# gpt-5.4-pro-2026-03-05

> AI model available via Core.Today API.

- **Provider**: openai
- **Model ID**: gpt-5.4-pro-2026-03-05
- **Category**: llm_general
- **Credits**: 1 per request
- **Pricing Type**: token_based

## API Endpoint

Base URL: https://api.core.today

### Responses
POST /llm/openai/v1/responses

## Authentication

Header: `Authorization: Bearer YOUR_API_KEY`

Note: Your Core.Today API key (`cdt_xxx`) works as Bearer token.

## Input Parameters

- `model` (string, **required**): Model identifier. Use `gpt-5.4-pro-2026-03-05`
- `input` (string or array, **required**): Prompt text, or an array of input items with `role` and `content`
- `instructions` (string, optional): System-level instructions
- `max_output_tokens` (integer, optional): Maximum tokens to generate (includes reasoning tokens)
- `reasoning` (object, optional): Reasoning options, e.g. `{"effort": "medium"}`
- `stream` (boolean, optional): Enable streaming responses (Default: `false`)

## Example Request

```json
{
  "model": "gpt-5.4-pro-2026-03-05",
  "input": "Hello, how are you?"
}
```

## Response Format

```json
{
  "id": "resp_abc123",
  "object": "response",
  "model": "gpt-5.4-pro-2026-03-05",
  "status": "completed",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Response text here"
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 10,
    "output_tokens": 20,
    "total_tokens": 30
  }
}
```

## Usage Flow

1. POST /llm/openai/v1/responses with model and input
2. Response is returned synchronously (or streamed if stream=true)
3. Credits are deducted based on token usage


## Token Pricing

- Input: 0.05574 credits/token
- Output: 0.33444 credits/token