Skip to main content
POST
/
v1
/
agents
/
{agent_id}
/
invoke
/
async
curl --request POST \
  --url https://api.xpander.ai/v1/agents/{agent_id}/invoke/async \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "input": {
    "text": "What is xpander.ai?",
    "user": {
      "id": "user-uuid",
      "email": "user@example.com"
    }
  }
}
'
{
  "id": "87b81bf7-7777-456e-805d-2767da39c62d",
  "agent_id": "47c3b020-9a6b-4699-8d94-d92d71929b53",
  "organization_id": "91fbe9bc-35b3-41e8-b59d-922fb5a0f031",
  "status": "pending",
  "result": null,
  "created_at": "2026-04-10T19:01:35.114410Z",
  "finished_at": null,
  "source": "api"
}

Documentation Index

Fetch the complete documentation index at: https://docs.xpander.ai/llms.txt

Use this file to discover all available pages before exploring further.

Invoke an agent asynchronously. Returns immediately with a task ID and status: "pending". Poll the Get Task endpoint to check when results are ready. Use this for long-running tasks, background processing, or when you don’t want to block a request.

​
Path Parameters

​
agent_id
string
required
Agent ID (UUID)

​
Request Body

The request body is identical to Invoke Agent (Sync).
  • input.text is required
  • input.user.id is required
  • input.user.email is required
  • user_oidc_token is optional for MCP OAuth-backed tools
​
input
object
required
​
user_oidc_token
string
Optional OIDC token for MCP OAuth-authenticated tools.
​
id
string
Thread ID for multi-turn conversations. Pass the id from a previous task to continue the conversation.
​
disable_attachment_injection
boolean
default:"false"
When true, files in input.files are not injected into the LLM context window. See Invoke Sync: Processing Files.
​
think_mode
string
default:"default"
default or harder. Controls reasoning depth.
​
instructions_override
string
Additional instructions appended to the system prompt for this invocation only.
​
additional_context
string
Extra context appended to the agent’s system prompt for this invocation only. Unlike instructions_override (which adds behavioral instructions), this supplies supplementary facts or context the agent should consider for this run — e.g. relevant background data, the current state of an external system, or a user’s recent activity.
​
expected_output
string
Natural-language description of desired output
​
llm_model_provider
string
Per-execution LLM provider override. See Invoke Sync: Per-Execution LLM Override.
​
llm_model_name
string
Per-execution model override. See Invoke Sync: Per-Execution LLM Override.
​
llm_reasoning_effort
string
default:"medium"
Per-execution reasoning-effort override (low | medium | high | xhigh). See Invoke Sync: Per-Execution LLM Override.

​
Query Parameters

​
version
string
Agent version to invoke. Defaults to latest deployed. Use "draft" to test undeployed changes.

​
Response

Returns immediately with the task object in pending state.
​
id
string
Task ID — use this to poll for results via Get Task
​
status
string
Always pending on initial return. Transitions to executing → completed (or failed/error).
​
result
string | null
null until the task completes

​
Basic Example

curl -s -X POST "https://api.xpander.ai/v1/agents/<agent-id>/invoke/async" \
  -H "Content-Type: application/json" \
  -H "x-api-key: <your-api-key>" \
  -d '{"input": {"text": "Analyze competitor pricing for Q1 2026"}}'
Response (immediate): 
{
  "id": "81250b20-e9d7-4b3b-9995-07dc72b4bb59",
  "agent_id": "<agent-id>",
  "status": "pending",
  "result": null,
  "created_at": "2026-02-07T02:13:26.325626Z"
}

​
Polling for Results

# 1. Start the async task
TASK_ID=$(curl -s -X POST "https://api.xpander.ai/v1/agents/<agent-id>/invoke/async" \
  -H "Content-Type: application/json" \
  -H "x-api-key: <your-api-key>" \
  -d '{"input": {"text": "Generate a market report"}}' | jq -r '.id')

echo "Task started: $TASK_ID"

# 2. Poll until done
while true; do
  RESPONSE=$(curl -s "https://api.xpander.ai/v1/tasks/$TASK_ID" \
    -H "x-api-key: <your-api-key>")

  STATUS=$(echo "$RESPONSE" | jq -r '.status')
  echo "Status: $STATUS"

  if [ "$STATUS" = "completed" ] || [ "$STATUS" = "failed" ] || [ "$STATUS" = "error" ]; then
    echo "$RESPONSE" | jq -r '.result'
    break
  fi

  sleep 2
done

​
Example Response (After Completion)

Poll the task after it finishes to get the full result: 
{
  "id": "81250b20-e9d7-4b3b-9995-07dc72b4bb59",
  "agent_id": "<agent-id>",
  "status": "completed",
  "input": {
    "text": "Analyze competitor pricing for Q1 2026",
    "user": null
  },
  "result": "Based on my analysis, the three main competitors...",
  "created_at": "2026-02-07T02:13:26.325626Z",
  "finished_at": "2026-02-07T02:13:41.897000Z",
  "source": "api"
}

​
Task Status Flow

pending → executing → completed | failed | error | stopped
For multi-turn conversations, always wait for a task to reach completed before sending the next message with the same id. Sending a follow-up while the previous task is still executing may cause unexpected behavior.

​
See Also

Authorizations

​
x-api-key
string
header
required

API Key for authentication

Path Parameters

​
agent_id
string
required

Query Parameters

​
version
string | null

The agent/workflow version to invoke. default = latest

Body

application/json
​
input
AgentExecutionInput · object
required
​
id
string

Pass the id from a previous response to continue a multi-turn conversation with the same agent. Omit for a new conversation.

Example:

"02843b37-4d77-48a0-8da7-2c76afe54401"

​
llm_model_provider
string | null

Per-execution override of the agent's LLM provider (e.g. openai, anthropic). Must match one of GET /llm_providers. Omit to use the agent's configured provider.

​
llm_model_name
string | null

Per-execution override of the model name within the chosen provider. Must match a model from GET /llm_providers/{provider}/models. Examples: claude-sonnet-4-6, gpt-5, gemini-2.0-flash. Omit to use the agent's configured model.

​
llm_reasoning_effort
enum<string> | null

Per-execution override of reasoning effort for reasoning-capable models (e.g. GPT-5). low for simple tasks, medium for balanced performance, high for complex reasoning, xhigh for maximum reasoning depth (slower, more expensive). Omit to use the agent's configured reasoning effort.

Available options:
low,
medium,
high,
xhigh

Response

Successful Response

​
id
string

Unique task identifier. Use this to poll for results when invoking async.

Example:

"02843b37-4d77-48a0-8da7-2c76afe54401"

​
agent_id
string
Example:

"47c3b020-9a6b-4699-8d94-d92d71929b53"

​
organization_id
string
Example:

"91fbe9bc-35b3-41e8-b59d-922fb5a0f031"

​
status
enum<string>

pending | executing | completed | error

Available options:
pending,
executing,
completed,
error,
failed,
stopped
Example:

"completed"

​
result
string | null

The agent's response. Populated when status is 'completed'. Null for async until polling shows completed.

Example:

"Hello! 👋"

​
created_at
string<date-time>
Example:

"2026-04-10T19:01:22.898813Z"

​
finished_at
string<date-time> | null

Null until the task completes.

Example:

"2026-04-10T19:01:33.120590Z"

​
source
string
Example:

"api"