Skip to main content
APIXO provides the official Google Gemini endpoints. Keep your Gemini request shape and switch the base URL to https://llm.apixo.ai.

Quick Start

Non-streaming

curl -X POST "https://llm.apixo.ai/v1beta/models/gemini-3.1-pro-preview:generateContent" \
  -H "x-goog-api-key: YOUR_APIXO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [{"text": "Explain function calling in Gemini."}]
      }
    ]
  }'

Streaming

curl -N -X POST "https://llm.apixo.ai/v1beta/models/gemini-3.1-pro-preview:streamGenerateContent" \
  -H "x-goog-api-key: YOUR_APIXO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [{"text": "Stream a concise architecture review."}]
      }
    ]
  }'

Endpoints

  • POST /v1beta/models/{model}:generateContent
  • POST /v1beta/models/{model}:streamGenerateContent
  • Base URL: https://llm.apixo.ai

Authentication

x-goog-api-key
string
required
Your APIXO API key.
?key= query auth is not recommended and is disabled by default in production configuration.

Supported Gemini Models

  • gemini-2.5-pro
  • gemini-3-pro-preview
  • gemini-3.1-pro-preview

SDK Integration (JavaScript fetch)

const model = "gemini-3.1-pro-preview";
const response = await fetch(
  `https://llm.apixo.ai/v1beta/models/${model}:generateContent`,
  {
    method: "POST",
    headers: {
      "x-goog-api-key": process.env.APIXO_API_KEY,
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      contents: [
        {
          role: "user",
          parts: [{ text: "Give me 3 rollout risk checks." }]
        }
      ]
    })
  }
);

const data = await response.json();
console.log(data);

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
Non-stream pathPOST /v1beta/models/{model}:generateContent
Stream pathPOST /v1beta/models/{model}:streamGenerateContent
Stream switchpath-based (separate stream endpoint)
Model locationURL path {model}
Auth headerx-goog-api-key