Aller au contenu
Référence API
Référence API

OpenAI Responses

Envoyer une requête via l'opération Responses compatible OpenAI de RunAPI.

Voir en Markdown
01

Vue d'ensemble

Utilisez l'opération Responses compatible OpenAI de RunAPI avec un modèle compatible et les structures de requête et de réponse du protocole.

Démarrage rapide

  1. Créez une clé API et définissez-la comme RUNAPI_API_KEY.
  2. Choisissez un modèle compatible, puis envoyez les paramètres de chemin et le corps JSON documentés.
  3. Lisez la réponse JSON ou les événements envoyés par le serveur affichés pour cette opération, et gérez les erreurs de protocole.

Point de terminaison

POST /v1/responses
URL de base
https://runapi.ai
Version du contrat
v1
Authentification recommandée
Authorization: Bearer YOUR_API_TOKEN
02

Supports d'authentification

RunAPI accepte chaque protocole listé ci-dessous. Les exemples générés utilisent l'en-tête préféré du protocole.

header - Recommandé
Authorization: Bearer YOUR_API_TOKEN
header
x-api-key: YOUR_API_TOKEN
header
x-goog-api-key: YOUR_API_TOKEN
query
?key=YOUR_API_TOKEN
03

Modèles compatibles

Ouvrez une page de modèle pour consulter la tarification actuelle, les limites de débit et les conditions d'utilisation commerciale.

Afficher 58 modèles compatibles
04

Contrat de requête

Corps JSON

Seuls les champs disposant à la fois d'un protocole public et d'une prise en charge RunAPI avérée sont listés. Les champs supplémentaires du corps JSON sont transmis tels quels.

Corps JSON13 champs
input["string", "array"]
Optionnel

Texte, éléments de message ou résultats d'outils fournis au modèle.

instructions["string", "null"]
Optionnel

Instructions système ou développeur pour cette réponse.

max_output_tokens["integer", "null"]
Optionnel

Nombre maximum de tokens en sortie, y compris les tokens visibles et de raisonnement.

modelstring
Requis

Identifiant de modèle RunAPI retourné par le catalogue de modèles compatible.

moderation["object", "null"]
Optionnel

Retourner des signaux de modération indépendants pour l'entrée actuelle et la sortie complète.

moderation.modelstring
Requis Valeurs autorisées: omni-moderation-latest
moderation.policy["object", "null"]
Optionnel
moderation.policy.input["object", "null"]
Optionnel
moderation.policy.input.modestring
Requis Valeurs autorisées: score, block
moderation.policy.output["object", "null"]
Optionnel
moderation.policy.output.modestring
Requis Valeurs autorisées: score, block
stream["boolean", "null"]
Optionnel

Retourner des événements Responses typés sous forme d'événements server-sent.

Par défaut: false
toolsarray
Optionnel

Outils que le modèle peut appeler.

Exemple de requête

JSON 
{
  "input": "Summarize one practical improvement for an API deployment.",
  "model": "gpt-5.4",
  "moderation": {
    "model": "omni-moderation-latest",
    "policy": {
      "input": {
        "mode": "score"
      },
      "output": {
        "mode": "block"
      }
    }
  }
}
05

Réponse synchrone

HTTP 200

Schéma

JSON 
{
  "additionalProperties": true,
  "properties": {
    "id": {
      "type": "string"
    },
    "model": {
      "type": "string"
    },
    "moderation": {
      "additionalProperties": true,
      "properties": {
        "input": {
          "oneOf": [
            {
              "additionalProperties": true,
              "properties": {
                "categories": {
                  "additionalProperties": true,
                  "type": "object"
                },
                "category_applied_input_types": {
                  "additionalProperties": true,
                  "type": "object"
                },
                "category_scores": {
                  "additionalProperties": true,
                  "type": "object"
                },
                "flagged": {
                  "type": "boolean"
                },
                "model": {
                  "const": "omni-moderation-latest",
                  "type": "string"
                },
                "type": {
                  "const": "moderation_result",
                  "type": "string"
                }
              },
              "required": [
                "type",
                "model",
                "flagged",
                "categories",
                "category_scores",
                "category_applied_input_types"
              ],
              "type": "object"
            },
            {
              "additionalProperties": true,
              "properties": {
                "code": {
                  "type": "string"
                },
                "message": {
                  "type": "string"
                },
                "type": {
                  "const": "error",
                  "type": "string"
                }
              },
              "required": [
                "type",
                "code",
                "message"
              ],
              "type": "object"
            }
          ]
        },
        "output": {
          "oneOf": [
            {
              "additionalProperties": true,
              "properties": {
                "categories": {
                  "additionalProperties": true,
                  "type": "object"
                },
                "category_applied_input_types": {
                  "additionalProperties": true,
                  "type": "object"
                },
                "category_scores": {
                  "additionalProperties": true,
                  "type": "object"
                },
                "flagged": {
                  "type": "boolean"
                },
                "model": {
                  "const": "omni-moderation-latest",
                  "type": "string"
                },
                "type": {
                  "const": "moderation_result",
                  "type": "string"
                }
              },
              "required": [
                "type",
                "model",
                "flagged",
                "categories",
                "category_scores",
                "category_applied_input_types"
              ],
              "type": "object"
            },
            {
              "additionalProperties": true,
              "properties": {
                "code": {
                  "type": "string"
                },
                "message": {
                  "type": "string"
                },
                "type": {
                  "const": "error",
                  "type": "string"
                }
              },
              "required": [
                "type",
                "code",
                "message"
              ],
              "type": "object"
            }
          ]
        }
      },
      "required": [
        "input",
        "output"
      ],
      "type": "object"
    },
    "object": {
      "const": "response",
      "type": "string"
    },
    "output": {
      "type": "array"
    },
    "status": {
      "type": "string"
    },
    "usage": {
      "additionalProperties": true,
      "properties": {
        "input_tokens": {
          "type": "integer"
        },
        "output_tokens": {
          "type": "integer"
        },
        "total_tokens": {
          "type": "integer"
        }
      },
      "required": [
        "input_tokens",
        "output_tokens",
        "total_tokens"
      ],
      "type": "object"
    }
  },
  "required": [
    "id",
    "object",
    "status",
    "model",
    "output"
  ],
  "type": "object"
}

