1197, "totalSpend": 493.7819, "avgDailySpend": 87.37, "projectedSpend": 2708.55 } } } } ] } ``` --- ### [taskType](#response-tasktype) - **Type**: `string` - **Required**: true - **Value**: `accountManagement` Identifier for the type of task this response belongs to. ### [taskUUID](#response-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier echoed from the original request, used to match async responses to their tasks. ### [operation](#response-operation) - **Type**: `string` - **Required**: true - **Value**: `getUsageActivity` The account management operation that produced this response. ### [startDate](#response-startdate) - **Type**: `string` - **Format**: `date` Start of the returned window (inclusive). ### [endDate](#response-enddate) - **Type**: `string` - **Format**: `date` End of the returned window (inclusive). ### [usage](#response-usage) - **Path**: `usage.today` - **Type**: `object (46 properties)` Account usage statistics. #### [today](#response-usage-today) - **Path**: `usage.today` - **Type**: `object` Usage stats for today. #### [last7Days](#response-usage-last7days) - **Path**: `usage.last7Days` - **Type**: `object` Usage stats for the last 7 days. #### [last30Days](#response-usage-last30days) - **Path**: `usage.last30Days` - **Type**: `object` Usage stats for the last 30 days. #### [total](#response-usage-total) - **Path**: `usage.total` - **Type**: `object` Total lifetime usage stats. #### [timeseries](#response-usage-timeseries) - **Path**: `usage.timeseries` - **Type**: `object (13 properties)` Per-day breakdown (from groupBy date). ##### [data](#response-usage-timeseries-data) - **Path**: `usage.timeseries.data` - **Type**: `array of objects (6 properties)` - **Required**: true Rows for this breakdown. ##### [date](#response-usage-timeseries-data-date) - **Path**: `usage.timeseries.data.date` - **Type**: `string` - **Format**: `date` Day bucket. ##### [model](#response-usage-timeseries-data-model) - **Path**: `usage.timeseries.data.model` - **Type**: `string` Model AIR. ##### [modelName](#response-usage-timeseries-data-modelname) - **Path**: `usage.timeseries.data.modelName` - **Type**: `string` Human-friendly model name. Falls back to the AIR when none exists. ##### [apiKey](#response-usage-timeseries-data-apikey) - **Path**: `usage.timeseries.data.apiKey` - **Type**: `string` API key UUID. ##### [count](#response-usage-timeseries-data-count) - **Path**: `usage.timeseries.data.count` - **Type**: `integer` Number of requests in this bucket. ##### [spend](#response-usage-timeseries-data-spend) - **Path**: `usage.timeseries.data.spend` - **Type**: `float` Amount spent in this bucket. ##### [meta](#response-usage-timeseries-meta) - **Path**: `usage.timeseries.meta` - **Type**: `object (5 properties)` - **Required**: true Roll-up totals for a breakdown. Which fields are present depends on the operation. ##### [totalRequests](#response-usage-timeseries-meta-totalrequests) - **Path**: `usage.timeseries.meta.totalRequests` - **Type**: `integer` Total requests across the window. ##### [totalResults](#response-usage-timeseries-meta-totalresults) - **Path**: `usage.timeseries.meta.totalResults` - **Type**: `integer` Total results produced across the window. ##### [totalSpend](#response-usage-timeseries-meta-totalspend) - **Path**: `usage.timeseries.meta.totalSpend` - **Type**: `float` Total spend across the window. ##### [avgDailySpend](#response-usage-timeseries-meta-avgdailyspend) - **Path**: `usage.timeseries.meta.avgDailySpend` - **Type**: `float` Average spend per day. An estimate that drifts between calls. ##### [projectedSpend](#response-usage-timeseries-meta-projectedspend) - **Path**: `usage.timeseries.meta.projectedSpend` - **Type**: `float` Projected 30-day spend extrapolated from the window. An estimate that drifts between calls. #### [model](#response-usage-model) - **Path**: `usage.model` - **Type**: `object (13 properties)` Per-model breakdown (from groupBy model). ##### [data](#response-usage-model-data) - **Path**: `usage.model.data` - **Type**: `array of objects (6 properties)` - **Required**: true Rows for this breakdown. ##### [date](#response-usage-model-data-date) - **Path**: `usage.model.data.date` - **Type**: `string` - **Format**: `date` Day bucket. ##### [model](#response-usage-model-data-model) - **Path**: `usage.model.data.model` - **Type**: `string` Model AIR. ##### [modelName](#response-usage-model-data-modelname) - **Path**: `usage.model.data.modelName` - **Type**: `string` Human-friendly model name. Falls back to the AIR when none exists. ##### [apiKey](#response-usage-model-data-apikey) - **Path**: `usage.model.data.apiKey` - **Type**: `string` API key UUID. ##### [count](#response-usage-model-data-count) - **Path**: `usage.model.data.count` - **Type**: `integer` Number of requests in this bucket. ##### [spend](#response-usage-model-data-spend) - **Path**: `usage.model.data.spend` - **Type**: `float` Amount spent in this bucket. ##### [meta](#response-usage-model-meta) - **Path**: `usage.model.meta` - **Type**: `object (5 properties)` - **Required**: true Roll-up totals for a breakdown. Which fields are present depends on the operation. ##### [totalRequests](#response-usage-model-meta-totalrequests) - **Path**: `usage.model.meta.totalRequests` - **Type**: `integer` Total requests across the window. ##### [totalResults](#response-usage-model-meta-totalresults) - **Path**: `usage.model.meta.totalResults` - **Type**: `integer` Total results produced across the window. ##### [totalSpend](#response-usage-model-meta-totalspend) - **Path**: `usage.model.meta.totalSpend` - **Type**: `float` Total spend across the window. ##### [avgDailySpend](#response-usage-model-meta-avgdailyspend) - **Path**: `usage.model.meta.avgDailySpend` - **Type**: `float` Average spend per day. An estimate that drifts between calls. ##### [projectedSpend](#response-usage-model-meta-projectedspend) - **Path**: `usage.model.meta.projectedSpend` - **Type**: `float` Projected 30-day spend extrapolated from the window. An estimate that drifts between calls. #### [apiKey](#response-usage-apikey) - **Path**: `usage.apiKey` - **Type**: `object (13 properties)` Per-key breakdown (from groupBy apiKey). ##### [data](#response-usage-apikey-data) - **Path**: `usage.apiKey.data` - **Type**: `array of objects (6 properties)` - **Required**: true Rows for this breakdown. ##### [date](#response-usage-apikey-data-date) - **Path**: `usage.apiKey.data.date` - **Type**: `string` - **Format**: `date` Day bucket. ##### [model](#response-usage-apikey-data-model) - **Path**: `usage.apiKey.data.model` - **Type**: `string` Model AIR. ##### [modelName](#response-usage-apikey-data-modelname) - **Path**: `usage.apiKey.data.modelName` - **Type**: `string` Human-friendly model name. Falls back to the AIR when none exists. ##### [apiKey](#response-usage-apikey-data-apikey) - **Path**: `usage.apiKey.data.apiKey` - **Type**: `string` API key UUID. ##### [count](#response-usage-apikey-data-count) - **Path**: `usage.apiKey.data.count` - **Type**: `integer` Number of requests in this bucket. ##### [spend](#response-usage-apikey-data-spend) - **Path**: `usage.apiKey.data.spend` - **Type**: `float` Amount spent in this bucket. ##### [meta](#response-usage-apikey-meta) - **Path**: `usage.apiKey.meta` - **Type**: `object (5 properties)` - **Required**: true Roll-up totals for a breakdown. Which fields are present depends on the operation. ##### [totalRequests](#response-usage-apikey-meta-totalrequests) - **Path**: `usage.apiKey.meta.totalRequests` - **Type**: `integer` Total requests across the window. ##### [totalResults](#response-usage-apikey-meta-totalresults) - **Path**: `usage.apiKey.meta.totalResults` - **Type**: `integer` Total results produced across the window. ##### [totalSpend](#response-usage-apikey-meta-totalspend) - **Path**: `usage.apiKey.meta.totalSpend` - **Type**: `float` Total spend across the window. ##### [avgDailySpend](#response-usage-apikey-meta-avgdailyspend) - **Path**: `usage.apiKey.meta.avgDailySpend` - **Type**: `float` Average spend per day. An estimate that drifts between calls. ##### [projectedSpend](#response-usage-apikey-meta-projectedspend) - **Path**: `usage.apiKey.meta.projectedSpend` - **Type**: `float` Projected 30-day spend extrapolated from the window. An estimate that drifts between calls. ## getUsagePerformance How fast the account's models run. For a date window, each `model` row reports the **average, p90, and p99 inference time** in seconds, so you can track tail latency per model. Percentiles are only meaningful within a single model, so the data lives in the `model` breakdown and the `timeseries` breakdown **comes back empty**. ### Request **TypeScript**: ```typescript import { createClient } from '@runware/sdk' const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY }) await client.connect() const result = await client.accountManagement({ operation: 'getUsagePerformance', startDate: '2026-07-01', endDate: '2026-07-06', groupBy: [ 'date', 'model' ] }) ``` **Python**: ```python import asyncio import os from runware import Runware async def main(): async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client: result = await client.account_management({ "operation": "getUsagePerformance", "startDate": "2026-07-01", "endDate": "2026-07-06", "groupBy": [ "date", "model" ] }) asyncio.run(main()) ``` **cURL**: ```bash curl https://api.runware.ai/v1 \ -H "Authorization: Bearer $RUNWARE_API_KEY" \ -H "Content-Type: application/json" \ -d '[ { "taskType": "accountManagement", "taskUUID": "ed936635-488f-48c2-8c4d-dbf117c8a7b1", "operation": "getUsagePerformance", "startDate": "2026-07-01", "endDate": "2026-07-06", "groupBy": [ "date", "model" ] } ]' ``` **CLI**: ```bash runware account getUsagePerformance ``` **JSON**: ```json { "taskType": "accountManagement", "taskUUID": "ed936635-488f-48c2-8c4d-dbf117c8a7b1", "operation": "getUsagePerformance", "startDate": "2026-07-01", "endDate": "2026-07-06", "groupBy": [ "date", "model" ] } ``` --- ### [taskType](#request-tasktype) - **Type**: `string` - **Required**: true - **Value**: `accountManagement` Identifier for the type of task being performed ### [taskUUID](#request-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task. ### [operation](#request-operation) - **Type**: `string` - **Required**: true - **Value**: `getUsagePerformance` The specific account management operation to perform. ### [startDate](#request-startdate) - **Type**: `string` - **Format**: `date` Start of the usage window (inclusive). ### [endDate](#request-enddate) - **Type**: `string` - **Format**: `date` End of the usage window (inclusive). Must be on or after startDate, and the span must not exceed 30 days. ### [models](#request-models) - **Type**: `array of strings` - **Max items**: `100` Restrict usage to these model AIRs. Defaults to all models. ### [apiKeys](#request-apikeys) - **Type**: `array of strings` - **Max items**: `100` Restrict usage to these API key UUIDs. Defaults to all keys. ### [groupBy](#request-groupby) - **Type**: `array of strings` - **Default**: `date,model` Breakdowns to return. ### [timezone](#request-timezone) - **Type**: `string` - **Default**: `UTC` IANA timezone name used for day-bucketing. ### Response ```json { "data": [ { "taskType": "accountManagement", "taskUUID": "ed936635-488f-48c2-8c4d-dbf117c8a7b1", "operation": "getUsagePerformance", "startDate": "2026-07-01", "endDate": "2026-07-06", "usage": { "model": { "data": [{ "date": "2026-07-03", "model": "bytedance:video-upscaler@standard", "modelName": "Bytedance Video Upscaler", "avgInferenceTime": 134.8486, "p90InferenceTime": 226.245, "p99InferenceTime": 291.6665 }], "meta": { "totalRequests": 164, "totalResults": 164, "totalSpend": 1.6226, "avgDailySpend": 0.2704, "projectedSpend": 8.38, "avgInferenceTime": 134.8486, "p50InferenceTime": 144.49, "p90InferenceTime": 226.245, "p99InferenceTime": 291.6665 } } } } ] } ``` --- ### [taskType](#response-tasktype) - **Type**: `string` - **Required**: true - **Value**: `accountManagement` Identifier for the type of task this response belongs to. ### [taskUUID](#response-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier echoed from the original request, used to match async responses to their tasks. ### [operation](#response-operation) - **Type**: `string` - **Required**: true - **Value**: `getUsagePerformance` The account management operation that produced this response. ### [startDate](#response-startdate) - **Type**: `string` - **Format**: `date` Start of the returned window (inclusive). ### [endDate](#response-enddate) - **Type**: `string` - **Format**: `date` End of the returned window (inclusive). ### [usage](#response-usage) - **Path**: `usage.today` - **Type**: `object (61 properties)` Account usage statistics. #### [today](#response-usage-today) - **Path**: `usage.today` - **Type**: `object` Usage stats for today. #### [last7Days](#response-usage-last7days) - **Path**: `usage.last7Days` - **Type**: `object` Usage stats for the last 7 days. #### [last30Days](#response-usage-last30days) - **Path**: `usage.last30Days` - **Type**: `object` Usage stats for the last 30 days. #### [total](#response-usage-total) - **Path**: `usage.total` - **Type**: `object` Total lifetime usage stats. #### [timeseries](#response-usage-timeseries) - **Path**: `usage.timeseries` - **Type**: `object (18 properties)` Per-day breakdown (from groupBy date). ##### [data](#response-usage-timeseries-data) - **Path**: `usage.timeseries.data` - **Type**: `array of objects (7 properties)` - **Required**: true Rows for this breakdown. ##### [date](#response-usage-timeseries-data-date) - **Path**: `usage.timeseries.data.date` - **Type**: `string` - **Format**: `date` Day bucket. ##### [model](#response-usage-timeseries-data-model) - **Path**: `usage.timeseries.data.model` - **Type**: `string` Model AIR. ##### [modelName](#response-usage-timeseries-data-modelname) - **Path**: `usage.timeseries.data.modelName` - **Type**: `string` Human-friendly model name. Falls back to the AIR when none exists. ##### [apiKey](#response-usage-timeseries-data-apikey) - **Path**: `usage.timeseries.data.apiKey` - **Type**: `string` API key UUID. ##### [avgInferenceTime](#response-usage-timeseries-data-avginferencetime) - **Path**: `usage.timeseries.data.avgInferenceTime` - **Type**: `float | null` Average inference time in seconds, or null when there were no inferences. ##### [p90InferenceTime](#response-usage-timeseries-data-p90inferencetime) - **Path**: `usage.timeseries.data.p90InferenceTime` - **Type**: `float | null` 90th-percentile inference time in seconds, or null when there were no inferences. ##### [p99InferenceTime](#response-usage-timeseries-data-p99inferencetime) - **Path**: `usage.timeseries.data.p99InferenceTime` - **Type**: `float | null` 99th-percentile inference time in seconds, or null when there were no inferences. ##### [meta](#response-usage-timeseries-meta) - **Path**: `usage.timeseries.meta` - **Type**: `object (9 properties)` - **Required**: true Roll-up totals for a breakdown. Which fields are present depends on the operation. ##### [totalRequests](#response-usage-timeseries-meta-totalrequests) - **Path**: `usage.timeseries.meta.totalRequests` - **Type**: `integer` Total requests across the window. ##### [totalResults](#response-usage-timeseries-meta-totalresults) - **Path**: `usage.timeseries.meta.totalResults` - **Type**: `integer` Total results produced across the window. ##### [totalSpend](#response-usage-timeseries-meta-totalspend) - **Path**: `usage.timeseries.meta.totalSpend` - **Type**: `float` Total spend across the window. ##### [avgDailySpend](#response-usage-timeseries-meta-avgdailyspend) - **Path**: `usage.timeseries.meta.avgDailySpend` - **Type**: `float` Average spend per day. An estimate that drifts between calls. ##### [projectedSpend](#response-usage-timeseries-meta-projectedspend) - **Path**: `usage.timeseries.meta.projectedSpend` - **Type**: `float` Projected 30-day spend extrapolated from the window. An estimate that drifts between calls. ##### [avgInferenceTime](#response-usage-timeseries-meta-avginferencetime) - **Path**: `usage.timeseries.meta.avgInferenceTime` - **Type**: `float` Average inference time in seconds. ##### [p50InferenceTime](#response-usage-timeseries-meta-p50inferencetime) - **Path**: `usage.timeseries.meta.p50InferenceTime` - **Type**: `float` Median inference time in seconds. ##### [p90InferenceTime](#response-usage-timeseries-meta-p90inferencetime) - **Path**: `usage.timeseries.meta.p90InferenceTime` - **Type**: `float` 90th-percentile inference time in seconds. ##### [p99InferenceTime](#response-usage-timeseries-meta-p99inferencetime) - **Path**: `usage.timeseries.meta.p99InferenceTime` - **Type**: `float` 99th-percentile inference time in seconds. #### [model](#response-usage-model) - **Path**: `usage.model` - **Type**: `object (18 properties)` Per-model breakdown (from groupBy model). ##### [data](#response-usage-model-data) - **Path**: `usage.model.data` - **Type**: `array of objects (7 properties)` - **Required**: true Rows for this breakdown. ##### [date](#response-usage-model-data-date) - **Path**: `usage.model.data.date` - **Type**: `string` - **Format**: `date` Day bucket. ##### [model](#response-usage-model-data-model) - **Path**: `usage.model.data.model` - **Type**: `string` Model AIR. ##### [modelName](#response-usage-model-data-modelname) - **Path**: `usage.model.data.modelName` - **Type**: `string` Human-friendly model name. Falls back to the AIR when none exists. ##### [apiKey](#response-usage-model-data-apikey) - **Path**: `usage.model.data.apiKey` - **Type**: `string` API key UUID. ##### [avgInferenceTime](#response-usage-model-data-avginferencetime) - **Path**: `usage.model.data.avgInferenceTime` - **Type**: `float | null` Average inference time in seconds, or null when there were no inferences. ##### [p90InferenceTime](#response-usage-model-data-p90inferencetime) - **Path**: `usage.model.data.p90InferenceTime` - **Type**: `float | null` 90th-percentile inference time in seconds, or null when there were no inferences. ##### [p99InferenceTime](#response-usage-model-data-p99inferencetime) - **Path**: `usage.model.data.p99InferenceTime` - **Type**: `float | null` 99th-percentile inference time in seconds, or null when there were no inferences. ##### [meta](#response-usage-model-meta) - **Path**: `usage.model.meta` - **Type**: `object (9 properties)` - **Required**: true Roll-up totals for a breakdown. Which fields are present depends on the operation. ##### [totalRequests](#response-usage-model-meta-totalrequests) - **Path**: `usage.model.meta.totalRequests` - **Type**: `integer` Total requests across the window. ##### [totalResults](#response-usage-model-meta-totalresults) - **Path**: `usage.model.meta.totalResults` - **Type**: `integer` Total results produced across the window. ##### [totalSpend](#response-usage-model-meta-totalspend) - **Path**: `usage.model.meta.totalSpend` - **Type**: `float` Total spend across the window. ##### [avgDailySpend](#response-usage-model-meta-avgdailyspend) - **Path**: `usage.model.meta.avgDailySpend` - **Type**: `float` Average spend per day. An estimate that drifts between calls. ##### [projectedSpend](#response-usage-model-meta-projectedspend) - **Path**: `usage.model.meta.projectedSpend` - **Type**: `float` Projected 30-day spend extrapolated from the window. An estimate that drifts between calls. ##### [avgInferenceTime](#response-usage-model-meta-avginferencetime) - **Path**: `usage.model.meta.avgInferenceTime` - **Type**: `float` Average inference time in seconds. ##### [p50InferenceTime](#response-usage-model-meta-p50inferencetime) - **Path**: `usage.model.meta.p50InferenceTime` - **Type**: `float` Median inference time in seconds. ##### [p90InferenceTime](#response-usage-model-meta-p90inferencetime) - **Path**: `usage.model.meta.p90InferenceTime` - **Type**: `float` 90th-percentile inference time in seconds. ##### [p99InferenceTime](#response-usage-model-meta-p99inferencetime) - **Path**: `usage.model.meta.p99InferenceTime` - **Type**: `float` 99th-percentile inference time in seconds. #### [apiKey](#response-usage-apikey) - **Path**: `usage.apiKey` - **Type**: `object (18 properties)` Per-key breakdown (from groupBy apiKey). ##### [data](#response-usage-apikey-data) - **Path**: `usage.apiKey.data` - **Type**: `array of objects (7 properties)` - **Required**: true Rows for this breakdown. ##### [date](#response-usage-apikey-data-date) - **Path**: `usage.apiKey.data.date` - **Type**: `string` - **Format**: `date` Day bucket. ##### [model](#response-usage-apikey-data-model) - **Path**: `usage.apiKey.data.model` - **Type**: `string` Model AIR. ##### [modelName](#response-usage-apikey-data-modelname) - **Path**: `usage.apiKey.data.modelName` - **Type**: `string` Human-friendly model name. Falls back to the AIR when none exists. ##### [apiKey](#response-usage-apikey-data-apikey) - **Path**: `usage.apiKey.data.apiKey` - **Type**: `string` API key