Skip to main content
APIXO provides the official OpenAI Responses endpoint. Keep your Responses request shape and switch the base URL to https://llm.apixo.ai.

Quick Start

Non-streaming

curl -X POST "https://llm.apixo.ai/v1/responses" \
  -H "Authorization: Bearer YOUR_APIXO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "input": "Explain semantic caching in 3 bullets."
  }'

Streaming

curl -N -X POST "https://llm.apixo.ai/v1/responses" \
  -H "Authorization: Bearer YOUR_APIXO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "stream": true,
    "input": "Write a short changelog summary."
  }'

Endpoints

  • POST /v1/responses (non-stream and stream)
  • Base URL: https://llm.apixo.ai

Authentication

Authorization
string
required
Bearer token using your APIXO API key.

Supported OpenAI Responses Models

  • gpt-5.2
  • gpt-5.2-codex
  • gpt-5.3-codex
  • gpt-5.4

SDK Integration (Node.js OpenAI SDK)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.APIXO_API_KEY,
  baseURL: "https://llm.apixo.ai/v1"
});

const response = await client.responses.create({
  model: "gpt-5.4",
  input: "Summarize this sprint update in plain language."
});

console.log(response.output_text);

Error Handling and Retry

  • 401: missing or invalid API key
  • 400: invalid request body or missing required fields
  • 429: rate limit or daily quota exceeded
  • 502: upstream request failed
  • 504: upstream timeout
Recommended retry policy:
  • Retry 429/502/504 with exponential backoff
  • Do not retry 400/401 before fixing request/auth issues

Quick Reference

ItemValue
Base URLhttps://llm.apixo.ai
PathPOST /v1/responses
Stream switchrequest body stream: true
Model locationrequest body model
Auth headerAuthorization: Bearer <APIXO_KEY>