Exemple

JSON 
{
  "id": "resp_example",
  "model": "gpt-5.4",
  "moderation": {
    "input": {
      "categories": {
        "sexual": false,
        "violence": true
      },
      "category_applied_input_types": {
        "sexual": [
          "text"
        ],
        "violence": [
          "text"
        ]
      },
      "category_scores": {
        "sexual": 0.0002,
        "violence": 0.96
      },
      "flagged": true,
      "model": "omni-moderation-latest",
      "type": "moderation_result"
    },
    "output": {
      "categories": {
        "sexual": false,
        "violence": false
      },
      "category_applied_input_types": {
        "sexual": [
          "text"
        ],
        "violence": [
          "text"
        ]
      },
      "category_scores": {
        "sexual": 0.0002,
        "violence": 0.0001
      },
      "flagged": false,
      "model": "omni-moderation-latest",
      "type": "moderation_result"
    }
  },
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "text": "Hello! How can I help today?",
          "type": "output_text"
        }
      ],
      "id": "msg_example",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "status": "completed",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 8,
    "total_tokens": 20
  }
}
06

Événement SSE : output_text_delta

text/event-stream

Schéma

JSON 
{
  "additionalProperties": true,
  "properties": {
    "content_index": {
      "type": "integer"
    },
    "delta": {
      "type": "string"
    },
    "item_id": {
      "type": "string"
    },
    "output_index": {
      "type": "integer"
    },
    "type": {
      "const": "response.output_text.delta",
      "type": "string"
    }
  },
  "required": [
    "type",
    "item_id",
    "output_index",
    "content_index",
    "delta"
  ],
  "type": "object"
}

Exemple

JSON 
{
  "content_index": 0,
  "delta": "Hello",
  "item_id": "msg_example",
  "output_index": 0,
  "type": "response.output_text.delta"
}
07

Événement SSE : completed

text/event-stream

Schéma

JSON 
{
  "additionalProperties": true,
  "properties": {
    "response": {
      "additionalProperties": true,
      "properties": {
        "id": {
          "type": "string"
        },
        "model": {
          "type": "string"
        },
        "moderation": {
          "additionalProperties": true,
          "properties": {
            "input": {
              "oneOf": [
                {
                  "additionalProperties": true,
                  "properties": {
                    "categories": {
                      "additionalProperties": true,
                      "type": "object"
                    },
                    "category_applied_input_types": {
                      "additionalProperties": true,
                      "type": "object"
                    },
                    "category_scores": {
                      "additionalProperties": true,
                      "type": "object"
                    },
                    "flagged": {
                      "type": "boolean"
                    },
                    "model": {
                      "const": "omni-moderation-latest",
                      "type": "string"
                    },
                    "type": {
                      "const": "moderation_result",
                      "type": "string"
                    }
                  },
                  "required": [
                    "type",
                    "model",
                    "flagged",
                    "categories",
                    "category_scores",
                    "category_applied_input_types"
                  ],
                  "type": "object"
                },
                {
                  "additionalProperties": true,
                  "properties": {
                    "code": {
                      "type": "string"
                    },
                    "message": {
                      "type": "string"
                    },
                    "type": {
                      "const": "error",
                      "type": "string"
                    }
                  },
                  "required": [
                    "type",
                    "code",
                    "message"
                  ],
                  "type": "object"
                }
              ]
            },
            "output": {
              "oneOf": [
                {
                  "additionalProperties": true,
                  "properties": {
                    "categories": {
                      "additionalProperties": true,
                      "type": "object"
                    },
                    "category_applied_input_types": {
                      "additionalProperties": true,
                      "type": "object"
                    },
                    "category_scores": {
                      "additionalProperties": true,
                      "type": "object"
                    },
                    "flagged": {
                      "type": "boolean"
                    },
                    "model": {
                      "const": "omni-moderation-latest",
                      "type": "string"
                    },
                    "type": {
                      "const": "moderation_result",
                      "type": "string"
                    }
                  },
                  "required": [
                    "type",
                    "model",
                    "flagged",
                    "categories",
                    "category_scores",
                    "category_applied_input_types"
                  ],
                  "type": "object"
                },
                {
                  "additionalProperties": true,
                  "properties": {
                    "code": {
                      "type": "string"
                    },
                    "message": {
                      "type": "string"
                    },
                    "type": {
                      "const": "error",
                      "type": "string"
                    }
                  },
                  "required": [
                    "type",
                    "code",
                    "message"
                  ],
                  "type": "object"
                }
              ]
            }
          },
          "required": [
            "input",
            "output"
          ],
          "type": "object"
        },
        "object": {
          "const": "response",
          "type": "string"
        },
        "output": {
          "type": "array"
        },
        "status": {
          "type": "string"
        },
        "usage": {
          "additionalProperties": true,
          "properties": {
            "input_tokens": {
              "type": "integer"
            },
            "output_tokens": {
              "type": "integer"
            },
            "total_tokens": {
              "type": "integer"
            }
          },
          "required": [
            "input_tokens",
            "output_tokens",
            "total_tokens"
          ],
          "type": "object"
        }
      },
      "required": [
        "id",
        "object",
        "status",
        "model",
        "output",
        "usage"
      ],
      "type": "object"
    },
    "type": {
      "const": "response.completed",
      "type": "string"
    }
  },
  "required": [
    "type",
    "response"
  ],
  "type": "object"
}

