Models for Assistant API

Retrieve the list of models and their ids available for use with the Assistant API. Useful to see which models you can specify when creating a temporary assistant.

Endpoint GET https://api.langdock.com/assistant/v1/models

Headers

• Authorization: Bearer YOUR_API_KEY (required)

Supported responses

• 200 application/json — List of available models

• 400 — Invalid request parameters

• 429 — Rate limited

• 500 — Internal server error

cURL

curl --request GET \
  --url https://api.langdock.com/assistant/v1/models \
  --header 'Authorization: <authorization>'

JavaScript (axios)

Response format The API returns a top-level object with object: "list" and a data array of model objects.

Example response

{
  "object": "list",
  "data": [
    {
      "id": "gpt-5",
      "object": "model",
      "created": 1686935735000,
      "owned_by": "system"
    }
    // …other models
  ]
}

Response fields

• object (string) — Always "list", indicating the top-level JSON object type.

• data (array) — Array containing available model objects.

Model object fields:

• id (string) — Unique identifier of the model (e.g., gpt-5).

• object (string) — Always "model".

• created (integer) — Unix timestamp (ms) when the model was created.

• owned_by (string) — Owner of the model (currently always "system").

Using a model when creating a temporary assistant Specify any model ID from the list in the model field of your assistant configuration.

const response = await axios.post("https://api.langdock.com/assistant/v1/chat/completions", {
  assistant: {
    name: "Custom Assistant",
    instructions: "You are a helpful assistant",
    model: "gpt-5" // Specify the model ID here
  },
  messages: [
    { role: "user", content: "Hello!" }
  ]
});

Error handling

Example pattern:

try {
  const response = await axios.get("https://api.langdock.com/assistant/v1/models", {
    headers: {
      Authorization: "Bearer YOUR_API_KEY",
    },
  });
} catch (error) {
  if (error.response) {
    switch (error.response.status) {
      case 400:
        console.error("Invalid request parameters");
        break;
      case 500:
        console.error("Internal server error");
        break;
    }
  }
}