Admin - Claude API Reference

AdminOrganizations

Get Current Organization

client.admin.organizations.me(?): Organization { id, name, type }

GET/v1/organizations/me

ModelsExpand Collapse

Organization { id, name, type }

id: string

ID of the Organization.

name: string

Name of the Organization.

type: "organization"

Object type.

For Organizations, this is always "organization".

AdminInvites

Create Invite

client.admin.invites.create(, ?): Invite { id, email, expires_at, 4 more }

POST/v1/organizations/invites

Get Invite

client.admin.invites.retrieve(, ?): Invite { id, email, expires_at, 4 more }

GET/v1/organizations/invites/{invite_id}

List Invites

client.admin.invites.list(?, ?): Page<Invite { id, email, expires_at, 4 more } >

GET/v1/organizations/invites

Delete Invite

client.admin.invites.delete(, ?): InviteDeleteResponse { id, type }

DELETE/v1/organizations/invites/{invite_id}

ModelsExpand Collapse

Invite { id, email, expires_at, 4 more }

id: string

ID of the Invite.

email: string

Email of the User being invited.

expires_at: string

RFC 3339 datetime string indicating when the Invite expires.

invited_at: string

RFC 3339 datetime string indicating when the Invite was created.

role: "user" | "developer" | "billing" | 3 more

Organization role of the User.

Accepts one of the following:

"user"

"developer"

"billing"

"admin"

"claude_code_user"

"managed"

status: "accepted" | "expired" | "deleted" | "pending"

Status of the Invite.

Accepts one of the following:

"accepted"

"expired"

"deleted"

"pending"

type: "invite"

Object type.

For Invites, this is always "invite".

AdminUsers

Get User

client.admin.users.retrieve(, ?): User { id, added_at, email, 3 more }

GET/v1/organizations/users/{user_id}

List Users

client.admin.users.list(?, ?): Page<User { id, added_at, email, 3 more } >

GET/v1/organizations/users

Update User

client.admin.users.update(, , ?): User { id, added_at, email, 3 more }

POST/v1/organizations/users/{user_id}

Remove User

client.admin.users.delete(, ?): UserDeleteResponse { id, type }

DELETE/v1/organizations/users/{user_id}

ModelsExpand Collapse

User { id, added_at, email, 3 more }

id: string

ID of the User.

added_at: string

RFC 3339 datetime string indicating when the User joined the Organization.

email: string

Email of the User.

name: string

Name of the User.

role: "user" | "developer" | "billing" | 3 more

Organization role of the User.

Accepts one of the following:

"user"

"developer"

"billing"

"admin"

"claude_code_user"

"managed"

type: "user"

Object type.

For Users, this is always "user".

AdminWorkspaces

Create Workspace

client.admin.workspaces.create(, ?): Workspace { id, archived_at, created_at, 4 more }

POST/v1/organizations/workspaces

Get Workspace

client.admin.workspaces.retrieve(, ?): Workspace { id, archived_at, created_at, 4 more }

GET/v1/organizations/workspaces/{workspace_id}

List Workspaces

client.admin.workspaces.list(?, ?): Page<Workspace { id, archived_at, created_at, 4 more } >

GET/v1/organizations/workspaces

Update Workspace

client.admin.workspaces.update(, , ?): Workspace { id, archived_at, created_at, 4 more }

POST/v1/organizations/workspaces/{workspace_id}

Archive Workspace

client.admin.workspaces.archive(, ?): Workspace { id, archived_at, created_at, 4 more }

POST/v1/organizations/workspaces/{workspace_id}/archive

AdminWorkspacesMembers

Create Workspace Member

client.admin.workspaces.members.create(, , ?): WorkspaceMember { type, user_id, workspace_id, workspace_role }

POST/v1/organizations/workspaces/{workspace_id}/members

Get Workspace Member

client.admin.workspaces.members.retrieve(, , ?): WorkspaceMember { type, user_id, workspace_id, workspace_role }

GET/v1/organizations/workspaces/{workspace_id}/members/{user_id}

List Workspace Members

client.admin.workspaces.members.list(, ?, ?): Page<WorkspaceMember { type, user_id, workspace_id, workspace_role } >

GET/v1/organizations/workspaces/{workspace_id}/members

Update Workspace Member

client.admin.workspaces.members.update(, , ?): WorkspaceMember { type, user_id, workspace_id, workspace_role }

POST/v1/organizations/workspaces/{workspace_id}/members/{user_id}

Delete Workspace Member

client.admin.workspaces.members.delete(, , ?): MemberDeleteResponse { type, user_id, workspace_id }

DELETE/v1/organizations/workspaces/{workspace_id}/members/{user_id}

ModelsExpand Collapse

WorkspaceMember { type, user_id, workspace_id, workspace_role }

type: "workspace_member"

Object type.

