Responses - CometAPI Documentation

POST

responses

from openai import OpenAI

client = OpenAI(
    base_url="https://api.cometapi.com/v1",
    api_key="<COMETAPI_KEY>",
)

response = client.responses.create(
    model="gpt-5.4",
    input="Tell me a three sentence bedtime story about a unicorn.",
)

print(response.output_text)

{
  "id": "resp_0a153ae8201f73bc0069a7e8044cc481",
  "object": "response",
  "created_at": 1772611588,
  "status": "completed",
  "background": false,
  "completed_at": 1772611589,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "model": "gpt-4.1-nano",
  "output": [
    {
      "id": "msg_0a153ae8201f73bc0069a7e8049a8881",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "text": "Four."
        }
      ],
      "role": "assistant"
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": null,
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "auto",
  "store": true,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [],
  "top_p": 1,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 19,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 9,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 28
  },
  "user": null,
  "metadata": {}
}

L’API Responses étend Chat Completions avec des conversations avec état, des outils intégrés, des entrées de fichiers multimodales et le contrôle du raisonnement. Il s’agit du point de terminaison recommandé pour les modèles de raisonnement OpenAI série o, la série GPT-5 et les modèles Codex.

Différents fournisseurs de modèles prennent en charge différents paramètres de requête et renvoient des champs de réponse variables. Tous les paramètres listés dans le playground ci-dessus ne fonctionnent pas avec tous les modèles sur CometAPI.

Utiliser des conversations avec état

Chaînez les réponses à l’aide de previous_response_id au lieu de gérer vous-même l’historique des messages :

from openai import OpenAI

client = OpenAI(
    base_url="https://api.cometapi.com/v1",
    api_key="<COMETAPI_KEY>",
)

# First turn
response = client.responses.create(
    model="gpt-5.4",
    input="What is quantum computing?",
)

# Second turn — previous context is included automatically
follow_up = client.responses.create(
    model="gpt-5.4",
    input="Can you explain that more simply?",
    previous_response_id=response.id,
)

print(follow_up.output_text)

Utiliser des outils intégrés

L’API Responses inclut des outils fournis par la plateforme qui ne nécessitent aucune configuration :

Outil	Objectif
`web_search_preview`	Rechercher sur le web des informations en temps réel
`file_search`	Rechercher dans des fichiers téléversés
`code_interpreter`	Exécuter du code Python dans un environnement sandbox

Pour activer un outil intégré, ajoutez-le au tableau tools :

response = client.responses.create(
    model="gpt-5.4",
    input="Find the current price of Bitcoin",
    tools=[{"type": "web_search_preview"}],
)

print(response.output_text)

Appeler des fonctions personnalisées

Définissez des fonctions que le modèle peut invoquer avec des arguments structurés :

response = client.responses.create(
    model="gpt-5.4",
    input="What's the weather in Tokyo?",
    tools=[{
        "type": "function",
        "name": "get_weather",
        "description": "Get current weather for a location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string"}
            },
            "required": ["location"]
        }
    }],
)

Lorsque le modèle appelle une fonction, le tableau de réponse output contient un élément function_call avec le nom de la fonction et les arguments analysés. Exécutez la fonction et renvoyez le résultat dans une requête de suivi.

Demander une sortie structurée

Pour forcer une sortie JSON correspondant à un schéma spécifique, utilisez le paramètre text.format :

response = client.responses.create(
    model="gpt-5.4",
    input="List 3 programming languages with their main use cases",
    text={
        "format": {
            "type": "json_schema",
            "name": "languages",
            "strict": True,
            "schema": {
                "type": "object",
                "properties": {
                    "languages": {
                        "type": "array",
                        "items": {
                            "type": "object",
                            "properties": {
                                "name": {"type": "string"},
                                "use_case": {"type": "string"}
                            },
                            "required": ["name", "use_case"],
                            "additionalProperties": False
                        }
                    }
                },
                "required": ["languages"],
                "additionalProperties": False
            }
        }
    },
)

Configurer le raisonnement

Pour les modèles de la série o et GPT-5, contrôlez la profondeur du raisonnement avec reasoning.effort :

response = client.responses.create(
    model="o3",
    input="Solve this step by step: if f(x) = x^3 - 6x^2 + 11x - 6, find all roots.",
    reasoning={"effort": "high"},  # "low", "medium", or "high"
)

print(response.output_text)

Un effort de raisonnement plus élevé produit des réponses plus approfondies mais utilise davantage de tokens. Utilisez "low" pour les requêtes simples et "high" pour les problèmes complexes en plusieurs étapes.

