Runs

API Reference

List all thread runs.

Returns a list of thread runs, which represent individual executions or interactions within a thread.

GEThttps://api.aimlapi.com/threads/{threadId}/runs

Path parameters

threadId*string

Response

201

Body

application/json

id*string

assistant_id*string

cancelled_at*nullable number

completed_at*nullable number

created_at*number

expires_at*nullable number

failed_at*nullable number

incomplete_details*RunIncompleteDetailsDTO (object)

instructions*string

last_error*RunLastErrorDTO (object)

max_completion_tokens*nullable number

max_prompt_tokens*nullable number

metadatanullable any

model*string

object*enum

thread.run

parallel_tool_calls*boolean

required_action*nullable object

response_formatnullable any

started_at*nullable number

status*enum

queuedin_progressrequires_actioncancellingcancelledfailedcompletedincompleteexpired

thread_id*string

tool_choicenullable any

tools*array of nullable any

truncation_strategy*RunTruncationStrategyDTO (object)

usage*RunUsageDTO (object)

temperaturenullable number

top_pnullable number

Request

JavaScriptCurlPython

const response = await fetch('https://api.aimlapi.com/threads/{threadId}/runs', {
    method: 'GET',
    headers: {},
});
const data = await response.json();

Response

201

[
  {
    "id": "text",
    "assistant_id": "text",
    "cancelled_at": 0,
    "completed_at": 0,
    "created_at": 0,
    "expires_at": 0,
    "failed_at": 0,
    "incomplete_details": {
      "reason": "max_completion_tokens"
    },
    "instructions": "text",
    "last_error": {
      "code": "server_error",
      "message": "text"
    },
    "max_completion_tokens": 0,
    "max_prompt_tokens": 0,
    "model": "text",
    "object": "thread.run",
    "parallel_tool_calls": false,
    "required_action": {
      "submit_tool_outputs": {
        "tool_calls": []
      },
      "type": "submit_tool_outputs"
    },
    "started_at": 0,
    "status": "queued",
    "thread_id": "text",
    "tools": [],
    "truncation_strategy": {
      "type": "auto",
      "last_messages": 0
    },
    "usage": {
      "completion_tokens": 0,
      "prompt_tokens": 0,
      "total_tokens": 0
    },
    "temperature": 0,
    "top_p": 0
  }
]

Create a new thread run.

Creates a new thread run, executing a task or interaction within a thread context.

POSThttps://api.aimlapi.com/threads/{threadId}/runs

Path parameters

threadId*string

Body

application/json

assistant_id*string

streamboolean

metadataobject

Response

201

Body

application/json

id*string

assistant_id*string

cancelled_at*nullable number

completed_at*nullable number

created_at*number

expires_at*nullable number

failed_at*nullable number

incomplete_details*RunIncompleteDetailsDTO (object)

instructions*string

last_error*RunLastErrorDTO (object)

max_completion_tokens*nullable number

max_prompt_tokens*nullable number

metadatanullable any

model*string

object*enum

thread.run

parallel_tool_calls*boolean

required_action*nullable object

response_formatnullable any

started_at*nullable number

status*enum

queuedin_progressrequires_actioncancellingcancelledfailedcompletedincompleteexpired

thread_id*string

tool_choicenullable any

tools*array of nullable any

truncation_strategy*RunTruncationStrategyDTO (object)

usage*RunUsageDTO (object)

temperaturenullable number

top_pnullable number

Request

JavaScriptCurlPython

const response = await fetch('https://api.aimlapi.com/threads/{threadId}/runs', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "assistant_id": "text"
    }),
});
const data = await response.json();

Response

201

{
  "id": "text",
  "assistant_id": "text",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "text",
  "last_error": {
    "code": "server_error",
    "message": "text"
  },
  "max_completion_tokens": 0,
  "max_prompt_tokens": 0,
  "model": "text",
  "object": "thread.run",
  "parallel_tool_calls": false,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": []
    },
    "type": "submit_tool_outputs"
  },
  "started_at": 0,
  "status": "queued",
  "thread_id": "text",
  "tools": [],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 0
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Update a thread run’s details.