UUID. ##### [avgInferenceTime](#response-usage-apikey-data-avginferencetime) - **Path**: `usage.apiKey.data.avgInferenceTime` - **Type**: `float | null` Average inference time in seconds, or null when there were no inferences. ##### [p90InferenceTime](#response-usage-apikey-data-p90inferencetime) - **Path**: `usage.apiKey.data.p90InferenceTime` - **Type**: `float | null` 90th-percentile inference time in seconds, or null when there were no inferences. ##### [p99InferenceTime](#response-usage-apikey-data-p99inferencetime) - **Path**: `usage.apiKey.data.p99InferenceTime` - **Type**: `float | null` 99th-percentile inference time in seconds, or null when there were no inferences. ##### [meta](#response-usage-apikey-meta) - **Path**: `usage.apiKey.meta` - **Type**: `object (9 properties)` - **Required**: true Roll-up totals for a breakdown. Which fields are present depends on the operation. ##### [totalRequests](#response-usage-apikey-meta-totalrequests) - **Path**: `usage.apiKey.meta.totalRequests` - **Type**: `integer` Total requests across the window. ##### [totalResults](#response-usage-apikey-meta-totalresults) - **Path**: `usage.apiKey.meta.totalResults` - **Type**: `integer` Total results produced across the window. ##### [totalSpend](#response-usage-apikey-meta-totalspend) - **Path**: `usage.apiKey.meta.totalSpend` - **Type**: `float` Total spend across the window. ##### [avgDailySpend](#response-usage-apikey-meta-avgdailyspend) - **Path**: `usage.apiKey.meta.avgDailySpend` - **Type**: `float` Average spend per day. An estimate that drifts between calls. ##### [projectedSpend](#response-usage-apikey-meta-projectedspend) - **Path**: `usage.apiKey.meta.projectedSpend` - **Type**: `float` Projected 30-day spend extrapolated from the window. An estimate that drifts between calls. ##### [avgInferenceTime](#response-usage-apikey-meta-avginferencetime) - **Path**: `usage.apiKey.meta.avgInferenceTime` - **Type**: `float` Average inference time in seconds. ##### [p50InferenceTime](#response-usage-apikey-meta-p50inferencetime) - **Path**: `usage.apiKey.meta.p50InferenceTime` - **Type**: `float` Median inference time in seconds. ##### [p90InferenceTime](#response-usage-apikey-meta-p90inferencetime) - **Path**: `usage.apiKey.meta.p90InferenceTime` - **Type**: `float` 90th-percentile inference time in seconds. ##### [p99InferenceTime](#response-usage-apikey-meta-p99inferencetime) - **Path**: `usage.apiKey.meta.p99InferenceTime` - **Type**: `float` 99th-percentile inference time in seconds. ## getUsageErrors Reliability, sliced the same way `getUsageActivity` slices spend. Each row splits failures into **client errors** (`4xx`) and **server errors** (`5xx`), and the `meta` roll-up carries the window's `totalErrors` and an `errorRate` as a percentage. Group by `model` or `apiKey` to see **which one is failing**. ### Request **TypeScript**: ```typescript import { createClient } from '@runware/sdk' const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY }) await client.connect() const result = await client.accountManagement({ operation: 'getUsageErrors', startDate: '2026-07-01', endDate: '2026-07-06', groupBy: [ 'date', 'model' ] }) ``` **Python**: ```python import asyncio import os from runware import Runware async def main(): async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client: result = await client.account_management({ "operation": "getUsageErrors", "startDate": "2026-07-01", "endDate": "2026-07-06", "groupBy": [ "date", "model" ] }) asyncio.run(main()) ``` **cURL**: ```bash curl https://api.runware.ai/v1 \ -H "Authorization: Bearer $RUNWARE_API_KEY" \ -H "Content-Type: application/json" \ -d '[ { "taskType": "accountManagement", "taskUUID": "cb460b4c-0d63-4fe2-9694-2115b2ce2161", "operation": "getUsageErrors", "startDate": "2026-07-01", "endDate": "2026-07-06", "groupBy": [ "date", "model" ] } ]' ``` **CLI**: ```bash runware account getUsageErrors ``` **JSON**: ```json { "taskType": "accountManagement", "taskUUID": "cb460b4c-0d63-4fe2-9694-2115b2ce2161", "operation": "getUsageErrors", "startDate": "2026-07-01", "endDate": "2026-07-06", "groupBy": [ "date", "model" ] } ``` --- ### [taskType](#request-tasktype) - **Type**: `string` - **Required**: true - **Value**: `accountManagement` Identifier for the type of task being performed ### [taskUUID](#request-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task. ### [operation](#request-operation) - **Type**: `string` - **Required**: true - **Value**: `getUsageErrors` The specific account management operation to perform. ### [startDate](#request-startdate) - **Type**: `string` - **Format**: `date` Start of the usage window (inclusive). ### [endDate](#request-enddate) - **Type**: `string` - **Format**: `date` End of the usage window (inclusive). Must be on or after startDate, and the span must not exceed 30 days. ### [models](#request-models) - **Type**: `array of strings` - **Max items**: `100` Restrict usage to these model AIRs. Defaults to all models. ### [apiKeys](#request-apikeys) - **Type**: `array of strings` - **Max items**: `100` Restrict usage to these API key UUIDs. Defaults to all keys. ### [groupBy](#request-groupby) - **Type**: `array of strings` - **Default**: `date,model` Breakdowns to return. ### [timezone](#request-timezone) - **Type**: `string` - **Default**: `UTC` IANA timezone name used for day-bucketing. ### Response ```json { "data": [ { "taskType": "accountManagement", "taskUUID": "cb460b4c-0d63-4fe2-9694-2115b2ce2161", "operation": "getUsageErrors", "startDate": "2026-07-01", "endDate": "2026-07-06", "usage": { "timeseries": { "data": [{ "date": "2026-07-03", "clientErrors": 126, "serverErrors": 0 }], "meta": { "totalErrors": 128, "errorRate": 78.05 } }, "model": { "data": [{ "date": "2026-07-03", "model": "bytedance:video-upscaler@standard", "modelName": "Bytedance Video Upscaler", "clientErrors": 126, "serverErrors": 0 }], "meta": { "totalErrors": 128, "errorRate": 78.05 } } } } ] } ``` --- ### [taskType](#response-tasktype) - **Type**: `string` - **Required**: true - **Value**: `accountManagement` Identifier for the type of task this response belongs to. ### [taskUUID](#response-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier echoed from the original request, used to match async responses to their tasks. ### [operation](#response-operation) - **Type**: `string` - **Required**: true - **Value**: `getUsageErrors` The account management operation that produced this response. ### [startDate](#response-startdate) - **Type**: `string` - **Format**: `date` Start of the returned window (inclusive). ### [endDate](#response-enddate) - **Type**: `string` - **Format**: `date` End of the returned window (inclusive). ### [usage](#response-usage) - **Path**: `usage.today` - **Type**: `object (37 properties)` Account usage statistics. #### [today](#response-usage-today) - **Path**: `usage.today` - **Type**: `object` Usage stats for today. #### [last7Days](#response-usage-last7days) - **Path**: `usage.last7Days` - **Type**: `object` Usage stats for the last 7 days. #### [last30Days](#response-usage-last30days) - **Path**: `usage.last30Days` - **Type**: `object` Usage stats for the last 30 days. #### [total](#response-usage-total) - **Path**: `usage.total` - **Type**: `object` Total lifetime usage stats. #### [timeseries](#response-usage-timeseries) - **Path**: `usage.timeseries` - **Type**: `object (10 properties)` Per-day breakdown (from groupBy date). ##### [data](#response-usage-timeseries-data) - **Path**: `usage.timeseries.data` - **Type**: `array of objects (6 properties)` - **Required**: true Rows for this breakdown. ##### [date](#response-usage-timeseries-data-date) - **Path**: `usage.timeseries.data.date` - **Type**: `string` - **Format**: `date` Day bucket. ##### [model](#response-usage-timeseries-data-model) - **Path**: `usage.timeseries.data.model` - **Type**: `string` Model AIR. ##### [modelName](#response-usage-timeseries-data-modelname) - **Path**: `usage.timeseries.data.modelName` - **Type**: `string` Human-friendly model name. Falls back to the AIR when none exists. ##### [apiKey](#response-usage-timeseries-data-apikey) - **Path**: `usage.timeseries.data.apiKey` - **Type**: `string` API key UUID. ##### [clientErrors](#response-usage-timeseries-data-clienterrors) - **Path**: `usage.timeseries.data.clientErrors` - **Type**: `integer` Number of 4xx (client) errors in this bucket. ##### [serverErrors](#response-usage-timeseries-data-servererrors) - **Path**: `usage.timeseries.data.serverErrors` - **Type**: `integer` Number of 5xx (server) errors in this bucket. ##### [meta](#response-usage-timeseries-meta) - **Path**: `usage.timeseries.meta` - **Type**: `object (2 properties)` - **Required**: true Roll-up totals for a breakdown. Which fields are present depends on the operation. ##### [totalErrors](#response-usage-timeseries-meta-totalerrors) - **Path**: `usage.timeseries.meta.totalErrors` - **Type**: `integer` Total errors across the window. ##### [errorRate](#response-usage-timeseries-meta-errorrate) - **Path**: `usage.timeseries.meta.errorRate` - **Type**: `float` Error rate across the window, as a percentage. #### [model](#response-usage-model) - **Path**: `usage.model` - **Type**: `object (10 properties)` Per-model breakdown (from groupBy model). ##### [data](#response-usage-model-data) - **Path**: `usage.model.data` - **Type**: `array of objects (6 properties)` - **Required**: true Rows for this breakdown. ##### [date](#response-usage-model-data-date) - **Path**: `usage.model.data.date` - **Type**: `string` - **Format**: `date` Day bucket. ##### [model](#response-usage-model-data-model) - **Path**: `usage.model.data.model` - **Type**: `string` Model AIR. ##### [modelName](#response-usage-model-data-modelname) - **Path**: `usage.model.data.modelName` - **Type**: `string` Human-friendly model name. Falls back to the AIR when none exists. ##### [apiKey](#response-usage-model-data-apikey) - **Path**: `usage.model.data.apiKey` - **Type**: `string` API key UUID. ##### [clientErrors](#response-usage-model-data-clienterrors) - **Path**: `usage.model.data.clientErrors` - **Type**: `integer` Number of 4xx (client) errors in this bucket. ##### [serverErrors](#response-usage-model-data-servererrors) - **Path**: `usage.model.data.serverErrors` - **Type**: `integer` Number of 5xx (server) errors in this bucket. ##### [meta](#response-usage-model-meta) - **Path**: `usage.model.meta` - **Type**: `object (2 properties)` - **Required**: true Roll-up totals for a breakdown. Which fields are present depends on the operation. ##### [totalErrors](#response-usage-model-meta-totalerrors) - **Path**: `usage.model.meta.totalErrors` - **Type**: `integer` Total errors across the window. ##### [errorRate](#response-usage-model-meta-errorrate) - **Path**: `usage.model.meta.errorRate` - **Type**: `float` Error rate across the window, as a percentage. #### [apiKey](#response-usage-apikey) - **Path**: `usage.apiKey` - **Type**: `object (10 properties)` Per-key breakdown (from groupBy apiKey). ##### [data](#response-usage-apikey-data) - **Path**: `usage.apiKey.data` - **Type**: `array of objects (6 properties)` - **Required**: true Rows for this breakdown. ##### [date](#response-usage-apikey-data-date) - **Path**: `usage.apiKey.data.date` - **Type**: `string` - **Format**: `date` Day bucket. ##### [model](#response-usage-apikey-data-model) - **Path**: `usage.apiKey.data.model` - **Type**: `string` Model AIR. ##### [modelName](#response-usage-apikey-data-modelname) - **Path**: `usage.apiKey.data.modelName` - **Type**: `string` Human-friendly model name. Falls back to the AIR when none exists. ##### [apiKey](#response-usage-apikey-data-apikey) - **Path**: `usage.apiKey.data.apiKey` - **Type**: `string` API key UUID. ##### [clientErrors](#response-usage-apikey-data-clienterrors) - **Path**: `usage.apiKey.data.clientErrors` - **Type**: `integer` Number of 4xx (client) errors in this bucket. ##### [serverErrors](#response-usage-apikey-data-servererrors) - **Path**: `usage.apiKey.data.serverErrors` - **Type**: `integer` Number of 5xx (server) errors in this bucket. ##### [meta](#response-usage-apikey-meta) - **Path**: `usage.apiKey.meta` - **Type**: `object (2 properties)` - **Required**: true Roll-up totals for a breakdown. Which fields are present depends on the operation. ##### [totalErrors](#response-usage-apikey-meta-totalerrors) - **Path**: `usage.apiKey.meta.totalErrors` - **Type**: `integer` Total errors across the window. ##### [errorRate](#response-usage-apikey-meta-errorrate) - **Path**: `usage.apiKey.meta.errorRate` - **Type**: `float` Error rate across the window, as a percentage.