Skip to content
HIPS
  • Earn with your GPU
  • Pricing
  • Docs
Sign inJoin early access
01Weights, requests, outputs_

Understand how your models and data will be used

A model’s weights, the inputs sent to it, and the outputs it generates are different things. The HIPS platform is being designed to make those distinctions visible before you choose a plan or execution pool.

Join early accessContact HIPS

We are inviting early-access interest while we develop the platform.

  • No executable code from your model’s repository will runSheet 02
  • HIPS never trains on, retains or logs your prompt dataSheet 03
  • HIPS holds content only where you ask it toSheet 03
  1. 02Weights
  2. 03Inputs and outputs
  3. 04Pools
  4. 05Encryption
  5. 06Controls
Sheet01 of 06
  • Your model weightsCustomer-owned model weights will never be used to train other models on any plan.
  • Request inputs and generated outputsHIPS never trains on, retains or logs your prompt data. For anyone, on any plan: no prompt, file, result or response is used to train any model, and none is kept or written to a log.
  • Encryption and runtime accessWe will publish the execution protections and access conditions for each pool before customers deploy workloads to it.

Set out in the legal texts in force from 2026-11-16

  • Terms of Service
  • Privacy Notice
  • Data Processing Agreement
  • Acceptable Use Policy

Your model weights

Customer-owned model weights will never be used to train other models on any plan.

That commitment applies to the weights themselves. It does not change the separate policy for request inputs and generated outputs.

Your model will come to HIPS from a model hub as weight files only. HIPS will run those files on its own inference engines: no executable code from your model’s repository (scripts, libraries or custom operators) will run anywhere in the network, a language model’s chat template will be read as data and rendered only inside the inference engine’s sandbox, and files that would need code to load will be refused when the model is imported.

02Your weights_

Request inputs and generated outputs

HIPS never trains on, retains or logs your prompt data. For anyone, on any plan: no prompt, file, result or response is used to train any model, and none is kept or written to a log. This includes requests processed by customer-owned models.

HIPS holds content only where you ask it to, to deliver what you asked for (batch files for thirty (30) days, task results for seven (7) days, uploads for twenty-four (24) hours, and Knowledge documents, files kept for later use and agents' own definitions and kept disks until you delete them, or thirty (30) days after their storage goes unpaid), keeps a prompt cache only in the GPU memory of its own servers, and on a provider's computer only in the engine's memory once it has given notice of it, re-runs a result to verify it only in memory, leaves it on a provider's computer only in the engine's memory until it is overwritten, and otherwise keeps content only where the law requires (Common Clauses Section 3.14).

The Common Clauses define what this covers: Prompt Data means all the content of a Request and of its response, whatever the interface, the Plan or the pool: Request Data; Batch Files; files uploaded to the Services; the results of task Requests and of jobs; documents added to a Workspace for the Services to search (Knowledge), and the passages the Services find in them; the inputs and the results of tools that HIPS runs for a Request; and anything kept for an agent. The Console will show this before you send work.

03Inputs and outputs, per plan_
04The two pools_

Where computation happens

HIPS will centrally coordinate inference across independently supplied GPUs. For customer-owned models, customers will select between the Community pool and the Certified pool.

The choices must disclose the relevant model-access conditions as well as price and availability. Cross-pool fallback will be off by default and require explicit enablement. It must not override region or data-use rules.

Customer models will run in the Certified pool first. The Community pool will follow later, only for supported ONNX models and only for deployments you opt in. If you opt in, the device owner’s machine will hold your model’s weights while it serves your requests.

Encryption and runtime access

Encryption in transit and at rest is part of the platform requirements. It protects data during transfer and storage, but does not by itself prevent a GPU operator from accessing weights or request data during execution.

We will publish the execution protections and access conditions for each pool before customers deploy workloads to it.

05Transit, rest and run time_

Organization controls

The Business plan is intended to include region selection and single sign-on. The scope of region controls, including how they apply to processing and related data, will be specified before that feature is offered.

06Organization controls_

Early-access information

The contact details you submit to join early access are enrollment information, not inference request data. They require a separate privacy notice explaining how we use them for access updates and how you can withdraw.

Join early accessContact HIPS

Product

  • Inference
  • Models
  • Deploy your model
  • Always-on GPU capacity
  • How it works
  • Use cases
  • Pricing

Developer

  • Docs
  • Quickstart
  • Migrate to HIPS
  • HIPS SDK
  • Batch jobs
  • API reference

Provider

  • Earn with your GPU
  • Register GPU interest
  • Download for Mac
  • Download for Windows
  • Download for Linux

Resource

  • Security and Data
  • Resources
  • llms.txt

Compare

  • OpenRouter alternatives
  • Together AI alternatives
  • Groq alternatives
  • All comparisons

Company

  • About
  • Contact
  • Affiliate program
  • HIPS Payments

Legal

  • Legal
  • Consumer Health Data Privacy Policy
  • Report content
  • Cookie preferences

Support

  • Contact HIPS
  • Looking for payments support?

HIPS. AI inference for builders.

hips.com

Hyperscale Inference Processing Systems OÜ