Exemple

JSON 
{
  "response": {
    "id": "resp_example",
    "model": "gpt-5.4",
    "moderation": {
      "input": {
        "categories": {
          "sexual": false,
          "violence": true
        },
        "category_applied_input_types": {
          "sexual": [
            "text"
          ],
          "violence": [
            "text"
          ]
        },
        "category_scores": {
          "sexual": 0.0002,
          "violence": 0.96
        },
        "flagged": true,
        "model": "omni-moderation-latest",
        "type": "moderation_result"
      },
      "output": {
        "categories": {
          "sexual": false,
          "violence": false
        },
        "category_applied_input_types": {
          "sexual": [
            "text"
          ],
          "violence": [
            "text"
          ]
        },
        "category_scores": {
          "sexual": 0.0002,
          "violence": 0.0001
        },
        "flagged": false,
        "model": "omni-moderation-latest",
        "type": "moderation_result"
      }
    },
    "object": "response",
    "output": [
      {
        "content": [
          {
            "annotations": [],
            "text": "Hello! How can I help today?",
            "type": "output_text"
          }
        ],
        "id": "msg_example",
        "role": "assistant",
        "status": "completed",
        "type": "message"
      }
    ],
    "status": "completed",
    "usage": {
      "input_tokens": 12,
      "output_tokens": 8,
      "total_tokens": 20
    }
  },
  "type": "response.completed"
}
08

Erreur de protocole : invalid_request

HTTP 400

Schéma

JSON 
{
  "additionalProperties": true,
  "properties": {
    "error": {
      "additionalProperties": true,
      "properties": {
        "code": {
          "type": [
            "string",
            "null"
          ]
        },
        "message": {
          "type": "string"
        },
        "param": {
          "type": [
            "string",
            "null"
          ]
        },
        "type": {
          "type": "string"
        }
      },
      "required": [
        "message",
        "type"
      ],
      "type": "object"
    }
  },
  "required": [
    "error"
  ],
  "type": "object"
}

Exemple

JSON 
{
  "error": {
    "code": null,
    "message": "input must be a string or an array",
    "param": "input",
    "type": "invalid_request_error"
  }
}
09

Utilisation

Schéma

JSON 
{
  "additionalProperties": true,
  "properties": {
    "input_tokens": {
      "type": "integer"
    },
    "output_tokens": {
      "type": "integer"
    },
    "total_tokens": {
      "type": "integer"
    }
  },
  "required": [
    "input_tokens",
    "output_tokens",
    "total_tokens"
  ],
  "type": "object"
}

Exemple

JSON 
{
  "input_tokens": 12,
  "output_tokens": 8,
  "total_tokens": 20
}
10

Exemples de code générés

Chaque exemple cURL, JavaScript et Python envoie la requête validée depuis ce contrat sans nécessiter de SDK spécifique au protocole.

Installer

Shell 
pip install requests
PYTHON 
import requests

response = requests.post(
    "https://runapi.ai/v1/responses",
    headers={"Authorization": "Bearer YOUR_API_TOKEN", "Content-Type": "application/json"},
    json={"model": "gpt-5.4", "input": "Summarize one practical improvement for an API deployment.", "moderation": {"model": "omni-moderation-latest", "policy": {"input": {"mode": "score"}, "output": {"mode": "block"}}}}
)
response.raise_for_status()
print(response.json())