specification: FinOps Framework
specificationVersion: '1.0'
schema: https://www.finops.org/framework/
provider: Chutes
providerId: chutes
created: '2026-06-21'
modified: '2026-06-21'
reconciled: false
tags:
- AI
- LLM
- Inference
- Serverless
- GPU
- Bittensor
- FinOps
- Cost Management
- FOCUS
description: >-
  FinOps view of Chutes spend. Chutes bills usage-based per-token rates for public
  LLM inference (per model, with some models free/subsidized by Bittensor TAO
  incentives), per-second GPU runtime plus a one-time deployment fee for private
  (dedicated) chutes, and optional fixed monthly budgets (Plus/Pro) that discount
  per-token rates beyond an included quota. Costs fluctuate with Bittensor Subnet
  64 economics, so unit rates are not reconciled here.
notes: >-
  Per-model token rates and GPU hourly rates are snapshots subject to subnet
  economics; verify against the Chutes pricing page during reconciliation.
sources:
- https://chutes.ai/pricing
- https://chutes.ai/docs
- 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: Chutes
serviceCategory: AI and Machine Learning
billingModel:
  pricingCategory: Usage-Based
  billingFrequency: Monthly
  billingCurrency: USD
  chargeCategories:
  - Usage
  - Purchase
  - Adjustment
focusColumns:
  ServiceName: Chutes
  ServiceCategory: AI and Machine Learning
  ProviderName: Chutes
  PublisherName: Chutes
  InvoiceIssuerName: Chutes
  BillingCurrency: USD
  ChargeCategory: Usage
  PricingCategory: Usage-Based
meters:
- name: input_tokens
  description: Tokens sent in chat completion requests, billed per 1M tokens per model.
  unit: tokens
  aggregation: sum
  dimensions:
  - account
  - model
  - api
- name: output_tokens
  description: Tokens generated, billed per 1M tokens per model.
  unit: tokens
  aggregation: sum
  dimensions:
  - account
  - model
  - api
- name: gpu_runtime_seconds
  description: Per-second runtime of private (dedicated) chutes on confidential GPU capacity.
  unit: seconds
  aggregation: sum
  dimensions:
  - account
  - chute
  - gpu_type
- name: deployment_fee
  description: One-time fee charged per private chute deployment (3x the GPU hourly rate).
  unit: deploys
  aggregation: sum
  dimensions:
  - account
  - chute
- name: monthly_budget
  description: Fixed monthly plan budget (Plus/Pro) charged per subscription.
  unit: subscriptions
  aggregation: sum
  dimensions:
  - account
  - plan
principles:
- name: Visibility
  description: Pull Chutes usage and billing data; inspect per-model token burn and per-chute GPU-seconds.
- name: Allocation
  description: Tag API keys and chutes per workload/team; map to internal cost centers.
- name: Optimization
  description: Route eligible work to free/subsidized models; pick smaller open-source models when sufficient; rely on idle auto-shutdown for private chutes; use Plus/Pro budgets for predictable spend.
- name: Accountability
  description: Assign owners per chute/key; review token and GPU-second spend monthly against budget.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com