Skip to main content
GET
Lists the available models
Retrieve the list of models and their ids, available for use with the Agent API. This endpoint is useful when you want to see which models you can use when creating a temporary agent.

Before You Start

  • Legacy Assistants API: This is the new Agents API with native Vercel AI SDK compatibility. If you’re using the legacy Assistants API, see the migration guide.

Base URL

Dedicated deploymentsReplace api.langdock.com with <your-deployment-url>/api/public in all requests.

Example Request

Response Format

The API returns a list of available models in the following format:

Response Fields

string
Always ‘list’, indicating the top-level JSON object type.
array<Model>
Array containing available model objects.
string
Value to send as model on create, update, and completions. When the deployment name maps to one accessible row, id is that name (for example gpt-5). When several rows share the name, id is that row’s model UUID.
string
Deployment name for the row. Present on every row.
string
Always ‘model’, indicating the object type.
integer
Unix timestamp (ms) when the model was created.
string
Region where the model is available (e.g., “eu”, “us”, “global”).
boolean
Whether this model supports extended thinking mode.
Example response

Error Handling

Send id in the model field when you create a temporary agent. Completions rejects a deployment name that maps to more than one accessible row. Unique names and existing Anthropic aliases still work.
Langdock intentionally blocks browser-origin requests to protect your API key and ensure your applications remain secure. For more information, please see our guide on API Key Best Practices.

Authorizations

Authorization
string
header
required

API key as Bearer token. Format "Bearer YOUR_API_KEY"

Response

200 - application/json

List of available models

object
enum<string>
required
Available options:
list
data
object[]
required