Skip to main content
GET
List runs

Authorizations

Authorization
string
header
required

Your Seekr API key, sent in the Authorization header with no 'Bearer' prefix.

Headers

x-team-id
string | null

ID of the team to use for the request. If omitted, the request uses your personal workspace.

Path Parameters

thread_id
string
required

ID of the thread.

Query Parameters

limit
integer
default:20

Maximum number of results to return.

Required range: x >= 0
order
enum<string>
default:desc

Direction to sort the results. Options for order query param in list endpoints.

Available options:
asc,
desc
offset
integer
default:0

Number of results to skip.

Required range: x >= 0

Response

Success

id
string
required

ID of the run.

created_at
string<date-time>
required

Time the resource was created, in ISO 8601 format.

agent_id
string
required

ID of the agent.

thread_id
string
required

ID of the thread.

status
enum<string>
required

Available status for a run.

Available options:
queued,
running,
completed,
failed,
canceled,
cancelled
model
string
required

ID of the output model selected for the run.

temperature
number
required

Sampling temperature. Higher values make the output more random, and lower values make it more focused and repeatable.

top_p
number
required

Nucleus sampling. The model samples only from the smallest set of tokens whose combined probability reaches this value.

parallel_tool_calls
boolean
required

If true, the model can call more than one tool in a single turn.

object
string
default:thread.run

Object type. Always thread.run.

is_active
boolean
default:false

Whether this run currently holds the thread for execution.

started_at
string<date-time> | null

Time the run started, in ISO 8601 format.

expires_at
string<date-time> | null

Time the run expires, in ISO 8601 format.

cancelled_at
string<date-time> | null

Time the run was cancelled, in ISO 8601 format.

failed_at
string<date-time> | null

Time the run failed, in ISO 8601 format.

completed_at
string<date-time> | null

Time the run completed, in ISO 8601 format.

instructions
string | null

Instructions the agent follows for this run.

tools
Tools · object[]

Tools the model can call.

meta_data
Meta Data · object

Metadata recorded for the run, including the resolved model configuration.

usage
RunUsage · object | null

Token usage for the run.

max_completion_tokens
integer | null

Maximum number of tokens to generate in the completion.

truncation_strategy
Truncation Strategy · object

Prompt-truncation configuration recorded for the run. Empty when no strategy is recorded.

response_format
default:auto

Format the model must use for its output.

tool_choice
default:auto

Controls whether and which tool the model calls.

Last modified on July 31, 2026