Claude Platform Docs

Analytique

Models
interface BetaAnalyticsArtifactActivity { artifact_type; artifacts_created_count; distinct_user_count; /* 6 more */ }

Artifact-creation activity for one (artifact_type, is_shared) bucket on a given day.

Artifacts form a small finite cube — the canonical MIME type (8 values incl. other) crossed with shared-vs-private — so the response is the full set of non-empty buckets, not a ranked/paginated list. Claude Code and Cowork artifacts report under text/html and are counted from 2026-08-17 onward; earlier days contain claude.ai chat artifacts only. With group_by[]=product / user_id / rbac_group_id each row is further split by the flat group keys and counts are scoped to that cut.

interface BetaAnalyticsChatCoworkUnifiedChatMetrics { connectors_used_count; distinct_artifacts_created_count; distinct_connectors_used_count; /* 9 more */ }

Chat activity recorded while members had Chat and Cowork unified turned on.

interface BetaAnalyticsChatCoworkUnifiedSessionsMetrics { action_count; artifacts_created_count; connectors_used_count; /* 14 more */ }

Cowork session activity recorded while members had Chat and Cowork unified turned on.

interface BetaAnalyticsChatMetrics { connectors_used_count; distinct_artifacts_created_count; distinct_connectors_used_count; /* 9 more */ }

Claude.ai activity metrics for a single user on a given day.

interface BetaAnalyticsClaudeCodeMetrics { core_metrics; tool_actions }

Claude Code activity metrics for a single user on a given day.

type BetaAnalyticsClaudeTagCategory = "dm" | "engaged" | "monitoring" | 2 more
One of the following:
"dm"
"engaged"
"monitoring"
"proactive"
"scheduled"
interface BetaAnalyticsConnectorActivity { chat_metrics; claude_code_metrics; connector_name; /* 14 more */ }

Per-connector activity data for a given day.

interface BetaAnalyticsConnectorChatCoworkUnifiedChatMetrics { distinct_conversation_connector_used_count }

A connector's use in chat conversations recorded while members had Chat and Cowork unified turned on.

distinct_conversation_connector_used_count: number | null

Same measure as chat_metrics.distinct_conversation_connector_used_count, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

interface BetaAnalyticsConnectorChatCoworkUnifiedSessionsMetrics { distinct_session_connector_used_count }

A connector's use in Cowork sessions recorded while members had Chat and Cowork unified turned on.

distinct_session_connector_used_count: number | null

Same measure as cowork_metrics.distinct_session_connector_used_count, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

interface BetaAnalyticsConnectorChatMetrics { distinct_conversation_connector_used_count }

Claude.ai activity metrics for a single connector on a given day.

distinct_conversation_connector_used_count: number | null

Number of distinct conversations in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

interface BetaAnalyticsConnectorClaudeCodeMetrics { distinct_session_connector_used_count }

Claude Code activity metrics for a single connector on a given day.

distinct_session_connector_used_count: number | null

Number of distinct Claude Code sessions in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

interface BetaAnalyticsConnectorCoworkMetrics { distinct_session_connector_used_count }

Cowork activity metrics for a single connector on a given day.

distinct_session_connector_used_count: number | null

Number of distinct Cowork sessions in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

interface BetaAnalyticsConnectorOfficeMetrics { excel; outlook; powerpoint; word }

Office Agent activity metrics for a single connector on a given day, broken out by Office product.

interface BetaAnalyticsConnectorOfficeProductMetrics { distinct_session_connector_used_count }

Office Agent activity metrics for a single connector on a given day within one Office product.

distinct_session_connector_used_count: number | null

Number of distinct Office Agent sessions in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

type BetaAnalyticsContextWindow = "0-200k" | "200k-1M"
One of the following:
"0-200k"
"200k-1M"
interface BetaAnalyticsCoreCodeMetrics { artifacts_created_count; commit_count; distinct_session_count; /* 2 more */ }

Core Claude Code activity metrics for a single user on a given day.

artifacts_created_count: number

Number of artifacts created in Claude Code sessions: an artifact counts once, on the day a session first saves it. Counted from 2026-08-17; 0 on earlier days. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it.

commit_count: number

Number of commits made via Claude Code

distinct_session_count: number | null

Number of distinct Claude Code sessions. On aggregated rows and in date-range mode: summed per-day distinct counts. A session essentially never spans a UTC day, so the sum is in practice the true distinct count.

