specification: FinOps Framework
specificationVersion: '1.0'
schema: https://www.finops.org/framework/
provider: glhf
providerId: glhf-chat
created: '2026-06-21'
modified: '2026-06-21'
reconciled: false
tags:
- AI
- LLM
- Inference
- Open Source Models
- Hugging Face
- FinOps
- Cost Management
- FOCUS
description: >-
  FinOps view of glhf (glhf.chat) spend. glhf bills on a usage basis for GPU
  resources consumed while running open-source models through its
  OpenAI-compatible API, with no required subscription and no charge for boot
  time. Specific per-token or per-GPU-hour rates are not publicly documented, so
  meters below are modeled from the usage-based description and are not
  reconciled.
notes: >-
  Per-token and per-GPU-hour rates are not published; verify against the glhf
  pricing page and account settings during reconciliation.
sources:
- https://glhf.chat
- https://glhf.chat/pricing
- 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: glhf
serviceCategory: AI and Machine Learning
billingModel:
  pricingCategory: Usage-Based
  billingFrequency: Monthly
  billingCurrency: USD
  chargeCategories:
  - Usage
  - Purchase
  - Adjustment
focusColumns:
  ServiceName: glhf
  ServiceCategory: AI and Machine Learning
  ProviderName: glhf
  PublisherName: glhf
  InvoiceIssuerName: glhf
  BillingCurrency: USD
  ChargeCategory: Usage
  PricingCategory: Usage-Based
meters:
- name: gpu_hours
  description: GPU hours consumed while running models on the auto-scaling scheduler, billed per usage (rate not publicly documented).
  unit: hours
  aggregation: sum
  dimensions:
  - account
  - model
- name: input_tokens
  description: Tokens sent in chat completion requests (rate not publicly documented).
  unit: tokens
  aggregation: sum
  dimensions:
  - account
  - model
- name: output_tokens
  description: Tokens generated in chat completion responses (rate not publicly documented).
  unit: tokens
  aggregation: sum
  dimensions:
  - account
  - model
principles:
- name: Visibility
  description: Pull glhf account usage; inspect GPU and token burn per model.
- name: Allocation
  description: Tag API keys per workload/team; map to internal cost centers.
- name: Optimization
  description: Choose smaller open-source models when sufficient; avoid keeping large models warm unnecessarily since usage drives cost.
- name: Accountability
  description: Assign owners per project/key; review usage monthly against budget.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com