AI inference and GPU cloud
How to use
Hyperbolic.
Testing and serving open text, image, audio, and vision-language models through serverless APIs, or renting GPU capacity for controlled model and compute workloads.
Hyperbolic is a AI compute platform for serverless open-model inference and on-demand GPU marketplace workloads. Testing and serving open text, image, audio, and vision-language models through serverless APIs, or renting GPU capacity for controlled model and compute workloads. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.
AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.
Access & setup
Find, install, and sign in to Hyperbolic
Get into the official Hyperbolic experience with the right account and a setup you understand.
- 01
Start at https://hyperbolic.xyz/ and confirm the domain before entering account or payment information.
- 02
Availability: Hyperbolic is a browser-managed cloud service accessed through OpenAI-compatible and native inference APIs or rented GPU machines over SSH.
- 03
A Hyperbolic account, funded balance and server-side API key or SSH key, a licensed model, workload security controls, evaluation data, cost limits, and an operations plan for rented compute.
- 04
Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.
- 05
Run one low-risk test task before connecting sensitive files, repositories, or workspace data.
- Use official download pages.
- Review permissions during setup.
- Keep installers and applications updated.
First session
Your first useful Hyperbolic session
Learn the interaction loop using a small task with a clear outcome.
- 01
Define the task, data class, quality, latency, modality, context, model license, region, retention, throughput, cost, and rollback requirements.
- 02
Choose serverless inference for bounded API use or a rented GPU for controlled software and model workloads, documenting the different security responsibilities.
- 03
Run a versioned benchmark with server-side credentials, representative inputs, constrained outputs, usage logging, and no automatic consequential actions.
- 04
Review quality, safety, latency, failure, privacy path, license, and total cost, then pin the chosen model or image, monitor it, and retain a tested fallback.
- State the outcome before the background.
- Provide the real source material.
- Review the result before expanding the task.
Quality control
Check the quality of Hyperbolic output
Establish that a model's output is reliable enough for the job you are handing it.
- 01
Restate the task, the acceptance criteria, and the failure cost before evaluating any response.
- 02
Test with a fixed evaluation set rather than ad-hoc prompts, so changes are measurable across model versions.
- 03
Check determinism and drift: record model version, parameters, and date, because providers update models underneath you.
- 04
Probe the failure modes deliberately — ambiguous inputs, adversarial phrasing, and out-of-scope requests.
- 05
Validate structure as well as content: confirm schemas, types, and required fields survive real inputs.
- Pin and record the model version with every result.
- Evaluate against a fixed set, not one-off prompts.
- Validate output structure before it reaches downstream code.
Privacy & permissions
Use Hyperbolic safely
Understand what leaves your system on every call, and what the provider keeps.
- 01
Classify the data in each request before it is sent to a hosted model.
- 02
Check the provider's retention and training terms for your specific plan, not the marketing page.
- 03
Store API keys in a secret manager, scope them per project, and rotate them on a schedule.
- 04
Strip or tokenise personal and regulated data before it reaches the request body.
- 05
Set rate limits, spend caps, and monitoring so a runaway loop is bounded and visible.
- OpenAI compatibility covers interface shape, not model behavior, moderation, licensing, context, or reliability. Zero-retention serverless claims do not automatically govern software and data placed on a rented GPU. Treat marketplace machines as untrusted infrastructure until verified, use SSH keys and least privilege, encrypt and delete data, pin dependencies and models, control spend, and never expose credentials or management ports.
- Follow your organisation's approved-use policy.
- Never treat fluent output as authorization to act.
Core workflows
Step-by-step ways to use Hyperbolic for the work it does best.
Each workflow is a separate guide with its own steps and review checkpoints.
Choose an open model through a repeatable quality, safety, latency, license, and cost evaluation rather than API compatibility alone.
↗ 02 WorkflowSecure an on-demand Hyperbolic GPU workloadTreat rented GPU compute as a temporary server requiring independent identity, network, software, data, and cost controls.
↗Official references
Check the current product documentation.
Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.