Change history: Usage and limits

← Changelog. Entries: 17.

• 2026-11-08 FIX-1108-2: a call to a disabled model now counts once in AI usage statistics
• 2026-11-02 FIX-1102-12: AI call statistics cost excludes calls covered by the quota or a subscription
• 2026-10-27 NEW-1027-5: Exhausted AI quota period in the response
• 2026-10-26 BC-1026-14: Web search uses AI quota
• 2026-10-01 NEW-1001-18: recentCallsDataSince field in GET /v1/ai/usage
• 2026-10-01 BC-1001-27: string parameters no longer accept arrays and objects
• 2026-09-16 NEW-0916-8: Cowork off-peak and quota-relief keys now always arrive
• 2026-08-12 NEW-0812-7: the machine schema now describes the live app, AI and telephony methods
• 2026-08-11 NEW-0811-4: off-peak hours are visible in the Cowork subscription and in the exhausted-quota refusal
• 2026-08-11 FIX-0811-5: the next off-peak hour is counted from the hour boundary, not from the minute of the request
• 2026-08-06 BC-0806-20: quota consumption is reported as percentages only
• 2026-07-11 FIX-0711-3: GET /v1/ai/quota pacing can now be populated by the platform by default (gradual rollout)
• 2026-07-10 NEW-0710-16: AI quota pacing: pacing field in the response and 429 ai_pacing_limited error
• 2026-07-10 FIX-0710-25: pacing.active in GET /v1/ai/quota no longer reports an active limit when the quota is zero
• 2026-07-07 NEW-0707-8: Company AI quota is available via the API
• 2026-07-02 NEW-0702-9: GET /v1/ai/usage returns transcribed audio duration per model
• 2026-06-29 NEW-0629-2: AI quota off-peak hours schedule