Models

Astrodyne exposes a canonical model catalog. List the models your key can use with GET /v1/models, then pass an ID as the model field.

Listing your models

curl https://api.astrodyne.ai/v1/models \
  -H "Authorization: Bearer $ASTRODYNE_API_KEY"

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.astrodyne.ai/v1",
    api_key=os.environ["ASTRODYNE_API_KEY"],
)

for model in client.models.list():
    print(model.id)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.astrodyne.ai/v1",
  apiKey: process.env.ASTRODYNE_API_KEY,
});

for await (const model of client.models.list()) {
  console.log(model.id);
}

The response is the OpenAI list shape:

{
  "object": "list",
  "data": [
    { "id": "YOUR_MODEL_ID", "object": "model", "owned_by": "astrodyne" }
  ]
}

Why the list can vary

/v1/models returns exactly the models the authenticated key may request — the account's available catalog, minus anything excluded by that key's optional model restriction list. If a model is not in your list, requesting it returns a clear error.

Choosing and using a model

Browse the catalog on the Models page, try a model in the Playground, then use the same ID in your code. Model IDs are stable canonical identifiers, so the ID you test with is the ID you ship with.