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

Models

The full catalog behind one key, frontier and open weight.

One key reaches every model in the catalog: frontier models and open-weight models, listed with live pricing at allocate.network/models and served through the Gateway.

Listing models

curl https://api.allocate.network/v1/models \
  -H "Authorization: Bearer $ALLOCATE_API_KEY"

Each entry carries the model id, context window, and billed prices in USD per million tokens. See the API reference for the shape.

Pricing

Usage is billed at the provider's price plus a 7% transaction fee. The prices returned by /v1/models are the billed prices, so what you see is what the Meter records. Provider-reported usage is the billing truth; requests are never re-tokenized to compute your bill.

Pinned by you

Models are pinned per Route and per agent. The platform never silently changes which model serves a surface: the customer or an explicit Route change switches them, and the served model is always reported in the x-allocate-model header.

PreviousRoutesNextKeys
On this pageListing modelsPricingPinned by you