lines_of_code: BetaAnalyticsLinesOfCode { added_count; removed_count }

Lines of code added and removed via Claude Code.

added_count: number

Lines of code added

removed_count: number

Lines of code removed

pull_request_count: number

Number of pull requests created via Claude Code

interface BetaAnalyticsCostBucketedResult { amount; claude_tag_category; claude_tag_user_id; /* 12 more */ }
interface BetaAnalyticsCostReportTimeBucket { ending_at; results; starting_at }
type BetaAnalyticsCostType = "code_execution" | "tokens" | "web_search"
One of the following:
"code_execution"
"tokens"
"web_search"
interface BetaAnalyticsCostUsersItem { actor; amount; claude_tag_category; /* 15 more */ }
interface BetaAnalyticsCoworkMetrics { action_count; artifacts_created_count; connectors_used_count; /* 14 more */ }

Cowork activity metrics for a single user on a given day.

interface BetaAnalyticsDesignMetrics { distinct_projects_created_count; distinct_projects_used_count; distinct_session_count; message_count }

Claude Design activity metrics for a single user on a given day.

distinct_projects_created_count: number

Number of distinct Claude Design projects created. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it.

distinct_projects_used_count: number | null

Number of distinct Claude Design projects the user worked in. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

distinct_session_count: number | null

Number of distinct Claude Design sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

message_count: number

Number of messages sent in Claude Design sessions

type BetaAnalyticsInferenceGeoFilter = "global" | "not_available" | "us"
One of the following:
"global"
"not_available"
"us"
interface BetaAnalyticsLinesOfCode { added_count; removed_count }

Lines of code added and removed via Claude Code.

added_count: number

Lines of code added

removed_count: number

Lines of code removed

interface BetaAnalyticsOfficeMetrics { excel; outlook; powerpoint; word }

Office Agent activity metrics for a single user on a given day, broken out by Office product.

interface BetaAnalyticsOfficeProductMetrics { connectors_used_count; distinct_connectors_used_count; distinct_session_count; /* 3 more */ }

Office Agent activity metrics for a single user on a given day within one Office product.

connectors_used_count: number

Number of MCP connector invocations

distinct_connectors_used_count: number | null

Number of distinct MCP connectors used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

distinct_session_count: number | null

Number of distinct Office Agent sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

distinct_skills_used_count: number | null

Number of distinct skills used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

message_count: number

Number of messages sent

skills_used_count: number

Number of skill invocations

interface BetaAnalyticsPluginActivity { claude_code_metrics; cowork_metrics; distinct_user_count; /* 9 more */ }

Per-plugin install + invocation activity for a given day.

With group_by[]=user_id / rbac_group_id / product (cowork, claude_code and chat_cowork_unified only on this endpoint) each row is one (plugin, user), (plugin, group), or (plugin, product) cut: the flat user_id / rbac_group_id / product keys carry the cut and the counts are scoped to it.

interface BetaAnalyticsPluginClaudeCodeMetrics { distinct_session_plugin_used_count }

Claude Code activity metrics for a single plugin on a given day.

distinct_session_plugin_used_count: number | null

Number of distinct Claude Code sessions in which the plugin was invoked. Null on aggregated rows where a distinct count cannot be computed.

interface BetaAnalyticsPluginCoworkMetrics { distinct_session_plugin_used_count }

Cowork activity metrics for a single plugin on a given day.

distinct_session_plugin_used_count: number | null

Number of distinct Cowork sessions in which the plugin was invoked. Null on aggregated rows where a distinct count cannot be computed.

type BetaAnalyticsProductFilter = "chat" | "chat_cowork_unified" | "claude-tag" | 5 more

Publicly documented product surfaces. claude-tag is Claude Tag, the Claude product in Slack. chat_cowork_unified is Chat and Cowork unified, Cowork's features inside claude.ai chat: chat and Cowork usage by a member who has it turned on is reported under this value instead of chat or cowork. It is accepted as a filter only on deployments that offer Chat and Cowork unified.

