LLM Reference
H Company API

Using Holo3.1-35B-A3B on H Company API

Implementation guide · Holo · H Company

ServerlessOpen Source

H Company API exposes Holo3.1-35B-A3B through model ID holo3-1-35b-a3b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-29. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at H Company API and generate an API key.
  2. 2
    Use the H Company API SDK or REST API to call holo3-1-35b-a3b — see the documentation for request format.
  3. 3
    You'll be billed $0.25/1M input, $1.80/1M output tokens. See full pricing.

Code Examples

Install
pip install openai
API key
HAI_API_KEY
Model ID
holo3-1-35b-a3b

Use H Company API model IDs from provider rows, such as holo3-1-35b-a3b or holo3-122b-a10b. These differ from LLMReference display slugs.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["HAI_API_KEY"],
    base_url="https://api.hcompany.ai/v1"
)
response = client.chat.completions.create(
    model="holo3-1-35b-a3b",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing on H Company API

TypePrice (per 1M)
Input tokens$0.25
Output tokens$1.80
Image input$1.00

Capabilities

VisionMultimodalJSON / Tool useStructured Outputs

About Holo3.1-35B-A3B

Holo3.1-35B-A3B is H Company's flagship open-weights 35B (3B active) sparse MoE computer-use VLM released June 1, 2026 under Apache 2.0. Achieves 79.3% on AndroidWorld and >25% improvement on the Holotab harness over Holo3. Supports native function-calling, FP8/NVFP4 quantization for DGX Spark, and local self-hosting.

Model Specs

Released2026-06-01
Parameters35
Context262k
ArchitectureMixture of Experts

Provider

H Company API
H Company API

H Company

Paris, France