Skip to main content

Models

Thinking is on by default. Only holo4-27b has effort levels; reasoning_effort: "none" turns thinking off on every model. Every model takes up to 5 images per request (JPEG, PNG, WebP). Cached input is the part of a prompt served from the prompt cache. Pin a model ID in production: before one is removed, GET /v1/models sets its deprecation_date. Benchmarks and methodology: Holo4, Holo3.1. Holo4 and Holo3.1 also ship as open weights for local inference, including sizes the API does not serve.

Quickstart

1

Get an API key

Generate a key on H Platform and export it.
2

Install the OpenAI client

Only base_url changes from the OpenAI defaults. Skip this step for cURL.
3

Send a screenshot

Paid plans: swap in holo4-27b.Images can be a URL or a base64 data URI. List the models your key can reach with GET /v1/models.

Request options

Beyond model and messages, these are the fields that change Holo’s behavior. The rest are standard OpenAI sampling fields. The full list is in Chat completions.

Rate limits and credits

Free: 10 requests per minute on holo3-1-35b-a3b, no credit card. Paid: all models, higher limits, once you add credits. Credits can take up to 15 minutes to appear. The Inference credits tab of the credit dashboard shows your balance and usage. The balance is checked before a request runs, so a large request on a low balance can overshoot by a few cents. Contact support@hcompany.ai if the overshoot keeps growing. Unused credits may expire one year after purchase and are not refundable by default, subject to regional obligations and the terms of use.

Data retention

The API logs request time, model, and token counts. It does not store prompts or responses: zero data retention by default. H runs its own models, so it never shares inputs or outputs with third parties. H is SOC 2 Type II and ISO 27001 certified. Details are in the privacy policy.

Next