One of the following:
"chat"
"chat_cowork_unified"
"claude-tag"
"claude_code"
"claude_design"
"claude_in_chrome"
"cowork"
"office_agent"
interface BetaAnalyticsProjectActivity { distinct_user_count; message_count; project_id; /* 8 more */ }

Per-project activity data for a given day.

interface BetaAnalyticsScienceMetrics { delegation_count; distinct_session_count; message_count; /* 2 more */ }

Claude Science activity metrics for a single user on a given day.

delegation_count: number

Number of delegations (handoffs to a specialized agent) in Claude Science sessions

distinct_session_count: number | null

Number of distinct Claude Science sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

message_count: number

Number of messages sent in Claude Science sessions

remote_compute_job_count: number

Number of remote compute jobs launched from Claude Science sessions

skills_used_count: number

Total number of skill invocations in Claude Science sessions

interface BetaAnalyticsServerToolUse { web_search_requests }
web_search_requests: number

The number of web search requests made.

interface BetaAnalyticsSingleDayActivitySummary { assigned_seat_count; cowork_daily_active_user_count; cowork_monthly_active_user_count; /* 29 more */ }

Per-day entry in the /summaries response.

interface BetaAnalyticsSkillActivity { chat_metrics; claude_code_metrics; cowork_metrics; /* 15 more */ }

Per-skill activity data for a given day.

interface BetaAnalyticsSkillChatCoworkUnifiedChatMetrics { distinct_conversation_skill_used_count }

A skill's use in chat conversations recorded while members had Chat and Cowork unified turned on.

distinct_conversation_skill_used_count: number | null

Same measure as chat_metrics.distinct_conversation_skill_used_count, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

interface BetaAnalyticsSkillChatCoworkUnifiedSessionsMetrics { distinct_session_skill_used_count }

A skill's use in Cowork sessions recorded while members had Chat and Cowork unified turned on.

distinct_session_skill_used_count: number | null

Same measure as cowork_metrics.distinct_session_skill_used_count, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

interface BetaAnalyticsSkillChatMetrics { distinct_conversation_skill_used_count }

Claude.ai activity metrics for a single skill on a given day.

distinct_conversation_skill_used_count: number | null

Number of distinct conversations in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

interface BetaAnalyticsSkillClaudeCodeMetrics { distinct_session_skill_used_count }

Claude Code activity metrics for a single skill on a given day.

distinct_session_skill_used_count: number | null

Number of distinct Claude Code sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

interface BetaAnalyticsSkillCoworkMetrics { distinct_session_skill_used_count }

Cowork activity metrics for a single skill on a given day.

distinct_session_skill_used_count: number | null

Number of distinct Cowork sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

interface BetaAnalyticsSkillOfficeMetrics { excel; outlook; powerpoint; word }

Office Agent activity metrics for a single skill on a given day, broken out by Office product.

interface BetaAnalyticsSkillOfficeProductMetrics { distinct_session_skill_used_count }

Office Agent activity metrics for a single skill on a given day within one Office product.

distinct_session_skill_used_count: number | null

Number of distinct Office Agent sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.

type BetaAnalyticsTokenType = "cache_creation.ephemeral_1h_input_tokens" | "cache_creation.ephemeral_5m_input_tokens" | "cache_read_input_tokens" | 2 more
One of the following:
"cache_creation.ephemeral_1h_input_tokens"
"cache_creation.ephemeral_5m_input_tokens"
"cache_read_input_tokens"
"output_tokens"
"uncached_input_tokens"
interface BetaAnalyticsToolActionCounts { accepted_count; rejected_count }

Accepted/rejected counts for a single Claude Code tool type.

accepted_count: number

Number of tool proposals accepted

rejected_count: number

Number of tool proposals rejected

interface BetaAnalyticsToolActions { edit_tool; multi_edit_tool; notebook_edit_tool; write_tool }

Per-tool accepted/rejected counts for Claude Code file modification tools.

interface BetaAnalyticsUsageBucketedResult { cache_creation; cache_read_input_tokens; claude_tag_category; /* 12 more */ }
interface BetaAnalyticsUsageReportTimeBucket { ending_at; results; starting_at }
interface BetaAnalyticsUsageUsersItem { actor; cache_creation; cache_read_input_tokens; /* 16 more */ }
interface BetaAnalyticsUser { type: "user"; id; email_address }

A user in the organization, identified by tagged id and email address.

type: "user"

Object type. Always user.

defaultuser
id: string

Tagged user identifier (e.g. user_...)

email_address: string

Email address of the user

interface BetaAnalyticsUserActivity { chat_metrics; claude_code_metrics; cowork_metrics; /* 10 more */ }

Per-user activity data for a given day.

interface BetaAnalyticsUserActor { type: "user_actor"; deleted; email_address; /* 2 more */ }
type: "user_actor"

Actor type. Always "user_actor".

