Create job

Run an agent with specific input files.

POST

/responses

Authorization

`Authorization`
Required
Bearer <token>

In: header

Request Body

application/jsonRequired

`model`
Required
string

The Agent ID to run.

`input`
Required
array<object>

`include`array<string>

Controls how many step results are returned. Use ["last"] for only the latest step (default) or ["all"] for the full step history.

Default: ["last"]

`config_id`string

The ID of the configuration version. It is same as the Config ID in the Use via API page. If it is not provided, the latest configuration version will be used.

Example

Request

from openai import OpenAI
from time import sleep
import json
 
client = OpenAI(
    api_key="UPSTAGE_API_KEY",
    base_url="https://api.upstage.ai/v2"
)

# Supports multiple files
input_files = [
    {
        "type": "input_file",
        "file_id": "file-abc123"
    }
]
 
input = [
    {
        "role": "user",
        "content": [
            *input_files
        ]
    }
]
 
# Create a job
resp = client.responses.create(
    model="agt_BxcRatEWzVYH2yRNtyWynn",
    include=["last"],
    input=input,
)
 
# Poll until the job is no longer queued or in progress
while resp.status in {"queued", "in_progress"}:
    sleep(2)
    resp = client.responses.retrieve(
        resp.id,
        include=["last"]
    )

# When completed, read the final output text
if resp.status == "completed":
    print(json.loads(resp.output_text))

Response

{
  "id": "job_7yMqwGy3rfh6Pwo7MdseMo",
  "object": "response",
  "created_at": 1767613535,
  "status": "completed",
  "background": true,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "model": "agt_BxcRatEWzVYH2yRNtyWynn",
  "output": [
    {
      "id": "fb543069-1a45-4fde-94de-2383995d7339",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "model": "step_2_extract",
      "content": [
        {
          "type": "output_text",
          "text": "{\"key\": \"value\", \"group_key\": [{\"properties\": \"properties_value\"}]}",
          "annotations": [],
          "additional_values": "{...}"
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0,
    "total_tokens": 0
  }
}

Create job

Run an agent with specific input files.

POST

/responses

Authorization

`Authorization`
Required
Bearer <token>

In: header

Request Body

application/jsonRequired

`model`
Required
string

The Agent ID to run.

`input`
Required
array<object>

`include`array<string>

Controls how many step results are returned. Use ["last"] for only the latest step (default) or ["all"] for the full step history.

Default: ["last"]

`config_id`string

The ID of the configuration version. It is same as the Config ID in the Use via API page. If it is not provided, the latest configuration version will be used.

Example

Request

from openai import OpenAI
from time import sleep
import json
 
client = OpenAI(
    api_key="UPSTAGE_API_KEY",
    base_url="https://api.upstage.ai/v2"
)

# Supports multiple files
input_files = [
    {
        "type": "input_file",
        "file_id": "file-abc123"
    }
]
 
input = [
    {
        "role": "user",
        "content": [
            *input_files
        ]
    }
]
 
# Create a job
resp = client.responses.create(
    model="agt_BxcRatEWzVYH2yRNtyWynn",
    include=["last"],
    input=input,
)
 
# Poll until the job is no longer queued or in progress
while resp.status in {"queued", "in_progress"}:
    sleep(2)
    resp = client.responses.retrieve(
        resp.id,
        include=["last"]
    )

# When completed, read the final output text
if resp.status == "completed":
    print(json.loads(resp.output_text))

Response

{
  "id": "job_7yMqwGy3rfh6Pwo7MdseMo",
  "object": "response",
  "created_at": 1767613535,
  "status": "completed",
  "background": true,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "model": "agt_BxcRatEWzVYH2yRNtyWynn",
  "output": [
    {
      "id": "fb543069-1a45-4fde-94de-2383995d7339",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "model": "step_2_extract",
      "content": [
        {
          "type": "output_text",
          "text": "{\"key\": \"value\", \"group_key\": [{\"properties\": \"properties_value\"}]}",
          "annotations": [],
          "additional_values": "{...}"
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0,
    "total_tokens": 0
  }
}

Create job

Authorization

`Authorization`
Required
Bearer <token>

Request Body

`model`
Required
string

`input`
Required
array<object>

`include`array<string>

`config_id`string

Example

Request

Response

On this page

Create job

Authorization

`Authorization`
Required
Bearer <token>

Request Body

`model`
Required
string

`input`
Required
array<object>

`include`array<string>

`config_id`string

Example

Request

Response

On this page

Body

AuthorizationRequiredBearer <token>

modelRequiredstring

inputRequiredarray<object>

Object 1

includearray<string>

config_idstring

Response

On this page

Body

AuthorizationRequiredBearer <token>

modelRequiredstring

inputRequiredarray<object>

Object 1

includearray<string>

config_idstring

Response

On this page

`Authorization`
Required
Bearer <token>

`model`
Required
string

`input`
Required
array<object>

`include`array<string>

`config_id`string

`Authorization`
Required
Bearer <token>

`model`
Required
string

`input`
Required
array<object>

`include`array<string>

`config_id`string