Updates the details of a thread run, modifying its status or context.

POSThttps://api.aimlapi.com/threads/{threadId}/runs/{runId}

Path parameters

threadId*string

runId*string

Body

application/json

metadataobject

Response

200

Body

application/json

id*string

assistant_id*string

cancelled_at*nullable number

completed_at*nullable number

created_at*number

expires_at*nullable number

failed_at*nullable number

incomplete_details*RunIncompleteDetailsDTO (object)

instructions*string

last_error*RunLastErrorDTO (object)

max_completion_tokens*nullable number

max_prompt_tokens*nullable number

metadatanullable any

model*string

object*enum

thread.run

parallel_tool_calls*boolean

required_action*nullable object

response_formatnullable any

started_at*nullable number

status*enum

queuedin_progressrequires_actioncancellingcancelledfailedcompletedincompleteexpired

thread_id*string

tool_choicenullable any

tools*array of nullable any

truncation_strategy*RunTruncationStrategyDTO (object)

usage*RunUsageDTO (object)

temperaturenullable number

top_pnullable number

Request

JavaScriptCurlPython

const response = await fetch('https://api.aimlapi.com/threads/{threadId}/runs/{runId}', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({}),
});
const data = await response.json();

Response

200

{
  "id": "text",
  "assistant_id": "text",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "text",
  "last_error": {
    "code": "server_error",
    "message": "text"
  },
  "max_completion_tokens": 0,
  "max_prompt_tokens": 0,
  "model": "text",
  "object": "thread.run",
  "parallel_tool_calls": false,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": []
    },
    "type": "submit_tool_outputs"
  },
  "started_at": 0,
  "status": "queued",
  "thread_id": "text",
  "tools": [],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 0
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}

Get details of a specific thread run.

Retrieves a single thread run by its ID, providing access to its execution details.

GEThttps://api.aimlapi.com/threads/{threadId}/runs/{runId}

Path parameters

threadId*string

runId*string

Response

200

Body

application/json

id*string

assistant_id*string

cancelled_at*nullable number

completed_at*nullable number

created_at*number

expires_at*nullable number

failed_at*nullable number

incomplete_details*RunIncompleteDetailsDTO (object)

instructions*string

last_error*RunLastErrorDTO (object)

max_completion_tokens*nullable number

max_prompt_tokens*nullable number

metadatanullable any

model*string

object*enum

thread.run

parallel_tool_calls*boolean

required_action*nullable object

response_formatnullable any

started_at*nullable number

status*enum

queuedin_progressrequires_actioncancellingcancelledfailedcompletedincompleteexpired

thread_id*string

tool_choicenullable any

tools*array of nullable any

truncation_strategy*RunTruncationStrategyDTO (object)

usage*RunUsageDTO (object)

temperaturenullable number

top_pnullable number

Request

JavaScriptCurlPython

const response = await fetch('https://api.aimlapi.com/threads/{threadId}/runs/{runId}', {
    method: 'GET',
    headers: {},
});
const data = await response.json();

Response

200

{
  "id": "text",
  "assistant_id": "text",
  "cancelled_at": 0,
  "completed_at": 0,
  "created_at": 0,
  "expires_at": 0,
  "failed_at": 0,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "instructions": "text",
  "last_error": {
    "code": "server_error",
    "message": "text"
  },
  "max_completion_tokens": 0,
  "max_prompt_tokens": 0,
  "model": "text",
  "object": "thread.run",
  "parallel_tool_calls": false,
  "required_action": {
    "submit_tool_outputs": {
      "tool_calls": []
    },
    "type": "submit_tool_outputs"
  },
  "started_at": 0,
  "status": "queued",
  "thread_id": "text",
  "tools": [],
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 0
  },
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "temperature": 0,
  "top_p": 0
}