List models

Served models, limits, pricing, and deprecation dates.

GET /v1/models

Python

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)

200

{
  "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.

data[].id · string

The model ID to pass as model in Chat completions, for example holo4-27b.

data[].name · string

Display name, for example Holo3.1 35B A3B.

data[].description · string

Short description of the model.

data[].context_length · integer

Total context window in tokens.

data[].max_output_length · integer

Hard ceiling on output tokens per request. 8,192 on Holo3 and Holo3.1.

data[].input_modalities · string[]

["text", "image"] for all Holo models.

data[].output_modalities · string[]

["text"] for all Holo models.

data[].supported_features · string[]

Capability flags: reasoning on every model, and tools for native function calling on every model except holo3-122b-a10b.

data[].supported_sampling_parameters · string[]

Accepted sampling fields, for example temperature, top_p, top_k, max_tokens, stop, frequency_penalty, presence_penalty, seed.

data[].pricing · object

Per-token USD rates as decimal strings.

prompt · string

Per input token.

completion · string

Per output token.

input_cache_read · string

Per prompt token served from the cache.

data[].deprecation_date · string | null

Set when the model is scheduled for removal, otherwise null. After removal, requests to the ID fail with model_not_found.

data[].is_active · boolean

Whether the model is currently serving traffic.

data[].is_ready · boolean

Whether the model is ready to accept requests right now.

Python

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)

200

{
  "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
    }
  ]
}