API reference
List models
Served models, limits, pricing, and deprecation dates.
GET
/
v1
/
models
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.hcompany.ai/v1/",
api_key=os.environ["HAI_API_KEY"],
)
models = client.models.list()
for m in models.data:
print(m.id)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.hcompany.ai/v1/",
apiKey: process.env.HAI_API_KEY,
});
const models = await client.models.list();
for (const m of models.data) {
console.log(m.id);
}
curl https://api.hcompany.ai/v1/models \
-H "Authorization: Bearer $HAI_API_KEY"
{
"object": "list",
"data": [
{
"id": "holo3-1-35b-a3b",
"object": "model",
"name": "Holo3.1 35B A3B",
"description": "Holo3.1 35B (3B active) vision-language model optimized for GUI agents and computer use.",
"context_length": 65537,
"max_output_length": 8192,
"input_modalities": ["text", "image"],
"output_modalities": ["text"],
"supported_features": ["reasoning", "tools"],
"supported_sampling_parameters": ["temperature", "top_p", "top_k", "max_tokens", "stop", "frequency_penalty", "presence_penalty", "seed"],
"pricing": {"prompt": "0.00000025", "completion": "0.0000018", "input_cache_read": "0.000000025"},
"is_active": true,
"is_ready": true,
"deprecation_date": null
}
]
}
Response
200 with a list object whose data array contains one object per model. Model cards are on the Quickstart.
The model ID to pass as
model in Chat completions, for example holo4-27b.Capability flags:
reasoning on every model, and tools for native function calling on every model except holo3-122b-a10b.Accepted sampling fields, for example
temperature, top_p, top_k, max_tokens, stop, frequency_penalty, presence_penalty, seed.Per-token USD rates as decimal strings.
Per prompt token served from the cache.
Set when the model is scheduled for removal, otherwise
null. After removal, requests to the ID fail with model_not_found.import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.hcompany.ai/v1/",
api_key=os.environ["HAI_API_KEY"],
)
models = client.models.list()
for m in models.data:
print(m.id)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.hcompany.ai/v1/",
apiKey: process.env.HAI_API_KEY,
});
const models = await client.models.list();
for (const m of models.data) {
console.log(m.id);
}
curl https://api.hcompany.ai/v1/models \
-H "Authorization: Bearer $HAI_API_KEY"
{
"object": "list",
"data": [
{
"id": "holo3-1-35b-a3b",
"object": "model",
"name": "Holo3.1 35B A3B",
"description": "Holo3.1 35B (3B active) vision-language model optimized for GUI agents and computer use.",
"context_length": 65537,
"max_output_length": 8192,
"input_modalities": ["text", "image"],
"output_modalities": ["text"],
"supported_features": ["reasoning", "tools"],
"supported_sampling_parameters": ["temperature", "top_p", "top_k", "max_tokens", "stop", "frequency_penalty", "presence_penalty", "seed"],
"pricing": {"prompt": "0.00000025", "completion": "0.0000018", "input_cache_read": "0.000000025"},
"is_active": true,
"is_ready": true,
"deprecation_date": null
}
]
}
Was this page helpful?
⌘I
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.hcompany.ai/v1/",
api_key=os.environ["HAI_API_KEY"],
)
models = client.models.list()
for m in models.data:
print(m.id)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.hcompany.ai/v1/",
apiKey: process.env.HAI_API_KEY,
});
const models = await client.models.list();
for (const m of models.data) {
console.log(m.id);
}
curl https://api.hcompany.ai/v1/models \
-H "Authorization: Bearer $HAI_API_KEY"
{
"object": "list",
"data": [
{
"id": "holo3-1-35b-a3b",
"object": "model",
"name": "Holo3.1 35B A3B",
"description": "Holo3.1 35B (3B active) vision-language model optimized for GUI agents and computer use.",
"context_length": 65537,
"max_output_length": 8192,
"input_modalities": ["text", "image"],
"output_modalities": ["text"],
"supported_features": ["reasoning", "tools"],
"supported_sampling_parameters": ["temperature", "top_p", "top_k", "max_tokens", "stop", "frequency_penalty", "presence_penalty", "seed"],
"pricing": {"prompt": "0.00000025", "completion": "0.0000018", "input_cache_read": "0.000000025"},
"is_active": true,
"is_ready": true,
"deprecation_date": null
}
]
}