Last refreshed 2026-11-14. Next refresh: weekly.
Why use Holo4-35B-A3B on H Company API?
H Company API offers Holo4-35B-A3B with pay-as-you-go pricing at $0.30/1M input tokens. H Company API is the first-party OpenAI-compatible API for H Company Holo computer-use models, with hosted access to Holo3 and Holo3.1 models for web, desktop, and mobile GUI automation workflows.
Setup recipe
Python + curlpip install openaiexport HAI_API_KEY=...import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["HAI_API_KEY"],holo4-35b-a3bRequest example
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="holo4-35b-a3b",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "holo4-35b-a3b", not the LLMReference slug "holo-4-35b-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.
- The examples expect HAI_API_KEY; rename it only if your application config maps the new variable.
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.30 |
| Output tokens | $2.00 |
Capabilities
About Holo4-35B-A3B
Holo4-35B-A3B is H Company's 35B-parameter (3B active) Mixture-of-Experts vision-language model for computer-use agents, released September 28, 2026 alongside Holo4-27B. Built on Qwen3.6-35B-A3B, it reads screenshots and text and acts by clicking and typing, writing and running its own code, or calling MCP and API tools, across web, desktop and Android. It has a 262,144-token context, thinking that can be switched off, and native function calling. Open weights in BF16, FP8, NVFP4 and GGUF are released under Apache 2.0, and it is served on the H Models API (holo4-35b-a3b).