Skip to main content
GET
Get Super Agent run status

Authorizations

Authorization
string
header
default:cr_sk_your_key_here
required

Account API key from Developer Console. Keys start with cr_sk_.

Path Parameters

run_id
string<uuid>
required

Super Agent run ID.

Query Parameters

raw_output
boolean
default:false

When true, replace result.text with the persisted chat_text (the full assistant transcript). Historical runs without chat_text keep the stored text. Accepts true or false.

Response

Super Agent run object.

run_id
string<uuid>
required

Developer API run ID.

status
enum<string>
required
Available options:
pending,
running,
completed,
failed,
cancelled
agent_id
string<uuid> | null
required

Agent that ran. Creation runs return null until the agent is created, then the completed run includes the new agent ID.

conversation_id
string<uuid> | null
required

Conversation ID for follow-up runs.

model
string | null
required

Model id this run executed with. null only for runs created before model selection shipped.

workspace_id
string<uuid> | null

Personal workspace bound to this conversation, when set.

result
object

Final agent output. Completed runs commonly include text; agent-creation runs also include agent_id.

usage
object

Settlement credits plus an optional per-model breakdown for the run. Omitted when the run incurred no cost and collected no model usage. models is present only for Super Agent–allowlisted accounts. Token fields appear only for token-metered capabilities. Per-image and per-second capabilities use generated_images or duration_seconds instead. kind tells the client which fields apply.

error
object
created_at
string<date-time>
started_at
string<date-time> | null
completed_at
string<date-time> | null
webhook_delivered_at
string<date-time> | null