API Reference
Integration Guides
Libraries
Errors
Pricing & Billing
Text Models
Responses
Use CometAPI POST /v1/responses to generate advanced model outputs with multimodal input, stateful chat, built-in tools, and function calling.
POST
/
v1
/
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": {}
}The Responses API extends Chat Completions with stateful conversations, built-in tools, multimodal file inputs, and reasoning control. It is the recommended endpoint for OpenAI o-series reasoning models, GPT-5 series, and Codex models.Documentation Index
Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt
Use this file to discover all available pages before exploring further.
Different model providers support different request parameters and return varying response fields. Not all parameters listed in the playground above work with every model on CometAPI.
Use stateful conversations
Chain responses together usingprevious_response_id instead of managing message history yourself:
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)
Use built-in tools
The Responses API includes platform-provided tools that require no configuration:| Tool | Purpose |
|---|---|
web_search_preview | Search the web for real-time information |
file_search | Search through uploaded files |
code_interpreter | Execute Python code in a sandbox |
tools array:
response = client.responses.create(
model="gpt-5.4",
input="Find the current price of Bitcoin",
tools=[{"type": "web_search_preview"}],
)
print(response.output_text)
Call custom functions
Define functions the model can invoke with structured arguments: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"]
}
}],
)
output array contains a function_call item with the function name and parsed arguments. Execute the function and send the result back in a follow-up request.
Request structured output
To force JSON output matching a specific schema, use thetext.format parameter:
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
}
}
},
)
Configure reasoning
For o-series and GPT-5 models, control reasoning depth withreasoning.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)
Higher reasoning effort produces more thorough answers but uses more tokens. Use
"low" for simple queries and "high" for complex multi-step problems.Stream responses
To receive incremental output, setstream to true. The API sends server-sent events (SSE) in this order:
response.created— Response object initializedresponse.in_progress— Generation startedresponse.output_item.added— New output item (message or tool call)response.content_part.added— Content part startedresponse.output_text.delta— Text chunk (containsdeltafield)response.output_text.done— Text generation complete for this content partresponse.content_part.done— Content part finishedresponse.output_item.done— Output item finishedresponse.completed— Full response withusagedata
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="")
For in-depth guides on each capability, see the OpenAI documentation:
Text · Images · PDF files · Structured Outputs · Function Calling · Conversation State · Built-in Tools · Reasoning
Authorizations
Bearer token authentication. Use your CometAPI key.
Body
application/json
Model ID to use for this request. See the Models page for current options.
Example:
"gpt-5.4"
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.
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.
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 configuration for this request. Controls how the model manages context when the conversation exceeds the context window.
Show child attributes
Show child attributes
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.
Additional output data to include in the response. Use this to request extra information that is not included by default.
Available options:
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 An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
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.
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
Show child attributes
Whether to allow the model to run tool calls in parallel.
The unique ID of a previous response. Use this to create multi-turn conversations without manually managing conversation state. Cannot be used with conversation.
Reference to a prompt template and its variables.
Show child attributes
Show child attributes
A key used to cache responses for similar requests, helping optimize cache hit rates. Replaces the deprecated user field for caching purposes.
The retention policy for the prompt cache. Set to 24h to keep cached prefixes active for up to 24 hours.
Available options:
in-memory, 24h Configuration options for reasoning models (o-series and gpt-5). Controls the depth of reasoning before generating a response.
Show child attributes
Show child attributes
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:
64Specifies 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.
Available options:
auto, default, flex, priority Whether to store the generated response for later retrieval via API.
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.
Options for streaming responses. Only set this when stream is true.
Show child attributes
Show child attributes
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.
Required range:
0 <= x <= 2Configuration for text output. Use this to request structured JSON output via JSON mode or JSON Schema.
Show child attributes
Show child attributes
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.
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_previewandfile_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.
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.
Required range:
0 <= x <= 20Nucleus 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.
Required range:
0 <= x <= 1The 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.
Available options:
auto, disabled Deprecated. Use safety_identifier and prompt_cache_key instead. A stable identifier for your end-user.
Response
200 - application/json
The generated Response object.
Unique identifier for the response.
Example:
"resp_0a153ae8201f73bc0069a7e8044cc481"
The object type, always response.
Available options:
response Example:
"response"
Unix timestamp (in seconds) of when the response was created.
Example:
1772611588
The status of the response.
Available options:
completed, in_progress, failed, cancelled, queued Example:
"completed"
Whether the response was run in the background.
Example:
false
Unix timestamp of when the response was completed, or null if still in progress.
Example:
1772611589
Error information if the response failed, or null on success.
Show child attributes
Show child attributes
Details about why the response is incomplete, if applicable.
Show child attributes
Show child attributes
The system instructions used for this response.
The maximum output token limit that was applied.
The model used for the response.
Example:
"gpt-4.1-nano"
An array of output items generated by the model. Each item can be a message, function call, or other output type.
Show child attributes
Show child attributes
A convenience field containing the concatenated text output from all output message items.
Whether parallel tool calls were enabled.
The ID of the previous response, if this is a multi-turn conversation.
The reasoning configuration that was used.
Show child attributes
Show child attributes
The service tier actually used to process the request.
Example:
"default"
Whether the response was stored.
The temperature value used.
Example:
1
The text configuration used.
Show child attributes
Show child attributes
The tool choice setting used.
The tools that were available for this response.
The top_p value used.
Example:
1
The truncation strategy used.
Token usage statistics for this response.
Show child attributes
Show child attributes
The user identifier, if provided.
The metadata attached to this response.
Show child attributes
Show child attributes
Content filter results applied to the response, if any.
The frequency penalty applied to the request.
Maximum number of tool calls allowed, if set.
The presence penalty applied to the request.
Cache key for prompt caching, if applicable.
Prompt cache retention policy, if applicable.
Safety system identifier for the response, if applicable.
Number of top log probabilities returned per token position.
⌘I
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": {}
}