> ## 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.

# Réponses

> Appelez l’API Responses avec le SDK TypeScript.

**Méthode**: `client.generateResponse()` (diffusez les fragments analysés avec `client.streamResponses()`).

### Exemple

```typescript theme={null}
const resp = await client.generateResponse({
  model: "openai/gpt-4.1",
  input: [{ role: "user", content: [{ type: "input_text", text: "Summarise this text" }] }],
  temperature: 0.7,
  stream: false,
});
```

### Diffusion en continu

```typescript theme={null}
for await (const chunk of client.streamResponses({
  model: "openai/gpt-4.1",
  input: [{ role: "user", content: [{ type: "input_text", text: "Stream this" }] }],
  stream: true,
})) {
  if (chunk.text) process.stdout.write(chunk.text);
}
```

### Paramètres principaux

* `model` (required): ID du modèle cible.
* `input` (required): Tableau ordonné d’éléments d’entrée (messages, appels d’outils, etc.).
* `temperature` (0-2): Une valeur plus élevée augmente l’aléatoire.
* `top_p` (0-1) / `top_k` (>=1): Paramètres d’échantillonnage nucleus / top-k.
* `max_output_tokens` (int): Limite maximale du nombre de tokens générés par réponse.
* Outils : `tools` (définitions), `tool_choice` (`auto`/`none`/spécifique), `max_tool_calls` (int), `parallel_tool_calls` (bool).
* Logprobs : `logprobs` (bool), `top_logprobs` (0-20) pour renvoyer les logprobs de chaque token.
* Sortie : `response_format` (json/text), `service_tier`, `store` (bool), `stream` (bool).
* Métadonnées : `metadata` (object) pour le transfert sans modification, `reasoning` (object) pour indiquer le niveau d’effort.
* Options Gateway supplémentaires : `usage` (bool pour demander les données d’utilisation), `meta` (bool pour inclure le bloc meta).

### Réponse

`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
  }
}
```

Ou des trames SSE délimitées par des retours à la ligne lorsque `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.