Responses

Verwenden Sie CometAPI POST /v1/responses, um erweiterte Modellausgaben mit multimodalem Input, zustandsbehaftetem Chat, integrierten Tools und Function Calling zu erzeugen.

POST /v1/responses

Python

Text Input

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)

200

{
  "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": {}
}

​

Überblick

Die Responses API ist CometAPIs erweiterter Endpoint zur Generierung von Modellantworten. Sie bietet eine umfangreichere Schnittstelle als Chat Completions, mit integrierter Unterstützung für multimodale Inputs, zustandsbehaftete Konversationen, Tool-Integration und strukturierte Ausgaben — alles über einen einzigen Endpoint.

​

Zentrale Funktionen

• Multimodaler Input — Akzeptiert Text, Bilder, Dateien (einschließlich PDFs) und URLs als Input
• Zustandsbehaftete Konversationen — Verketten Sie Antworten mit previous_response_id oder conversation, ohne den Nachrichtenverlauf selbst verwalten zu müssen
• Integrierte Tools — Verwenden Sie web_search_preview, file_search, code_interpreter und mehr ohne jegliches Setup
• Function Calling — Definieren Sie benutzerdefinierte Funktionen, die das Modell mit strukturierten Argumenten aufrufen kann
• Strukturierte Ausgaben — Fordern Sie über den Parameter text.format eine JSON-Schema-konforme Ausgabe an
• Reasoning Models — Konfigurieren Sie die Reasoning-Tiefe mit dem Parameter reasoning.effort für o-series- und gpt-5-Modelle
• Streaming — Streamen Sie Antworten über SSE mit granularen Event-Typen (response.output_text.delta, response.completed usw.)

​

Wichtige Hinweise

Modellvarianten — Verschiedene Modellanbieter unterstützen möglicherweise unterschiedliche Anfrageparameter und geben abweichende Antwortfelder zurück. Nicht alle Parameter werden von jedem auf CometAPI verfügbaren Modell unterstützt.

Pass-through-Prinzip — CometAPI leitet Anfragen an Modellanbieter weiter und gibt deren Antworten unverändert zurück, damit Sie Ausgaben erhalten, die mit der ursprünglichen API konsistent sind. Das Antwortobjekt spiegelt viele Anfrageparameter (wie temperature, tools, reasoning) aus Transparenzgründen wider.

​

Streaming-Events

Wenn stream auf true gesetzt ist, sendet die API Server-Sent Events (SSE) in dieser Reihenfolge:

1. response.created — Antwortobjekt initialisiert
2. response.in_progress — Generierung gestartet
3. response.output_item.added — Neues Ausgabeelement (Nachricht oder Tool-Aufruf)
4. response.content_part.added — Inhaltsteil gestartet
5. response.output_text.delta — Textabschnitt (enthält das Feld delta mit dem Textfragment)
6. response.output_text.done — Textgenerierung für diesen Inhaltsteil abgeschlossen
7. response.content_part.done — Inhaltsteil abgeschlossen
8. response.output_item.done — Ausgabeelement abgeschlossen
9. response.completed — Vollständige Antwort mit usage-Daten

​

Referenzdokumentation

Detaillierte Parameterbeschreibungen finden Sie im interaktiven API-Playground oben. Dokumentation der Anbieter:

• Text Inputs and Outputs
• Image Inputs
• File Inputs (PDF)
• Structured Outputs
• Function Calling
• Conversation State
• Built-in Tools
• Reasoning Models

---

Autorisierungen

Authorization · string · header · erforderlich

Bearer token authentication. Use your CometAPI key.

Body

application/json

model · string · erforderlich

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

Beispiel:

"gpt-5.4"

input · string object[] · erforderlich

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 · Standard: 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 · string object

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.

Verfügbare Optionen: 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 · Standard: 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.

Verfügbare Optionen: 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.

Verfügbare Optionen: auto, default, flex, priority

store · boolean · Standard: true

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

stream · boolean · Standard: 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 · Standard: 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.

Erforderlicher Bereich: 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 · string object · Standard: 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.

Erforderlicher Bereich: 0 <= x <= 20

top_p · number · Standard: 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.

Erforderlicher Bereich: 0 <= x <= 1

truncation · enum<string> · Standard: 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.

Verfügbare Optionen: auto, disabled

user · string · veraltet

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

Antwort

200 - application/json

The generated Response object.

id · string

Unique identifier for the response.

Beispiel:

"resp_0a153ae8201f73bc0069a7e8044cc481"

object · enum<string>

The object type, always response.

Verfügbare Optionen: response

Beispiel:

"response"

created_at · integer

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

Beispiel:

1772611588

status · enum<string>

The status of the response.

Verfügbare Optionen: completed, in_progress, failed, cancelled, queued

Beispiel:

"completed"

background · boolean

Whether the response was run in the background.

Beispiel:

false

completed_at · integer | null

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

Beispiel:

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.

Beispiel:

"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.

Beispiel:

"default"

store · boolean

Whether the response was stored.

temperature · number

The temperature value used.

Beispiel:

1

text · object

The text configuration used.

Show child attributes

tool_choice · string object

The tool choice setting used.

tools · object[]

The tools that were available for this response.

top_p · number

The top_p value used.

Beispiel:

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 · Standard: 0

The frequency penalty applied to the request.

max_tool_calls · integer | null

Maximum number of tool calls allowed, if set.

presence_penalty · number · Standard: 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 · Standard: 0

Number of top log probabilities returned per token position.