List models (GET /v1/models) · Local API Guide

Local API Guide contents

Overview

Lists the models installed on this PC: the two chat models (when their files are present) and the knowledge (embedding) model. loaded: true marks the chat model on the GPU, the one that answers your requests.

Request

Parameter	Description
Authorization header	`Authorization: Bearer <key>`, only when Require API key is on in the app.

Response

An object with object: "list" and data, an array of models:

Field	Description
`id`string	The model id: `qwen3.8-27b`, `qwen3.6-35b-a3b` or `qwen3-embedding-4b`.
`object`string	Always `model`.
`created`integer	A fixed Unix timestamp.
`owned_by`string	Always `5090Ai`.
`display_name`string	The model's name, e.g. `Qwen3.6-35B-A3B`.
`context_length`integer	Chat models: the context of the loaded model, or the context configured in the app for the others.
`loaded`boolean	`true` for the model on the GPU right now.
`type, dimensions`string, integer	Only on the knowledge model: `embedding` and `2560`.

Example

curl http://localhost:1234/v1/models

from openai import OpenAI

client = OpenAI(base_url="http://localhost:1234/v1", api_key="not-needed")
for m in client.models.list():
    print(m.id, m.model_extra.get("loaded"))

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "http://localhost:1234/v1", apiKey: "not-needed" });
for await (const m of client.models.list()) console.log(m.id, m.loaded);

Response

{
  "object": "list",
  "data": [
    { "id": "qwen3.8-27b", "object": "model", "created": 1760000000, "owned_by": "5090Ai",
      "display_name": "Qwen3.8-27B", "context_length": 131072, "loaded": false },
    { "id": "qwen3.6-35b-a3b", "object": "model", "created": 1760000000, "owned_by": "5090Ai",
      "display_name": "Qwen3.6-35B-A3B", "context_length": 262144, "loaded": true },
    { "id": "qwen3-embedding-4b", "object": "model", "created": 1760000000, "owned_by": "5090Ai",
      "display_name": "Qwen3-Embedding-4B", "type": "embedding", "dimensions": 2560, "loaded": true }
  ]
}

Errors

Status	Code	When
401	`invalid_api_key`	Require API key is on and the key is missing or wrong.