# DataForSEO ChatGPT LLM Response API

> Send a prompt to ChatGPT and get the answer with token usage, for AI visibility checks.

Source: https://www.sandbase.ai/apis/dataforseo/v3/ai_optimization/chat_gpt/llm_responses/live
API reference: https://www.sandbase.ai/apis/dataforseo/v3/ai_optimization/chat_gpt/llm_responses/live/docs

## Facts

- Provider: DataForSEO
- Type: Data API
- Endpoint: `POST https://api.sandbase.ai/v1/api/dataforseo/v3/ai_optimization/chat_gpt/llm_responses/live`
- Price: From $0.0007 per call
- Capabilities: ai optimization, llm responses, chatgpt
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

`POST https://api.sandbase.ai/v1/api/dataforseo/v3/ai_optimization/chat_gpt/llm_responses/live` with `Authorization: Bearer $SANDBASE_API_KEY` and the parameters as a JSON body.

## FAQ

### How do I use the DataForSEO ChatGPT LLM Response API?

Send a POST request to https://api.sandbase.ai/v1/api/dataforseo/v3/ai_optimization/chat_gpt/llm_responses/live with your SandBase API key in the Authorization header (Bearer) and the parameters as a JSON body. You can also try it in the Playground on this page without writing code.

### How much does the DataForSEO ChatGPT LLM Response API cost?

From $0.0007 per call, billed from your SandBase balance. You are only charged for calls you make; there is no subscription.

### What parameters does the DataForSEO ChatGPT LLM Response API accept?

DataForSEO ChatGPT LLM Response takes no input parameters; send an empty JSON body.

### What does the DataForSEO ChatGPT LLM Response API return?

A JSON response returned in the same HTTP request (synchronous).

### Do I need a DataForSEO developer account or API key?

No. DataForSEO ChatGPT LLM Response runs through SandBase, so one SandBase API key covers this endpoint and every other API and model in the catalog. You do not need to apply for DataForSEO API access separately.

## README

### DataForSEO ChatGPT LLM Response API

Send a prompt to ChatGPT and get the answer with token usage, for AI visibility checks.

Request fields follow the official DataForSEO `/v3/ai_optimization/chat_gpt/llm_responses/live` task schema (one task per call). The response is DataForSEO's original JSON; results are in `tasks[].result`.

#### Request

```bash
curl -X POST "https://api.sandbase.ai/v1/api/dataforseo/v3/ai_optimization/chat_gpt/llm_responses/live" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"user_prompt": "best running shoes 2026", "model_name": "gpt-4o-mini", "max_output_tokens": 200}'
```

#### Parameters

The JSON body is forwarded to the upstream endpoint. Main fields:

| Name | Description |
|---|---|
| `user_prompt` | The prompt to send. |
| `model_name` | Model name from the vendor's model list. |
| `max_output_tokens` | Optional cap on answer length; longer answers cost more. |
| `system_message` | Optional system instruction. |
| `web_search` | Optional: let the model search the web (where supported). |

#### Reference

- Official docs: https://docs.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/live/

#### Pricing

Billed at the actual cost of each call, about $0.000724 for the request above. The cost grows with the number of rows, targets or tokens a call returns. Failed calls are not charged. Searches with no results are billed at their actual cost.