v1

latestOpenAPI 3.0.42026-07-26159287356.1 KB

studio

Prompt a deployment with streaming response

Sends a prompt to a specific miniapp generator deployment and returns a streaming response using Server-Sent Events. The response is a continuous stream of Server-Sent Events, not a single JSON payload. Each event contains a JSON object with type, message, and other fields specific to the message type. Requires authentication via API key in the request header. Note: Studio CU is tracked based on LLM token usage, not per API call.

post/v2/studio/deployment/prompt/stream

Request body

conversation_idstring uuid

Optional conversation ID to continue an existing chat. If not provided, a new conversation will be created.

deployment_idstring uuid

Deployment ID (UUID). Required if name not provided.

fidinteger

Farcaster ID of the user; if not provided, namespace must be provided

namestring

Kubernetes deployment name. Required if deployment_id not provided.

namespacestring

Optional Kubernetes namespace. If not provided, will query for the active namespace for the given FID.

promptstring required

Prompt string to send to the deployment

session_idstring

Optional Claude SDK session ID to resume an existing Claude Code session. Enables session-based conversation continuity.

system_prompt_variant'canary' | 'beta' | 'stable'

System prompt variant to use. Defaults to stable if not provided.

Example request

{
  "fid": 3
}

Response

Success