The HIPS SDK for other supported model types
Go beyond language models with the HIPS SDK
The HIPS SDK will provide the intended path for other supported model types, including image, video, audio, and specialist models such as classifiers. Import your supported model from Hugging Face, then use the SDK to send inputs and work with its results. The guides will explain each task’s request format, usage units, and result handling.
The HIPS SDK will ship in Python, TypeScript and JavaScript, Go, Rust, Java (usable from Kotlin), .NET, PHP and Ruby, released together. Package names and methods are not yet decided Not decided yet.
Note
No SDK is published yet. No install command, package name or method appears here until the package names are decided and every SDK passes the shared conformance suite Not decided yet; then each language gets its page. Swift, Kotlin-native and Dart get a page only if they ship. Until then, open-weight language models work through the OpenAI client, as the Quickstart shows.
The SDK wraps the HIPS task API, the versioned contract for every model type other than open-weight language models: POST /v1/tasks for synchronous work, POST /v1/uploads for task inputs, and the read side of deployments and models. Asynchronous work will go through the job routes (POST /v1/jobs and GET /v1/jobs/{id}), which the API does not serve yet: today they answer 404 route_not_found.
The SDK runs a customer model through its deployment and never imports a model, uploads weights or handles a hub token: the import is the Console's, described on Import and run your model.
For open-weight language models the SDK adds nothing: the OpenAI client is the client, and the SDK's documentation says so rather than wrapping it. A customer who uses both paths holds one key and one base URL; the OpenAI client and the HIPS SDK read the same three environment variables, HIPS_API_KEY, HIPS_BASE_URL and HIPS_MODEL; the base URL is https://ai.hips.com/v1.
- Typed methods per task type with the result shapes the catalog defines.
- An upload helper that sends an input through
POST /v1/uploadsabove an inline threshold and names theupl_id. - An
idempotency-keygenerated per task and job call, so a retry can never double-bill. - Polling of
GET /v1/jobs/{id}with backoff and a wait helper. - Retries on 429 and 503 honoring
Retry-After, and on connection failures before any byte; never on a 400. - The error envelope as typed exceptions by
typeandcode. - The
x-hips-*headers and the streamedhipsobject as typed fields. - The requirement object (pool, pricing mode, region, fallback) as a per-client default and a per-call override; the SDK sends the
hipsbody object and never the headers on the task API.
- No telemetry: nothing is sent that the call does not need.
- No second network destination, except the upload PUT to the address the API returned, always on a HIPS-controlled host over https.
- No stored keys: the key is read from an argument or the environment and never written to a file, a keychain or a cache; it is never logged.
- No caching, no deduplication, no thresholds, no interpretation: a score is returned as sent.
- No model substitution and no weakened requirement: the SDK sends what it was given; the server rejects what it cannot serve.
A language's SDK is released only when it implements the whole specification and passes the whole conformance suite: a language-neutral case file, a mock server for behavior cases, and a smoke test against the hosted API. There are no partial SDKs and no language-only features.
One guide per task follows, each with the request format, the usage unit and the result handling, in that order. Until the languages are decided, the task guides carry the wire shapes of the task API, which every SDK method maps onto.
Related sheets
- Sheet
- 04 of 20
- Updated
- 2026-11-11