> ## Documentation Index
> Fetch the complete documentation index at: https://hub.hcompany.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> H Platform has four products: the Agents API (managed computer-use agents, base URL https://agp.eu.hcompany.ai/api/v2 or https://agp.hcompany.ai/api/v2 for the US), the Models API (OpenAI-compatible Holo vision-language models at https://api.hcompany.ai/v1), HoloDesktop CLI (Holo on the user's own desktop), and HoloTab (a free no-code Chrome extension that runs Holo in the user's browser, with recordable routines and schedules).
> Authenticate with a bearer API key from the HAI_API_KEY environment variable. SDKs: `pip install hai-agents` (Python, `from hai_agents import Client`) and `npm install hai-agents` (TypeScript, `import { HaiAgentsClient } from "hai-agents"`). CLI: `hai`.
> Agents do work in a browser or on a desktop; describe the task as an imperative instruction. To run a task quickly, prefer the pre-built agent `h/web-surfer-flash`. Read results from the session's `latest_answer` after it reaches a terminal status.
> Sessions are the unit of work; wait for a terminal status (completed, failed, timed_out, interrupted) before reading the answer. Use webhooks or the `changes` long-poll endpoint to follow progress.

# Models API

> Holo agent models behind an OpenAI-compatible API: which model to pick, tiers, context, pricing, and data retention.

<a href="https://hcompany.ai/newsroom/holo4" className="not-prose mb-8 flex items-center gap-3 rounded-xl border border-zinc-200 bg-white px-4 py-3 no-underline transition-colors hover:border-zinc-400 dark:border-zinc-800 dark:bg-zinc-950 dark:hover:border-zinc-600">
  <span className="pill shrink-0">New</span>
  <span className="flex-1 text-sm text-zinc-700 dark:text-zinc-300"><strong className="font-semibold text-zinc-900 dark:text-zinc-100">Holo4 is here.</strong> One model for screens, code, and tools.</span>
  <span className="hidden shrink-0 text-sm font-medium text-zinc-900 sm:inline dark:text-zinc-100">Read the announcement →</span>
</a>

Holo is a family of agent models. Give Holo4 a toolbox and it clicks and types on a screen, writes and runs code, or calls your APIs and MCP tools, often in the same run. The API is OpenAI-compatible: tools in, `tool_calls` out. [Get an API key](https://platform.hcompany.ai/?product=modelsapi\&source=docs). The free tier needs no credit card.

## Models

| Model | Tier | Best for | Context | Price per 1M tokens (input / cached / output) |
| :- | :- | :- | -: | :- |
| `holo4-35b-a3b` | Paid | **Start here.** Interactive agent loops: low cost and latency | 262,144 | \$0.30 / \$0.03 / \$2.00 |
| `holo4-27b` | Paid | Strongest. Complex multi-step tasks and novel environments | 262,144 | \$0.40 / \$0.04 / \$3.00 |
| `holo3-1-35b-a3b` | Free, 10 requests per minute | Trying Holo at no cost | 65,536 | \$0.25 / \$0.025 / \$1.80 |
| `holo3-122b-a10b` | Paid | Holo3 generation: long tasks with dense reasoning | 65,536 | \$0.40 / \$0.04 / \$3.00 |

* **Architecture.** `holo4-35b-a3b` and `holo3-1-35b-a3b`: MoE, 35B total, 3B active. `holo4-27b`: dense, 27B. `holo3-122b-a10b`: MoE, 122B total, 10B active.
* **Limits.** Up to 5 images per request (JPEG, PNG, WebP) on every model. Holo3 models cap output at 8,192 tokens. Paid tiers get higher rate limits.
* **Agent format.** Every model supports native function calling except `holo3-122b-a10b`, which uses structured outputs. See [Pick an output format](/models-api/build-an-agent/core-concepts#pick-an-output-format).
* **Stable IDs.** Switching is a model ID change. Before a model is removed, `GET /v1/models` sets its [`deprecation_date`](/models-api/list-models) and a notice appears here. Pin an ID in production.

Benchmarks and methodology: [Holo4](https://hcompany.ai/newsroom/holo4), [Holo3.1](https://hcompany.ai/holo3.1). Holo4 and Holo3.1 are also open weights, including smaller sizes the API does not serve: see [Local inference](/models-api/local-inference). To try Holo without code, use [HoloTab](/holotab/introduction).

## 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. See the [privacy policy](https://hcompany.ai/privacy-policy).

## Start building

<CardGroup cols={2}>
  <Card title="Quickstart" icon="bolt" href="/models-api/quickstart">Your first call in a few minutes.</Card>
  <Card title="Function calling" icon="wrench" href="/models-api/build-an-agent/function-calling">The agent loop with `tools`.</Card>
  <Card title="Cookbooks" icon="book-open" href="/models-api/cookbooks/browser-agent">Runnable browser, code, and MCP agents.</Card>
  <Card title="Local inference" icon="microchip" href="/models-api/local-inference">Run the open weights yourself.</Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.