For Workspace Members, this is always "workspace_member".

user_id: string

ID of the User.

workspace_id: string

ID of the Workspace.

workspace_role: "workspace_user" | "workspace_developer" | "workspace_admin" | "workspace_billing"

Role of the Workspace Member.

Accepts one of the following:

"workspace_user"

"workspace_developer"

"workspace_admin"

"workspace_billing"

AdminAPI Keys

Get API Key

client.admin.apiKeys.retrieve(, ?): APIKey { id, created_at, created_by, 5 more }

GET/v1/organizations/api_keys/{api_key_id}

List API Keys

client.admin.apiKeys.list(?, ?): Page<APIKey { id, created_at, created_by, 5 more } >

GET/v1/organizations/api_keys

Update API Key

client.admin.apiKeys.update(, , ?): APIKey { id, created_at, created_by, 5 more }

POST/v1/organizations/api_keys/{api_key_id}

AdminUsage Report

Get Messages Usage Report

client.admin.usageReport.retrieveMessages(, ?): MessagesUsageReport { data, has_more, next_page }

GET/v1/organizations/usage_report/messages

Get Claude Code Usage Report

client.admin.usageReport.retrieveClaudeCode(, ?): ClaudeCodeUsageReport { data, has_more, next_page }

GET/v1/organizations/usage_report/claude_code

ModelsExpand Collapse

ClaudeCodeUsageReport { data, has_more, next_page }

data: Array<Data>

List of Claude Code usage records for the requested date.

actor: UserActor { email_address, type } | APIActor { api_key_name, type }

The user or API key that performed the Claude Code actions.

Accepts one of the following:

UserActor { email_address, type }

email_address: string

Email address of the user who performed Claude Code actions.

type: "user_actor"

APIActor { api_key_name, type }

api_key_name: string

Name of the API key used to perform Claude Code actions.

type: "api_actor"

core_metrics: CoreMetrics { commits_by_claude_code, lines_of_code, num_sessions, pull_requests_by_claude_code }

Core productivity metrics measuring Claude Code usage and impact.

commits_by_claude_code: number

Number of git commits created through Claude Code's commit functionality.

lines_of_code: LinesOfCode { added, removed }

Statistics on code changes made through Claude Code.

added: number

Total number of lines of code added across all files by Claude Code.

removed: number

Total number of lines of code removed across all files by Claude Code.

num_sessions: number

Number of distinct Claude Code sessions initiated by this actor.

pull_requests_by_claude_code: number

Number of pull requests created through Claude Code's PR functionality.

customer_type: "api" | "subscription"

Type of customer account (api for API customers, subscription for Pro/Team customers).

Accepts one of the following:

"api"

"subscription"

date: string

UTC date for the usage metrics in YYYY-MM-DD format.

model_breakdown: Array<ModelBreakdown>

Token usage and cost breakdown by AI model used.

estimated_cost: EstimatedCost { amount, currency }

Estimated cost for using this model

amount: number

Estimated cost amount in minor currency units (e.g., cents for USD).

currency: string

Currency code for the estimated cost (e.g., 'USD').

model: string

Name of the AI model used for Claude Code interactions.

tokens: Tokens { cache_creation, cache_read, input, output }

Token usage breakdown for this model

cache_creation: number

Number of cache creation tokens consumed by this model.

cache_read: number

Number of cache read tokens consumed by this model.

input: number

Number of input tokens consumed by this model.

output: number

Number of output tokens generated by this model.

organization_id: string

ID of the organization that owns the Claude Code usage.

terminal_type: string

Type of terminal or environment where Claude Code was used.

tool_actions: Record<string, ToolActions>

Breakdown of tool action acceptance and rejection rates by tool type.

accepted: number

Number of tool action proposals that the user accepted.

rejected: number

Number of tool action proposals that the user rejected.

subscription_type?: "enterprise" | "team" | null

Subscription tier for subscription customers. null for API customers.

Accepts one of the following:

"enterprise"

"team"

has_more: boolean

True if there are more records available beyond the current page.

next_page: string | null

Opaque cursor token for fetching the next page of results, or null if no more pages are available.

