Responses - Portrix docs

OpenAI-compatible Responses API on PipeLLM

Endpoint

POST https://api.portix.ai/v1/responses

This free route accepts OpenAI Responses requests and routes only to OpenAI-compatible platforms. Cross-protocol routing for the Responses API is not available yet. If you need cross-protocol routing today, use the OpenAI Format Converter with Chat Completions.

Code Examples

cURL
Python
TypeScript

curl https://api.portix.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -d '{
    "model": "gpt-4.1",
    "input": "Write a one-sentence explanation of why the sky is blue."
  }'

import os
from openai import OpenAI

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

response = client.responses.create(
  model="gpt-4.1",
  input="Write a one-sentence explanation of why the sky is blue."
)

print(response.output_text)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.YOUR_API_KEY,
  baseURL: "https://api.portix.ai/v1",
});

const response = await client.responses.create({
  model: "gpt-4.1",
  input: "Write a one-sentence explanation of why the sky is blue.",
});

console.log(response.output_text);

Common Request Fields

Field	Type	Required	Description
`model`	string	Yes	OpenAI-compatible model ID
`input`	string or array	Yes	Text or structured input items
`instructions`	string	No	Developer or system instruction
`stream`	boolean	No	Enable streaming output
`tools`	array	No	Built-in or custom tools
`temperature`	number	No	Sampling temperature
`max_output_tokens`	integer	No	Maximum output tokens

Response Shape

{
  "id": "resp_123",
  "object": "response",
  "model": "gpt-4.1",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "The atmosphere scatters blue light more strongly than red light."
        }
      ]
    }
  ]
}

⌘I