Last refreshed 2026-06-29. Next refresh: weekly.
Why use Holo3-122B-A10B on H Company API?
H Company API offers Holo3-122B-A10B with pay-as-you-go pricing at $0.40/1M 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.
Input / 1M
$0.40
Output / 1M
$3.00
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export HAI_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["HAI_API_KEY"],Model ID
holo3-122b-a10bRequest 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="holo3-122b-a10b",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "holo3-122b-a10b", not the LLMReference slug "holo-3-122b-a10b".
- 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 | $0.40 |
| Output tokens | $3.00 |
| Image input | $1.00 |
Capabilities
VisionMultimodalJSON / Tool useStructured Outputs
About Holo3-122B-A10B
Holo3-122B-A10B is H Company's flagship 122B (10B active) sparse MoE computer-use VLM. Released March 31, 2026, available via the H Company API only (no public open weights). Achieves 78.85% on OSWorld-Verified - SOTA at launch. Paid-tier API access at $0.40/$3.00 per 1M input/output tokens.
Get Started
Model Specs
Released2026-03-31
Parameters122
Context66k
ArchitectureMixture of Experts