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 estende Chat Completions con conversazioni con stato, strumenti integrati, input di file multimodali e controllo del ragionamento. È l’endpoint consigliato per i modelli di ragionamento OpenAI serie o, serie GPT-5 e modelli Codex.

Provider di modelli diversi supportano parametri di richiesta diversi e restituiscono campi di risposta variabili. Non tutti i parametri elencati nel playground sopra funzionano con ogni modello su CometAPI.

Usa conversazioni con stato

Concatena le risposte usando previous_response_id invece di gestire personalmente la cronologia dei messaggi:

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)

Usa strumenti integrati

L’API Responses include strumenti forniti dalla piattaforma che non richiedono alcuna configurazione:

Tool	Scopo
`web_search_preview`	Cerca sul web informazioni in tempo reale
`file_search`	Cerca tra i file caricati
`code_interpreter`	Esegue codice Python in un ambiente sandbox

Per abilitare uno strumento integrato, aggiungilo all’array 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)

Chiama funzioni personalizzate

Definisci funzioni che il modello può invocare con argomenti strutturati:

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"]
        }
    }],
)

Quando il modello chiama una funzione, l’array output della risposta contiene un elemento function_call con il nome della funzione e gli argomenti analizzati. Esegui la funzione e rimanda il risultato in una richiesta successiva.

Richiedi output strutturato

Per forzare un output JSON che corrisponda a uno schema specifico, usa il parametro 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
            }
        }
    },
)

Configurare il reasoning

Per i modelli della serie o e GPT-5, controlla la profondità del reasoning con 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 di reasoning più elevato produce risposte più approfondite ma usa più token. Usa "low" per query semplici e "high" per problemi complessi in più passaggi.

Trasmettere le risposte in Streaming

Per ricevere output incrementale, imposta stream su true. L’API invia eventi server-sent (SSE) in questo ordine:

response.created — Oggetto Response inizializzato
response.in_progress — Generazione avviata
response.output_item.added — Nuovo elemento di output (messaggio o chiamata a tool)
response.content_part.added — Parte di contenuto avviata
response.output_text.delta — Blocco di testo (contiene il campo delta)
response.output_text.done — Generazione del testo completata per questa parte di contenuto
response.content_part.done — Parte di contenuto terminata
response.output_item.done — Elemento di output terminato
response.completed — Response completa con dati usage

Trasmetti una risposta in Streaming con l’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="")

Per guide approfondite su ciascuna funzionalità, consulta la documentazione OpenAI: Text · Images · PDF files · Structured Outputs · Function Calling · Conversation State · Built-in Tools · Reasoning

Autorizzazioni

Authorization

string

header

obbligatorio

Bearer token authentication. Use your CometAPI key.

Corpo

application/json

model

string

obbligatorio

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

Esempio:

"gpt-5.4"

input

obbligatorio

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

predefinito: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.

Opzioni disponibili:

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

predefinito: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.

Opzioni disponibili:

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.

Opzioni disponibili:

auto,

default,

flex,

priority

store

boolean

predefinito:true

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

stream

boolean

predefinito: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

predefinito: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.

Intervallo richiesto: 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

predefinito: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.

Intervallo richiesto: 0 <= x <= 20

top_p

number

predefinito: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.

Intervallo richiesto: 0 <= x <= 1

truncation

enum<string>

predefinito: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.

Opzioni disponibili:

auto,

disabled

user

string

deprecato

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

Risposta

200 - application/json

The generated Response object.

string

Unique identifier for the response.

Esempio:

"resp_0a153ae8201f73bc0069a7e8044cc481"

object

enum<string>

The object type, always response.

Opzioni disponibili:

response

Esempio:

"response"

created_at

integer

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

Esempio:

1772611588

status

enum<string>

The status of the response.

Opzioni disponibili:

completed,

in_progress,

failed,

cancelled,

queued

Esempio:

"completed"

background

boolean

Whether the response was run in the background.

Esempio:

false

completed_at

integer | null

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

Esempio:

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.

Esempio:

"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.

Esempio:

"default"

store

boolean

Whether the response was stored.

temperature

number

The temperature value used.

Esempio:

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.

Esempio:

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

predefinito:0

The frequency penalty applied to the request.

max_tool_calls

integer | null

Maximum number of tool calls allowed, if set.

presence_penalty

number

predefinito: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

predefinito: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

​Usa conversazioni con stato

​Usa strumenti integrati

​Chiama funzioni personalizzate

​Richiedi output strutturato

​Configurare il reasoning

​Trasmettere le risposte in Streaming

Autorizzazioni

Corpo

Risposta

Usa conversazioni con stato

Usa strumenti integrati

Chiama funzioni personalizzate

Richiedi output strutturato

Configurare il reasoning

Trasmettere le risposte in Streaming