Diffuser les réponses en Streaming

Pour recevoir une sortie incrémentale, définissez stream sur true. L’API envoie des événements server-sent events (SSE) dans cet ordre :

response.created — Objet Response initialisé
response.in_progress — Génération démarrée
response.output_item.added — Nouvel élément de sortie (message ou appel d’outil)
response.content_part.added — Partie de contenu démarrée
response.output_text.delta — Segment de texte (contient le champ delta)
response.output_text.done — Génération de texte terminée pour cette partie de contenu
response.content_part.done — Partie de contenu terminée
response.output_item.done — Élément de sortie terminé
response.completed — Réponse complète avec les données usage

Diffuser une réponse en Streaming avec le SDK Python :

stream = client.responses.create(
    model="gpt-5.4",
    input="Write a haiku about coding",
    stream=True,
)

for event in stream:
    if event.type == "response.output_text.delta":
        print(event.delta, end="")

Pour des guides détaillés sur chaque capacité, consultez la documentation OpenAI : Texte · Images · Fichiers PDF · Structured Outputs · Function Calling · État de la conversation · Outils intégrés · Reasoning

Autorisations

Authorization

string

header

requis

Bearer token authentication. Use your CometAPI key.

Corps

application/json

model

string

requis

Model ID to use for this request. See the Models page for current options.

Exemple:

"gpt-5.4"

input

requis

Text, image, or file inputs to the model, used to generate a response. Can be a simple string for text-only input, or an array of input items for multimodal content (images, files) and multi-turn conversations.

instructions

string

A system (or developer) message inserted into the model's context. When used with previous_response_id, instructions from the previous response are not carried over — this makes it easy to swap system messages between turns.

background

boolean

défaut:false

Whether to run the model response in the background. Background responses do not return output directly — you retrieve the result later via the response ID.

context_management

object[]

Context management configuration for this request. Controls how the model manages context when the conversation exceeds the context window.

Show child attributes

conversation

The conversation this response belongs to. Items from the conversation are prepended to input for context. Input and output items are automatically added to the conversation after the response completes. Cannot be used with previous_response_id.

include

enum<string>[]

Additional output data to include in the response. Use this to request extra information that is not included by default.

Options disponibles:

web_search_call.action.sources,

code_interpreter_call.outputs,

computer_call_output.output.image_url,

file_search_call.results,

message.input_image.image_url,

message.output_text.logprobs,

reasoning.encrypted_content

max_output_tokens

integer

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

max_tool_calls

integer

The maximum number of total calls to built-in tools that can be processed in a response. This limit applies across all built-in tool calls, not per individual tool. Any further tool call attempts by the model will be ignored.

metadata

object

Set of up to 16 key-value pairs that can be attached to the response. Useful for storing additional information in a structured format. Keys have a maximum length of 64 characters; values have a maximum length of 512 characters.

Show child attributes

parallel_tool_calls

boolean

défaut:true

Whether to allow the model to run tool calls in parallel.

previous_response_id

string

The unique ID of a previous response. Use this to create multi-turn conversations without manually managing conversation state. Cannot be used with conversation.

prompt

object

Reference to a prompt template and its variables.

Show child attributes

prompt_cache_key

string

A key used to cache responses for similar requests, helping optimize cache hit rates. Replaces the deprecated user field for caching purposes.

prompt_cache_retention

enum<string>

The retention policy for the prompt cache. Set to 24h to keep cached prefixes active for up to 24 hours.

Options disponibles:

in-memory,

24h

reasoning

object

Configuration options for reasoning models (o-series and gpt-5). Controls the depth of reasoning before generating a response.

Show child attributes

safety_identifier

string

A stable identifier for your end-users, used to help detect policy violations. Should be a hashed username or email — do not send identifying information directly.

Maximum string length: 64

service_tier

enum<string>

Specifies the processing tier for the request. When set, the response will include the actual service_tier used.

auto: Uses the tier configured in project settings (default behavior).
default: Standard pricing and performance.
flex: Flexible processing with potential cost savings.
priority: Priority processing with faster response times.

Options disponibles:

auto,

default,

flex,

priority

store

boolean

défaut:true

Whether to store the generated response for later retrieval via API.

stream

boolean

défaut:false

If set to true, the response data will be streamed to the client as it is generated using server-sent events (SSE). Events include response.created, response.output_text.delta, response.completed, and more.

stream_options

object

Options for streaming responses. Only set this when stream is true.

Show child attributes

temperature

number

défaut:1

Sampling temperature between 0 and 2. Higher values (e.g., 0.8) increase randomness; lower values (e.g., 0.2) make output more focused and deterministic. We recommend adjusting either this or top_p, but not both.

Plage requise: 0 <= x <= 2

text

object

Configuration for text output. Use this to request structured JSON output via JSON mode or JSON Schema.

Show child attributes

tool_choice

défaut:auto

Controls how the model selects which tool(s) to call.

auto (default): The model decides whether and which tools to call.
none: The model will not call any tools.
required: The model must call at least one tool.
An object specifying a particular tool to use.

tools

object[]

An array of tools the model may call while generating a response. CometAPI supports three categories:

Built-in tools: Platform-provided tools like web_search_preview and file_search.
Function calls: Custom functions you define, enabling the model to call your own code with structured arguments.
MCP tools: Integrations with third-party systems via MCP servers.

top_logprobs

integer

Number of most likely tokens to return at each position (0–20), each with an associated log probability. Must include message.output_text.logprobs in the include parameter to receive logprobs.

