Allocate
Cloud AgentsA fleet that works, in secure sandboxesModelsEvery model behind one keyRecursiveDBWork becomes training signalTrainingYour data becomes your modelMeterEvery token tracked, liveData SecurityIsolated inside your boundary
EnterprisePricing
ChangelogDocsFree toolsGlossary
ModelsSign inTalk to sales
Allocate documentation
QuickstartsYour first inference callUse Allocate from your coding agent
PlatformGatewayRoutesModelsKeysMeter
API referenceCreate a chat completionList models
PlanesPrivate Inference CloudCloudlightCloudheavyLearningAgentsRecursiveDBTraining
Allocate

Regulated cloud inference. An AI model you own and grow, on infrastructure you control.

Product
Cloud AgentsModelsRecursiveDBTrainingMeterData SecurityPricing
Solutions
HealthcareInsuranceFinancial servicesOperationsAgenciesStartupsSouth AfricaGulf region
Resources
ChangelogDocumentationAPI referenceFree toolsGlossarySecurity
Popular models
Gemini 3.5 FlashDeepSeek V4GPT-5.5Qwen 3.5Best open-weight modelsExplore all
Company
EnterpriseAboutCareersContactTalk to sales
© 2026 Allocate. All rights reserved.POPIA ready · security overview

Keys

Per-organization API keys, scoped as narrowly as you need.

Keys are minted and revoked from the Keys page in your dashboard. Every key belongs to your organization and can optionally be scoped to a workspace or a single agent, so one leaked credential never exposes more than its scope.

How keys work

  • Minting and revoking happen in the dashboard, gated on an owner or admin role. Every key row records who created it and shows only a masked display value after creation.
  • The Gateway authenticates against an edge cache of key hashes. The full key is never stored, and the hot path never touches a database.
  • Revocation propagates to the edge; a disabled key stops authenticating everywhere.

Spending caps

Caps attach to scopes, never pools:

  • A key cap is a lifetime spend limit for that key.
  • A workspace cap is a calendar-month limit for everything in the workspace.

When your wallet balance is exhausted, new requests receive a 402 with type insufficient_quota. In-flight streams are never interrupted; only new requests are gated.

Handling keys well

Read keys from the environment, never from source. If you build with a coding agent, install the Allocate skill, which carries the same rule.

PreviousModelsNextMeter
On this pageHow keys workSpending capsHandling keys well