deleted: boolean

True when the account has been deleted, or when the user is no longer a member of the organization or its associated organizations (for example, their membership was removed or they were deprovisioned via your identity provider). email_address stays populated for removed users and is null when the account has been deleted. name follows the rules described on that field. The user_id is still populated for reconciliation.

email_address: string | null

The user's email address, including for users who are no longer members of the organization or its associated organizations. Null when the account has been deleted (check deleted) and for system-minted service accounts, which have no person's mailbox behind them (check name).

name: string | null

The user's full name. Null when the user has not set a name. Returns "Deleted User" when the account itself has been deleted, or when the user is no longer a member of the organization or its associated organizations and the organization has chosen to hide the names of removed users. Otherwise, the name stays populated for removed users. Rows for system-minted service accounts render the service name (for example, "Claude Security" for usage by Anthropic's security-patching service) or null.

user_id: string

Tagged user ID.

AnalytiqueRésumés

Obtenir les résumés d'activité
client.beta.organization.analytics.summaries.list(query, options?): PageCursor<BetaAnalyticsSingleDayActivitySummary>
GET/v1/organizations/analytics/summaries

Obtient les résumés d'activité à l'échelle de l'organisation pour une plage de dates.

AnalytiqueUtilisateurs

Lister l'activité des utilisateurs
client.beta.organization.analytics.users.list(query?, options?): PageCursor<BetaAnalyticsUserActivity>
GET/v1/organizations/analytics/users

Obtenir l'activité par utilisateur pour un jour donné, avec pagination par curseur.

AnalytiqueApplicationsChatProjets

Obtenir l'utilisation des projets de chat
client.beta.organization.analytics.apps.chat.projects.list(query?, options?): PageCursor<BetaAnalyticsProjectActivity>
GET/v1/organizations/analytics/apps/chat/projects

Obtient l'activité par projet pour un jour donné, avec une pagination par curseur.

AnalytiqueConnecteurs

Obtenir l'utilisation des connecteurs
client.beta.organization.analytics.connectors.list(query?, options?): PageCursor<BetaAnalyticsConnectorActivity>
GET/v1/organizations/analytics/connectors

Obtenir l'utilisation par connecteur pour un jour donné, avec pagination par curseur.

AnalytiquePlugins

Obtenir l'utilisation des plugins
client.beta.organization.analytics.plugins.list(query?, options?): PageCursor<BetaAnalyticsPluginActivity>
GET/v1/organizations/analytics/plugins

Obtenir l'utilisation par plugin (installations + invocations) pour un jour donné, avec pagination.

AnalytiqueCompétences

Obtenir l'utilisation des skills
client.beta.organization.analytics.skills.list(query?, options?): PageCursor<BetaAnalyticsSkillActivity>
GET/v1/organizations/analytics/skills

Obtenir l'utilisation par skill pour un jour donné, avec pagination par curseur.

AnalytiqueArtifacts

Obtenir l'activité des artifacts
client.beta.organization.analytics.artifacts.list(query, options?): PageCursor<BetaAnalyticsArtifactActivity>
GET/v1/organizations/analytics/artifacts

Obtenir l'activité de création d'artifacts pour un jour donné, ventilée par type MIME.

AnalytiqueRapport d'utilisation

Obtenir l'utilisation des tokens au fil du temps
client.beta.organization.analytics.usageReport.list(query, options?): PageCursor<BetaAnalyticsUsageReportTimeBucket>
GET/v1/organizations/analytics/usage_report

Obtient l'utilisation des tokens au fil du temps sur une plage de dates.

AnalytiqueRapport d'utilisation par utilisateur

Obtenir l'utilisation des tokens par utilisateur
client.beta.organization.analytics.userUsageReport.list(query, options?): PageCursor<BetaAnalyticsUsageUsersItem>
GET/v1/organizations/analytics/user_usage_report

Obtient l'utilisation des tokens par utilisateur sur une plage de dates.

AnalytiqueRapport de coûts

Obtenir les coûts au fil du temps
client.beta.organization.analytics.costReport.list(query, options?): PageCursor<BetaAnalyticsCostReportTimeBucket>
GET/v1/organizations/analytics/cost_report

Obtient les coûts en USD au fil du temps sur une plage de dates.

AnalytiqueRapport de coûts par utilisateur

Obtenir les coûts par utilisateur
client.beta.organization.analytics.userCostReport.list(query, options?): PageCursor<BetaAnalyticsCostUsersItem>
GET/v1/organizations/analytics/user_cost_report

Obtient les coûts par utilisateur en USD sur une plage de dates.