specification: FinOps Framework
specificationVersion: '1.0'
schema: https://www.finops.org/framework/
provider: Requesty
providerId: requesty
created: '2026-06-20'
modified: '2026-06-20'
reconciled: true
tags:
- AI
- LLM
- Routing
- Gateway
- Observability
- FinOps
- Cost Management
- FOCUS
description: >-
  FinOps view of Requesty gateway spend. Requesty bills usage-based on the
  underlying routed model's base token rates plus a 5% routing markup, with a
  Free tier capped at 200 requests/day on free models. Every request returns a
  Requesty USD `cost` field, and per-key and organization-level usage/spend
  reporting supports allocation and budgeting. Caching and fallbacks reduce
  effective spend; BYOK shifts base model cost to the customer's own provider
  accounts while Requesty applies its routing fee.
notes: >-
  The 5% markup and Free-tier cap are as published on the Requesty pricing
  page; per-model base rates change frequently and should be verified against
  the Requesty models page during reconciliation.
sources:
- https://www.requesty.ai/pricing
- https://docs.requesty.ai
- https://focus.finops.org/focus-specification/v1-3/
alignedWith:
  framework: FinOps Foundation Framework
  frameworkUrl: https://www.finops.org/framework/
  dataSpec: FOCUS
  dataSpecVersion: '1.3'
  dataSpecUrl: https://focus.finops.org/focus-specification/v1-3/
publisherName: Requesty
serviceCategory: AI and Machine Learning
billingModel:
  pricingCategory: Usage-Based
  billingFrequency: Monthly
  billingCurrency: USD
  chargeCategories:
  - Usage
  - Purchase
  - Adjustment
focusColumns:
  ServiceName: Requesty Router
  ServiceCategory: AI and Machine Learning
  ProviderName: Requesty
  PublisherName: Requesty
  InvoiceIssuerName: Requesty
  BillingCurrency: USD
  ChargeCategory: Usage
  PricingCategory: Usage-Based
meters:
- name: input_tokens
  description: Tokens sent in routed chat/embedding requests, billed at the routed model base rate plus 5% markup.
  unit: tokens
  aggregation: sum
  dimensions:
  - account
  - api_key
  - model
  - provider
- name: output_tokens
  description: Tokens generated by the routed model, billed at the base rate plus 5% markup.
  unit: tokens
  aggregation: sum
  dimensions:
  - account
  - api_key
  - model
  - provider
- name: routing_markup
  description: 5% markup applied on top of the underlying base model cost for routed traffic.
  unit: usd
  aggregation: sum
  dimensions:
  - account
  - api_key
- name: request_cost
  description: Per-request Requesty USD cost returned in the usage.cost field of each response.
  unit: usd
  aggregation: sum
  dimensions:
  - account
  - api_key
  - model
- name: cached_requests
  description: Requests served from response cache, reducing upstream model spend.
  unit: requests
  aggregation: sum
  dimensions:
  - account
  - api_key
principles:
- name: Visibility
  description: Read the per-request usage.cost field and pull per-key and organization usage reports to inspect spend by model and provider.
- name: Allocation
  description: Tag and label API keys per workload/team and map them to internal cost centers using key-level usage reporting.
- name: Optimization
  description: Enable response caching, use fallbacks to cheaper providers, route lower-stakes work to free or smaller models, and use BYOK to push base cost to existing provider contracts.
- name: Accountability
  description: Assign per-key spending limits and budget caps, assign owners per project/key, and review spend monthly against budget.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com