MessagesUsageReport { data, has_more, next_page }

data: Array<Data>

ending_at: string

End of the time bucket (exclusive) in RFC 3339 format.

results: Array<Result>

List of usage items for this time bucket. There may be multiple items if one or more group_by[] parameters are specified.

api_key_id: string | null

ID of the API key used. null if not grouping by API key or for usage in the Anthropic Console.

cache_creation: CacheCreation { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

The number of input tokens for cache creation.

ephemeral_1h_input_tokens: number

The number of input tokens used to create the 1 hour cache entry.

ephemeral_5m_input_tokens: number

The number of input tokens used to create the 5 minute cache entry.

cache_read_input_tokens: number

The number of input tokens read from the cache.

context_window: "0-200k" | "200k-1M" | null

Context window used. null if not grouping by context window.

Accepts one of the following:

"0-200k"

"200k-1M"

inference_geo: string | null

Inference geo used matching requests' inference_geo parameter if set, otherwise the workspace's default_inference_geo. For models that do not support specifying inference_geo the value is "not_available". Always null if not grouping by inference geo.

model: string | null

Model used. null if not grouping by model.

output_tokens: number

The number of output tokens generated.

server_tool_use: ServerToolUse { web_search_requests }

Server-side tool usage metrics.

web_search_requests: number

The number of web search requests made.

service_tier: "standard" | "batch" | "priority" | 3 more | null

Service tier used. null if not grouping by service tier.

Accepts one of the following:

"standard"

"batch"

"priority"

"priority_on_demand"

"flex"

"flex_discount"

speed: "standard" | "fast" | null

Speed of the usage (research preview). null if not grouping by speed. Only returned when the fast-mode-2026-02-01 beta header is provided.

Accepts one of the following:

"standard"

"fast"

uncached_input_tokens: number

The number of uncached input tokens processed.

workspace_id: string | null

ID of the Workspace used. null if not grouping by workspace or for the default workspace.

starting_at: string

Start of the time bucket (inclusive) in RFC 3339 format.

has_more: boolean

Indicates if there are more results.

next_page: string | null

Token to provide in as page in the subsequent request to retrieve the next page of data.

AdminCost Report

Get Cost Report

client.admin.costReport.retrieve(, ?): CostReport { data, has_more, next_page }

GET/v1/organizations/cost_report

ModelsExpand Collapse

CostReport { data, has_more, next_page }

data: Array<Data>

ending_at: string

End of the time bucket (exclusive) in RFC 3339 format.

results: Array<Result>

List of cost items for this time bucket. There may be multiple items if one or more group_by[] parameters are specified.

amount: string

Cost amount in lowest currency units (e.g. cents) as a decimal string. For example, "123.45" in "USD" represents $1.23.

context_window: "0-200k" | "200k-1M" | null

Input context window used. null if not grouping by description or for non-token costs.

Accepts one of the following:

"0-200k"

"200k-1M"

cost_type: "tokens" | "web_search" | "code_execution" | null

Type of cost. null if not grouping by description.

Accepts one of the following:

"tokens"

"web_search"

"code_execution"

currency: string

Currency code for the cost amount. Currently always "USD".

description: string | null

Description of the cost item. null if not grouping by description.

inference_geo: string | null

Inference geo used matching requests' inference_geo parameter if set, otherwise the workspace's default_inference_geo. For models that do not support specifying inference_geo the value is "not_available". Always null if not grouping by inference geo.

model: string | null

Model name used. null if not grouping by description or for non-token costs.

service_tier: "standard" | "batch" | null

Service tier used. null if not grouping by description or for non-token costs.

Accepts one of the following:

"standard"

"batch"

speed: "standard" | "fast" | null

Speed used (research preview). null if not grouping by speed, or for non-token costs. Only returned when the fast-mode-2026-02-01 beta header is provided.

Accepts one of the following:

"standard"

"fast"

token_type: "uncached_input_tokens" | "output_tokens" | "cache_read_input_tokens" | 2 more | null

Type of token. null if not grouping by description or for non-token costs.

Accepts one of the following:

"uncached_input_tokens"

"output_tokens"

"cache_read_input_tokens"

"cache_creation.ephemeral_1h_input_tokens"

"cache_creation.ephemeral_5m_input_tokens"

workspace_id: string | null

ID of the Workspace this cost is associated with. null if not grouping by workspace or for the default workspace.

starting_at: string

Start of the time bucket (inclusive) in RFC 3339 format.

has_more: boolean

Indicates if there are more results.

next_page: string | null

Token to provide in as page in the subsequent request to retrieve the next page of data.