The provider reference

Know what you can control.
And where the gaps are.

Spend limits differ by provider, product and account. This reference separates the existence of a control from the ability to read or change it through an API.

Documentation snapshot: 19 September 2026. This is the capability research behind SpendAssure, not a list of live integrations. Account entitlements and behaviour must be verified before delivery. No reviewed source establishes a numerical end-to-end overshoot bound.

Initial scope under evaluation

Four products. Different controls.

API spending and enterprise seat products are separate administrative boundaries. A feature on one does not imply the same feature on another.

01

OpenAI API

Documentation reviewed
Usage & cost
Usage and cost endpoints; per-key tracking
Spend cap
Organisation and project caps, monthly only; 429 on reach; slight overshoot possible
Change cap by API
Yes, Admin API
Read cap by API
Yes
Rate controls
Project limits writable (Admin API, Terraform)
Other controls & limits
Model allow and deny lists per project; key management
Control classification

Provider-capped

02

ChatGPT Enterprise

Documentation reviewed
Usage & cost
Cost API, analytics
Spend cap
Workspace budget or overage limit; user, group and workspace limits
Change cap by API
Yes, Spend Controls API
Read cap by API
Yes
Rate controls
Not applicable
Other controls & limits
Users can request increases natively; approval by API is an open question
Control classification

Provider-capped

03

Claude Enterprise

Documentation reviewed
Usage & cost
Analytics API, per user
Spend cap
Monthly per-member limits inherited from organisation, seat-tier or group defaults, or overridden per user
Change cap by API
Per-user overrides only; defaults are configured in claude.ai settings
Read cap by API
Effective member limits, inheritance and period spend
Rate controls
Not applicable
Other controls & limits
Approve or deny increase requests by API; requires usage credits enabled
Control classification

Provider-capped for covered member usage; no API-writable pooled organisation or group cap established

04

Anthropic API (Console)

Documentation reviewed
Usage & cost
Usage in 1-minute, 1-hour and 1-day buckets; cost daily
Spend cap
Workspace spend limit exists
Change cap by API
No, Console only
Read cap by API
No
Rate controls
Read-only by API
Other controls & limits
Disable API key; archive workspace (irreversible, never automated)
Control classification

Provider-capped only as an expiring attestation; otherwise velocity-bounded if all material dimensions qualify, else unbounded

A provider cap is not a guaranteed invoice maximum. Attestations are recorded separately from automatically verified settings and expire after 30 days by default. Rate limits support a Velocity-bounded classification only when every material billable dimension is covered.

Beyond the initial scope

Open questions stay open.

Microsoft Copilot Credits

Organisation and user spending policies are recorded in the source research. API read and write capabilities remain an open question.

Open

Azure OpenAI, Amazon Bedrock, Google Vertex

Outside the first scope. Cloud budgets, quotas and model-service controls require separate verification; no provider-wide cap capability is asserted here.

Out of first scope

Discuss your provider setup

Evidence behind the reference

Go straight to the source.

The review date above is preserved from the product research. Documentation can change. Use these primary sources to check current availability and the permissions required for your account.

New to the terminology? Read the guide to budgets, caps and rate limits.

Put these controls into context.

OpenAI budgets, alerts and spend limits →Anthropic API workspaces vs Claude Enterprise →

Let’s start with your AI estate

Put a plan behind
every AI budget.

Help shape SpendAssure around the spending controls, approvals and reporting your team actually needs.

Talk about early access For finance, FinOps and platform teams.