REST API ReferenceEndpointsAssistant

Start an assistant chat

Creates a new project and sends the first message to the VideoGen AI assistant, exactly like typing into the assistant on a new project in the app. Asynchronous: the response contains the `messageId` of the assistant's pending reply (e.g. `vg_mesg_...`). Poll `GET /v1/assistant-messages/{messageId}` until `status` is `succeeded`, `failed`, or `cancelled`, or subscribe to `assistant_message.*` webhooks. Fetch the parent assistant with `GET /v1/assistants/{assistantId}` to list all messages in the chat.

Authentication

AuthorizationBearer
API key from [app.videogen.io/developers](https://app.videogen.io/developers). The full key is only shown once when you create it.

Request

This endpoint expects an object.
messagestringRequired
The first message to send to the assistant, exactly as a person would type it into the assistant on a new project.
forceWorkflowSuggestionbooleanOptionalDefaults to false

When true, the assistant must respond with at least one workflow suggestion. If it doesn’t, the assistant message is settled to failed with a no_workflow_suggestion error.

autoGeneratebooleanOptionalDefaults to false

When true, the assistant picks the best workflow for the message and immediately starts generating, skipping the suggestion step. When the assistant message reaches succeeded, its generation carries the workflow run to poll.

Response

Assistant message accepted.
messageIdstring

Opaque assistant message id for the pending assistant reply (e.g. vg_mesg_...). Poll GET /v1/assistant-messages/{messageId}.

assistantIdstring

Opaque assistant chat id (e.g. vg_asst_...). Pass to GET /v1/assistants/{assistantId} and follow-up message/action calls.

projectIdstring

Opaque project id for the new chat (e.g. vg_proj_...).

projectUrlstringformat: "uri"
Deep link to open this project in the VideoGen web app.