Plage requise: 0 <= x <= 20

top_p

number

défaut:1

Nucleus sampling parameter. The model considers tokens with top_p cumulative probability mass. For example, 0.1 means only the top 10% probability tokens are considered. We recommend adjusting either this or temperature, but not both.

Plage requise: 0 <= x <= 1

truncation

enum<string>

défaut:disabled

The truncation strategy for handling inputs that exceed the model's context window.

auto: The model truncates the input by dropping items from the beginning of the conversation to fit.
disabled (default): The request fails with a 400 error if the input exceeds the context window.

Options disponibles:

auto,

disabled

user

string

obsolète

Deprecated. Use safety_identifier and prompt_cache_key instead. A stable identifier for your end-user.

Réponse

200 - application/json

The generated Response object.

string

Unique identifier for the response.

Exemple:

"resp_0a153ae8201f73bc0069a7e8044cc481"

object

enum<string>

The object type, always response.

Options disponibles:

response

Exemple:

"response"

created_at

integer

Unix timestamp (in seconds) of when the response was created.

Exemple:

1772611588

status

enum<string>

The status of the response.

Options disponibles:

completed,

in_progress,

failed,

cancelled,

queued

Exemple:

"completed"

background

boolean

Whether the response was run in the background.

Exemple:

false

completed_at

integer | null

Unix timestamp of when the response was completed, or null if still in progress.

Exemple:

1772611589

error

object

Error information if the response failed, or null on success.

Show child attributes

incomplete_details

object

Details about why the response is incomplete, if applicable.

Show child attributes

instructions

string | null

The system instructions used for this response.

max_output_tokens

integer | null

The maximum output token limit that was applied.

model

string

The model used for the response.

Exemple:

"gpt-4.1-nano"

output

object[]

An array of output items generated by the model. Each item can be a message, function call, or other output type.

Show child attributes

output_text

string

A convenience field containing the concatenated text output from all output message items.

parallel_tool_calls

boolean

Whether parallel tool calls were enabled.

previous_response_id

string | null

The ID of the previous response, if this is a multi-turn conversation.

reasoning

object

The reasoning configuration that was used.

Show child attributes

service_tier

string

The service tier actually used to process the request.

Exemple:

"default"

store

boolean

Whether the response was stored.

temperature

number

The temperature value used.

Exemple:

1

text

object

The text configuration used.

Show child attributes

tool_choice

The tool choice setting used.

tools

object[]

The tools that were available for this response.

top_p

number

The top_p value used.

Exemple:

1

truncation

string

The truncation strategy used.

usage

object

Token usage statistics for this response.

Show child attributes

user

string | null

The user identifier, if provided.

metadata

object

The metadata attached to this response.

Show child attributes

content_filters

array | null

Content filter results applied to the response, if any.

frequency_penalty

number

défaut:0

The frequency penalty applied to the request.

max_tool_calls

integer | null

Maximum number of tool calls allowed, if set.

presence_penalty

number

défaut:0

The presence penalty applied to the request.

prompt_cache_key

string | null

Cache key for prompt caching, if applicable.

prompt_cache_retention

string | null

Prompt cache retention policy, if applicable.

safety_identifier

string | null

Safety system identifier for the response, if applicable.

top_logprobs

integer

défaut:0

Number of top log probabilities returned per token position.

Chat Completions

Anthropic Messages

from openai import OpenAI

client = OpenAI(
    base_url="https://api.cometapi.com/v1",
    api_key="<COMETAPI_KEY>",
)

response = client.responses.create(
    model="gpt-5.4",
    input="Tell me a three sentence bedtime story about a unicorn.",
)

print(response.output_text)

{
  "id": "resp_0a153ae8201f73bc0069a7e8044cc481",
  "object": "response",
  "created_at": 1772611588,
  "status": "completed",
  "background": false,
  "completed_at": 1772611589,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "model": "gpt-4.1-nano",
  "output": [
    {
      "id": "msg_0a153ae8201f73bc0069a7e8049a8881",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "text": "Four."
        }
      ],
      "role": "assistant"
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": null,
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "auto",
  "store": true,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [],
  "top_p": 1,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 19,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 9,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 28
  },
  "user": null,
  "metadata": {}
}

Documentation Index

​Utiliser des conversations avec état

​Utiliser des outils intégrés

​Appeler des fonctions personnalisées

​Demander une sortie structurée

​Configurer le raisonnement

​Diffuser les réponses en Streaming

Autorisations

Corps

Réponse

Utiliser des conversations avec état

Utiliser des outils intégrés

Appeler des fonctions personnalisées

Demander une sortie structurée

Configurer le raisonnement

Diffuser les réponses en Streaming