Models and task guides
A model page explains the supported task, input and output formats, relevant limits, model version, and billing units; where a model has specific licensing or usage conditions, those sit alongside the practical details. This page shows the catalog's shape. The catalog lists every model HIPS has published, each with its status, on Models and in GET /v1/models.
Prelaunch
The catalog is the only source of model names, limits and prices. Nothing here is hardcoded, and no model id appears on these pages; samples use the HIPS_MODEL variable.
| Field | What it holds |
|---|---|
| Catalog id | The unversioned id (the alias) and the pinned ids of its versions |
| Display name | The name shown on the page and in GET /v1/models; no version in a display name |
| Family, size, variant | The three tokens of the id, as structured fields so the catalog can be filtered |
| Type and task | The model type and the task key the request is validated against |
| Modality | Inputs accepted (text, image, audio, video) and outputs returned |
| Formats | Input and output formats per modality; for language models, the runtime weight format per pool |
| Limits | Context length, maximum output tokens, images per request, input dimensions, audio or video duration, batch, upload size; set per model in the catalog |
| Version | The current version the alias resolves to; every pinned version with its status, release, deprecation and sunset dates |
| License and usage conditions | License name, the conditions that bind the customer and HIPS, the recorded source |
| Billing unit | The unit charged and the rates per pool and pricing mode; language models show input and output rates separately |
| Current availability | The supply state per pool: available, limited, unavailable, unknown, with its last update; a stale reading becomes unknown |
| Hardware fit | Per pool, the hardware classes the version fits, with engine and format per class |
| Supported features | For language models, each feature of the compatibility matrix with its validated status; unvalidated is shown as unvalidated |
- Field
- Catalog id
- What it holds
- The unversioned id (the alias) and the pinned ids of its versions
- Field
- Display name
- What it holds
- The name shown on the page and in
GET /v1/models; no version in a display name
- Field
- Family, size, variant
- What it holds
- The three tokens of the id, as structured fields so the catalog can be filtered
- Field
- Type and task
- What it holds
- The model type and the task key the request is validated against
- Field
- Modality
- What it holds
- Inputs accepted (text, image, audio, video) and outputs returned
- Field
- Formats
- What it holds
- Input and output formats per modality; for language models, the runtime weight format per pool
- Field
- Limits
- What it holds
- Context length, maximum output tokens, images per request, input dimensions, audio or video duration, batch, upload size; set per model in the catalog
- Field
- Version
- What it holds
- The current version the alias resolves to; every pinned version with its status, release, deprecation and sunset dates
- Field
- License and usage conditions
- What it holds
- License name, the conditions that bind the customer and HIPS, the recorded source
- Field
- Billing unit
- What it holds
- The unit charged and the rates per pool and pricing mode; language models show input and output rates separately
- Field
- Current availability
- What it holds
- The supply state per pool:
available,limited,unavailable,unknown, with its last update; a stale reading becomesunknown
- Field
- Hardware fit
- What it holds
- Per pool, the hardware classes the version fits, with engine and format per class
- Field
- Supported features
- What it holds
- For language models, each feature of the compatibility matrix with its validated status; unvalidated is shown as unvalidated
| Type | Task keys (working) | Public route |
|---|---|---|
language | chat (text in, text out; image inputs where the model is a vision-language model) | OpenAI-compatible routes |
image | image_generation, image_edit | Task API |
audio | transcription, translation, speech | Task API |
video | video_generation | Task API |
specialist | classification, embedding, detection, and further focused tasks as the catalog adds them | Task API |
- Type
language- Task keys (working)
chat(text in, text out; image inputs where the model is a vision-language model)- Public route
- OpenAI-compatible routes
- Type
image- Task keys (working)
image_generation,image_edit- Public route
- Task API
- Type
audio- Task keys (working)
transcription,translation,speech- Public route
- Task API
- Type
video- Task keys (working)
video_generation- Public route
- Task API
- Type
specialist- Task keys (working)
classification,embedding,detection, and further focused tasks as the catalog adds them- Public route
- Task API
A model is offered in a pool only when that pool's engine for its type runs it on at least one hardware class of the pool, as measured. The task list is set per model in the catalog.
A catalog id (<family>-<size>[-<variant>], lowercase) resolves to the current pinned version and moves with releases; a pinned id (<catalog id>-<version>) names one version and does not move. An alias moves with releases. Retirement of a pinned id and its notice period are open Not decided yet; a pinned id with a retirement date carries deprecates_at in GET /v1/models.
No availability before the catalog's listing state says so. No accuracy or benchmark claim without a labeled evaluation set and task-relevant error measures. No cost or performance comparison without measured representative workloads with the comparison, model, hardware, configuration and date stated.
Related sheets
- Sheet
- 06 of 13
- Updated
- 2026-10-21
- Status
- Preview