List models

GET /v1/models

Returns the installed chat models with their state, context length, capabilities and facts.

Request

The request does not load a model.

curl

curl https://api.albastov.com/v1/models \
  -H "Authorization: Bearer $ALBASTOV_API_KEY"

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.albastov.com/v1", api_key=os.environ["ALBASTOV_API_KEY"])
for model in client.models.list():
    print(model.id, model.state, model.context_length)

JavaScript

const res = await fetch("https://api.albastov.com/v1/models", {
  headers: { Authorization: `Bearer ${process.env.ALBASTOV_API_KEY}` },
});
if (!res.ok) throw new Error(`${res.status} ${await res.text()}`);
const { data } = await res.json();
for (const model of data) console.log(model.id, model.state, model.context_length);

Response

200, Content-Type: application/json, an OpenAI model list. The example shows one model.

Response

{
  "object": "list",
  "data": [
    {
      "id": "qwen3.8-27b",
      "object": "model",
      "created": 1793304723,
      "loaded": true,
      "state": "loaded",
      "context_length": 150000,
      "capabilities": {"parallel": true, "thinking": true, "vision": false, "max_parallel": 64},
      "facts": {
        "name": "Qwen3.8 27B",
        "params": "27B",
        "quantization": "W4A16 AutoRound",
        "bits": 4,
        "size": "about 14 GB",
        "context_tokens": 150000,
        "speed": {"min_tok_s": 41, "max_tok_s": 41}
      }
    }
  ]
}

Field	Value
`id`	The value for `model` in a chat completion
`state`	`loaded`, `starting`, `stopped` or `unavailable`
`loaded`	`true` when `state` is `loaded`
`context_length`	Prompt plus output token limit; `null` when not set
`created`	Unix seconds
`capabilities.parallel`	`true` when the model runs many requests at once
`capabilities.thinking`	`true` when the model reasons before answering
`capabilities.vision`	`true` when the model reads images; `false` for every current model
`capabilities.max_parallel`	Requests one account runs at once on the model
`facts.name`	Display name
`facts.params`	Parameter count
`facts.quantization`	Weight format
`facts.bits`	Bits per weight
`facts.size`	Size of the weights
`facts.context_tokens`	Context length in tokens
`facts.speed`	Output tokens per second for one request: `min_tok_s`, `max_tok_s`

Any facts field except name may be missing. Entries and facts carry further fields (owned_by, engine, mode, cold_start_s, notes, speed.note); their values may change without notice.

Errors

Status	Code	Meaning
401	`missing_api_key`	No `Authorization` header
401	`invalid_api_key`	Unknown or revoked key
403	`insufficient_scope`	The key does not carry the scope `llm`
429	`rate_limited`	The key's calls per minute or per day are used up
500	`internal`	Server error
502	`edge_error`	No valid answer from the model service
503	`device_offline`	The language model service is offline