Skip to main content
POST
/
v1
/
responses
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.routeway.ai/v1",
    api_key=os.getenv("ROUTEWAY_API_KEY")
)

response = client.responses.create(
    model="gpt-4o",
    input="What is the capital of France?"
)

print(response.output_text)

{
  "id": "<string>",
  "object": "response",
  "created_at": 123,
  "completed_at": 123,
  "status": "<string>",
  "incomplete_details": {
    "reason": "<string>"
  },
  "model": "<string>",
  "previous_response_id": "<string>",
  "instructions": "<string>",
  "output": [
    {
      "type": "<string>",
      "id": "<string>",
      "content": [
        {
          "type": "<string>",
          "text": "<string>"
        }
      ]
    }
  ],
  "error": {
    "code": "<string>",
    "message": "<string>"
  },
  "tools": [
    {
      "type": "function",
      "name": "<string>",
      "description": "<string>",
      "parameters": {},
      "strict": true
    }
  ],
  "tool_choice": {
    "type": "function",
    "name": "<string>"
  },
  "parallel_tool_calls": true,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "top_p": 123,
  "presence_penalty": 123,
  "frequency_penalty": 123,
  "top_logprobs": 123,
  "temperature": 123,
  "reasoning": {},
  "usage": {
    "input_tokens": 123,
    "output_tokens": 123,
    "total_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens_details": {
      "reasoning_tokens": 123
    }
  },
  "max_output_tokens": 123,
  "max_tool_calls": 123,
  "store": true,
  "background": true,
  "service_tier": "<string>",
  "prompt_cache_key": "<string>"
}
Generate a unified response block from various input configurations. The Responses API is a higher-level alternative to Chat Completions with built-in tools and optional server-side conversation state.

​
Create Response

To create a response, use the following endpoint: POST /v1/responses

​
Request Body

​
model
string
required
The model ID to use for the response (e.g. "gpt-4o", "gpt-4o-mini"). Only models that advertise /v1/responses in their endpoints array are supported. See Models for the full list.
​
input
string | array
required
The input for the model. Can be a plain text string or an array of input items (text, image, file, etc.).
​
instructions
string
A system-level instruction that guides the model’s behavior throughout the response. Equivalent to the system message in Chat Completions.
​
max_output_tokens
integer
The maximum number of tokens to generate in the output.
​
temperature
number
Sampling temperature between 0 and 2. Higher values make output more random; lower values make it more deterministic.
​
stream
boolean
Whether to stream the response back as Server-Sent Events (SSE).
​
previous_response_id
string
The ID of a previous response to continue from. Enables multi-turn conversations without resending full message history.
​
tools
array
A list of custom tools the model may call.
​
tool_choice
string | object
Controls whether and how the model calls tools. Can be "auto", "none", "required", or an object specifying a particular tool.
​
store
boolean
Whether to store the response server-side so it can be referenced by future requests via previous_response_id. Defaults to true.
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.routeway.ai/v1",
    api_key=os.getenv("ROUTEWAY_API_KEY")
)

response = client.responses.create(
    model="gpt-4o",
    input="What is the capital of France?"
)

print(response.output_text)

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Headers

​
x-api-key
string

Body

application/json
​
model
string | null
​
input
​
previous_response_id
string | null
​
include
enum<string>[] | null
Available options:
reasoning.encrypted_content,
message.output_text.logprobs
​
tools
(FunctionToolParam · object | ResponsesToolParam · object)[] | null
​
tool_choice
​
text
TextParam · object
​
temperature
number | null
​
top_p
number | null
​
presence_penalty
number | null
​
frequency_penalty
number | null
​
parallel_tool_calls
boolean | null
​
stream
boolean | null

Whether to stream response events as server-sent events.

​
background
boolean | null

Whether to run the request in the background and return immediately.

​
max_output_tokens
integer | null
Required range: x >= 16
​
max_tool_calls
integer | null
Required range: x >= 1
​
reasoning
ReasoningParam · object
​
prompt_cache_key
string | null
Maximum string length: 64
​
truncation
enum<string> | null
Available options:
auto,
disabled
​
instructions
string | null
​
store
boolean | null

Whether to store the response so it can be retrieved later.

​
service_tier
enum<string> | null
Available options:
auto,
default,
flex,
priority
​
top_logprobs
integer | null
Required range: 0 <= x <= 20

Response

Successful Response

​
id
string
required

The unique ID of the response that was created.

​
object
enum<string>
required

The object type, which was always response.

Available options:
response
​
created_at
integer
required

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

​
completed_at
integer | null
required
​
status
string
required

The status that was set for the response.

​
incomplete_details
IncompleteDetails · object
required
​
model
string
required

The model that generated this response.

​
previous_response_id
string | null
required
​
instructions
string | null
required
​
output
(Message · object | FunctionCall · object | FunctionCallOutput · object | ReasoningBody · object | CompactionBody · object)[]
required

The output items that were generated by the model.

​
error
Error1 · object
required
​
tools
Tool · object[]
required

The tools that were available to the model during response generation.

​
tool_choice
required
​
truncation
enum<string>
required
Available options:
auto,
disabled
​
parallel_tool_calls
boolean
required

Whether the model was allowed to call multiple tools in parallel.

​
text
TextField · object
required
​
top_p
number
required

The nucleus sampling parameter that was used for this response.

​
presence_penalty
number
required

The presence penalty that was used to penalize new tokens based on whether they appear in the text so far.

​
frequency_penalty
number
required

The frequency penalty that was used to penalize new tokens based on their frequency in the text so far.

​
top_logprobs
integer
required

The number of most likely tokens that were returned at each position, along with their log probabilities.

​
temperature
number
required

The sampling temperature that was used for this response.

​
reasoning
Reasoning · object
required
​
usage
Usage · object
required
​
max_output_tokens
integer | null
required
​
max_tool_calls
integer | null
required
​
store
boolean
required

Whether this response was stored so it can be retrieved later.

​
background
boolean
required

Whether this request was run in the background.

​
service_tier
string
required

The service tier that was used for this response.

​
prompt_cache_key
string | null
required