> ## Documentation Index
> Fetch the complete documentation index at: https://phaseo.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Respuestas

> Llama a la API de Responses con el SDK de Python.

**Método**: `client.generate_response()` (transmite fragmentos procesados con `client.stream_responses()`).

### Ejemplo

```python theme={null}
resp = client.generate_response({
    "model": "openai/gpt-4.1",
    "input": [{"role": "user", "content": [{"type": "input_text", "text": "Summarise this"}]}],
    "temperature": 0.7,
})
```

### Transmisión

```python theme={null}
for chunk in client.stream_responses({
    "model": "openai/gpt-4.1",
    "input": [{"role": "user", "content": [{"type": "input_text", "text": "Stream this"}]}],
    "stream": True,
}):
    if chunk.get("text"):
        print(chunk["text"], end="", flush=True)
```

### Parámetros clave

* `model` (obligatorio): ID del modelo de destino.
* `input` (obligatorio): matriz ordenada de elementos de entrada (mensajes, llamadas a herramientas, etc.).
* `temperature` (0–2): cuanto mayor sea el valor, más aleatorio será el resultado.
* `top_p` (0–1) / `top_k` (>=1): controles de muestreo por núcleo y de los k mejores candidatos.
* `max_output_tokens` (entero): límite máximo de tokens generados por respuesta.
* Herramientas: `tools` (definiciones), `tool_choice` (auto/none/específica), `max_tool_calls` (entero), `parallel_tool_calls` (booleano).
* Logprobs: `logprobs` (booleano), `top_logprobs` (0–20) para devolver logprobs por token.
* Salida: `response_format` (json/text), `service_tier`, `store` (booleano), `stream` (booleano).
* Metadatos: `metadata` (objeto transferido), `reasoning` (objeto con indicaciones de esfuerzo).
* Extras del gateway: `usage` (booleano para solicitar el uso), `meta` (booleano para incluir el bloque meta).

### Devuelve

`ResponsesResponse`

```json theme={null}
{
  "id": "resp_123",
  "object": "response",
  "created_at": 1677652288,
  "status": "completed",
  "model": "gpt-4.1",
  "output": [
    {
      "type": "message",
      "id": "msg_123",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Hello there, how may I assist you today?"
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 9,
    "output_tokens": 12,
    "total_tokens": 21
  }
}
```

O tramas SSE delimitadas por salto de línea cuando `stream: true`:

```
data: {"id":"resp_123","object":"response","created_at":1677652288,"status":"in_progress","model":"gpt-4.1","output":[{"type":"message","id":"msg_123","status":"in_progress","role":"assistant","content":[]}]}

data: {"id":"resp_123","object":"response","created_at":1677652288,"status":"in_progress","model":"gpt-4.1","output":[{"type":"message","id":"msg_123","status":"in_progress","role":"assistant","content":[{"type":"output_text","text":"Hello"}]}]}

data: {"id":"resp_123","object":"response","created_at":1677652288,"status":"completed","model":"gpt-4.1","output":[{"type":"message","id":"msg_123","status":"completed","role":"assistant","content":[{"type":"output_text","text":"Hello there, how may I assist you today?"}]}],"usage":{"input_tokens":9,"output_tokens":12,"total_tokens":21}}

data: [DONE]
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.