DocsAPI reference

Models

GET /v1/models — the models your API key can reach right now, with their context windows, readiness and instances.

HTTP

GET https://osarai.xyz/v1/models

Lists the models your running instances serve. Tools call it to fill their model pickers; you can use it to check that an instance is Ready before sending work.

Terminal

curl "https://osarai.xyz/v1/models" -H "Authorization: Bearer $OSARAI_API_KEY"

Python

from openai import OpenAI
import os

client = OpenAI(base_url="https://osarai.xyz/v1", api_key=os.environ["OSARAI_API_KEY"])
for model in client.models.list():
    print(model.id)

TypeScript

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://osarai.xyz/v1", apiKey: process.env.OSARAI_API_KEY });
for await (const model of client.models.list()) console.log(model.id);

Response

JSON

{
  "object": "list",
  "data": [
    {
      "id": "qwen3.8-27b",
      "object": "model",
      "created": 1793952000,
      "owned_by": "osarai",
      "display_name": "qwen3.8-27b",
      "type": "model",
      "max_model_len": 131072,
      "ready": true,
      "instances": [{ "id": "a1b2c3d4e5", "ready": true, "max_model_len": 131072 }]
    }
  ]
}

Field	Meaning
`id`	The model id to send as `model`
`display_name`, `type`	For Anthropic clients such as Claude Code's model picker
`max_model_len`	Context window in tokens; with several instances, the smallest among the ready ones
`ready`	`true` when at least one instance answers requests
`instances`	Each instance with its id (for `X-Instance-Id`), readiness and context window

An instance appears from the moment you deploy it, with ready: false until it finishes starting. With no instance running, data is empty and requests answer 503.

Models

#Response

Response