Create Text Generator task

High-performance text generation endpoint on the async Starlette service. Authenticates via API token (X-API-KEY + X-API-ID).

Supports two modes:

• Sync (sync: true): blocks until generation completes, returns the result directly.
• Async (default): returns immediately with pending status. Poll GET /api/text_generator/{id}/ or use a webhook.

POST /sse/text_generator

Create Text Generator task

cURL

curl --request POST \
  --url https://api.creatify.ai/sse/text_generator/ \
  --header 'Content-Type: application/json' \
  --header 'X-API-ID: <api-key>' \
  --header 'X-API-KEY: <api-key>' \
  --data '
{
  "model_name": "<string>",
  "messages": [
    {
      "content": ""
    }
  ],
  "system_instruction": "",
  "config": {
    "temperature": 123,
    "max_output_tokens": 123,
    "top_p": 123,
    "top_k": 123,
    "presence_penalty": 123,
    "frequency_penalty": 123,
    "seed": 123,
    "stop_sequences": [
      "<string>"
    ],
    "response_json_schema": "<unknown>"
  },
  "tools": [
    {
      "function_declarations": [
        {
          "name": "<string>",
          "description": "",
          "parameters": "<unknown>"
        }
      ]
    }
  ],
  "tool_config": {
    "function_calling_config": {
      "allowed_function_names": [
        "<string>"
      ]
    }
  },
  "webhook_url": "<string>",
  "sync": false
}
'

201

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "model_name": "<string>",
  "messages": [
    {
      "content": "",
      "function_call": {
        "name": "<string>",
        "args": {}
      },
      "function_response": {
        "name": "<string>",
        "response": {}
      }
    }
  ],
  "config": {
    "temperature": 123,
    "max_output_tokens": 123,
    "top_p": 123,
    "top_k": 123,
    "presence_penalty": 123,
    "frequency_penalty": 123,
    "seed": 123,
    "stop_sequences": [
      "<string>"
    ],
    "response_json_schema": "<unknown>"
  },
  "response_function_calls": [
    {
      "name": "<string>",
      "args": {}
    }
  ],
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "system_instruction": "<string>",
  "response_text": "<string>",
  "failed_reason": "<string>",
  "credits_used": 123
}

Authorizations

X-API-ID · string · header · required

API ID, from your settings page.

X-API-KEY · string · header · required

API Key, from your settings page.

Body

application/json

model_name · string · required

Name of the Gemini model (e.g. gemini-2.5-flash).

Maximum string length: 255

messages · object[] · required

List of messages with 'role' (user/model) and 'content'.

Show child attributes

system_instruction · string · default: ""

Optional system instruction for the model.

config · object

Generation config parameters.

Show child attributes

tools · object[]

List of tools (function declarations) the model may call.

Show child attributes

tool_config · object

Controls how the model uses the provided tools.

Show child attributes

webhook_url · string<uri>

Webhook URL for async status updates.

sync · boolean · default: false

If true, the request blocks until generation completes and returns the result directly. Default is false (async).

Response

201

application/json

Text generation result or pending task.

id · string<uuid> · required · read-only

model_name · string · required · read-only

messages · object[] · required · read-only

Show child attributes

config · object · required

Structured config serializer for OpenAPI documentation.

Show child attributes

response_function_calls · object[] · required · read-only

Show child attributes

created_at · string<date-time> · required · read-only

updated_at · string<date-time> · required · read-only

system_instruction · string

Optional system instruction for the model.

status · enum<string>

• pending - pending
• running - running
• done - done
• failed - failed

Available options: pending, running, done, failed

response_text · string

Generated text response from the model.

failed_reason · string

Reason for failure if status is failed.

credits_used · number<double>

Credits consumed for this generation.