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)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.routeway.ai/v1",
apiKey: process.env.ROUTEWAY_API_KEY,
});
const response = await client.responses.create({
model: "gpt-4o",
input: "What is the capital of France?",
});
console.log(response.output_text);
curl https://api.routeway.ai/v1/responses \
-H "Authorization: Bearer $ROUTEWAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"input": "What is the capital of France?"
}'
{
"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": "message",
"id": "<string>",
"status": "in_progress",
"role": "user",
"content": [
{
"type": "input_text",
"text": "<string>"
}
],
"phase": "commentary"
}
],
"error": {
"code": "<string>",
"message": "<string>"
},
"tools": [
{
"type": "function",
"name": "<string>",
"description": "<string>",
"parameters": {},
"strict": true
}
],
"tool_choice": {
"type": "function",
"name": "<string>"
},
"truncation": "auto",
"parallel_tool_calls": true,
"text": {
"format": {
"type": "text"
},
"verbosity": "low"
},
"top_p": 123,
"presence_penalty": 123,
"frequency_penalty": 123,
"top_logprobs": 123,
"temperature": 123,
"reasoning": {
"effort": "none",
"summary": "concise"
},
"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>"
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}API Reference
Responses
Generate a unified response block from various input configurations.
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)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.routeway.ai/v1",
apiKey: process.env.ROUTEWAY_API_KEY,
});
const response = await client.responses.create({
model: "gpt-4o",
input: "What is the capital of France?",
});
console.log(response.output_text);
curl https://api.routeway.ai/v1/responses \
-H "Authorization: Bearer $ROUTEWAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"input": "What is the capital of France?"
}'
{
"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": "message",
"id": "<string>",
"status": "in_progress",
"role": "user",
"content": [
{
"type": "input_text",
"text": "<string>"
}
],
"phase": "commentary"
}
],
"error": {
"code": "<string>",
"message": "<string>"
},
"tools": [
{
"type": "function",
"name": "<string>",
"description": "<string>",
"parameters": {},
"strict": true
}
],
"tool_choice": {
"type": "function",
"name": "<string>"
},
"truncation": "auto",
"parallel_tool_calls": true,
"text": {
"format": {
"type": "text"
},
"verbosity": "low"
},
"top_p": 123,
"presence_penalty": 123,
"frequency_penalty": 123,
"top_logprobs": 123,
"temperature": 123,
"reasoning": {
"effort": "none",
"summary": "concise"
},
"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>"
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"status_code": 123,
"id": "<string>",
"param": "<string>",
"code": "<string>",
"tip": "<string>",
"docs": "https://docs.routeway.ai",
"support": "https://discord.gg/RjX2CpdPpd",
"community": {}
}
}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
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.string | array
required
The input for the model. Can be a plain text string or an array of input items (text,
image, file, etc.).
string
A system-level instruction that guides the model’s behavior throughout the response.
Equivalent to the
system message in Chat Completions.integer
The maximum number of tokens to generate in the output.
number
Sampling temperature between 0 and 2. Higher values make output more random; lower values
make it more deterministic.
boolean
Whether to stream the response back as Server-Sent Events (SSE).
string
The ID of a previous response to continue from. Enables multi-turn conversations without
resending full message history.
array
A list of custom tools the model may call.
string | object
Controls whether and how the model calls tools. Can be
"auto", "none", "required",
or an object specifying a particular tool.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)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.routeway.ai/v1",
apiKey: process.env.ROUTEWAY_API_KEY,
});
const response = await client.responses.create({
model: "gpt-4o",
input: "What is the capital of France?",
});
console.log(response.output_text);
curl https://api.routeway.ai/v1/responses \
-H "Authorization: Bearer $ROUTEWAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"input": "What is the capital of France?"
}'
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Headers
Body
application/json
input
(ItemReferenceParam · object | ReasoningItemParam · object | CompactionSummaryItemParam · object | UserMessageItemParam · object | SystemMessageItemParam · object | DeveloperMessageItemParam · object | AssistantMessageItemParam · object | FunctionCallItemParam · object | FunctionCallOutputItemParam · object)[]string
- ItemReferenceParam
- ReasoningItemParam
- CompactionSummaryItemParam
- UserMessageItemParam
- SystemMessageItemParam
- DeveloperMessageItemParam
- AssistantMessageItemParam
- FunctionCallItemParam
- FunctionCallOutputItemParam
Show child attributes
Show child attributes
Available options:
reasoning.encrypted_content, message.output_text.logprobs - FunctionToolParam
- ResponsesToolParam
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Whether to stream response events as server-sent events.
Whether to run the request in the background and return immediately.
Required range:
x >= 16Required range:
x >= 1Show child attributes
Show child attributes
Maximum string length:
64Available options:
auto, disabled Whether to store the response so it can be retrieved later.
Available options:
auto, default, flex, priority Required range:
0 <= x <= 20Response
Successful Response
The unique ID of the response that was created.
The object type, which was always response.
Available options:
response The Unix timestamp (in seconds) for when the response was created.
The status that was set for the response.
Show child attributes
Show child attributes
The model that generated this response.
output
(Message · object | FunctionCall · object | FunctionCallOutput · object | ReasoningBody · object | CompactionBody · object)[]
required
The output items that were generated by the model.
- Message
- FunctionCall
- FunctionCallOutput
- ReasoningBody
- CompactionBody
Show child attributes
Show child attributes
Show child attributes
Show child attributes
The tools that were available to the model during response generation.
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Available options:
auto, disabled Whether the model was allowed to call multiple tools in parallel.
Show child attributes
Show child attributes
The nucleus sampling parameter that was used for this response.
The presence penalty that was used to penalize new tokens based on whether they appear in the text so far.
The frequency penalty that was used to penalize new tokens based on their frequency in the text so far.
The number of most likely tokens that were returned at each position, along with their log probabilities.
The sampling temperature that was used for this response.
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Whether this response was stored so it can be retrieved later.
Whether this request was run in the background.
The service tier that was used for this response.
Was this page helpful?