Documentation

ARXON AI is an OpenAI-compatible API gateway. Integrate in minutes using any OpenAI SDK.

Overview

Arxon exposes a single base URL compatible with any OpenAI SDK. Change your base URL and API key — everything else stays the same.

Base URL
https://arxon.armanxai.com/api/v1

Authentication

Get your API key from the dashboard. Pass it in one of two ways:

bash
# Option 1 — Authorization header (recommended)
Authorization: Bearer sk-arxon-your-key-here

# Option 2 — X-API-Key header
X-API-Key: sk-arxon-your-key-here

Chat Completions

POST /api/v1/chat/completions
bash
curl https://arxon.armanxai.com/api/v1/chat/completions \
  -H "Authorization: Bearer sk-arxon-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "arxon-main",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user", "content": "What is 2 + 2?" }
    ]
  }'

Response:

json
{
  "id": "arxon-abc123",
  "object": "chat.completion",
  "model": "arxon-main",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "2 + 2 = 4" },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 540,
    "completion_tokens": 11,
    "total_tokens": 551
  }
}

List Models

bash
curl https://arxon.armanxai.com/api/v1/models \
  -H "Authorization: Bearer sk-arxon-..."

Python

python
import openai

client = openai.OpenAI(
    api_key="sk-arxon-your-key",
    base_url="https://arxon.armanxai.com/api/v1"
)

response = client.chat.completions.create(
    model="arxon-main",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

JavaScript

javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-arxon-your-key",
  baseURL: "https://arxon.armanxai.com/api/v1",
});

const res = await client.chat.completions.create({
  model: "arxon-main",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(res.choices[0].message.content);

Claude Code

Point Claude Code at Arxon's endpoint to use Arxon models inside your terminal and IDE.

1. Install Claude Code

bash
npm install -g @anthropic-ai/claude-code

2. Set Arxon as endpoint

bash
export ANTHROPIC_API_KEY=sk-arxon-your-key-here
export ANTHROPIC_BASE_URL=https://arxon.armanxai.com/api/v1

3. Run Claude Code

bash
claude
# or
claude "explain this codebase"

4. VS Code settings.json

json
{
  "claude.apiKey": "sk-arxon-your-key-here",
  "claude.baseUrl": "https://arxon.armanxai.com/api/v1",
  "claude.model": "arxon-main"
}

Rate Limits

Understanding Rate Limits

Rate limits are measured in:

  • RPMRequests per minute
  • RPDRequests per day
  • RPKRequests per API Key
  • TPMTokens per minute
  • TPDTokens per day
  • TPKTokens per API Key

Chat Rate Limit

MODEL IDRPMRPDTPMTPD
arxon/main101006,00060,000
arxon/agentic1010012,000120,000
arxon/r11010012,000120,000
arxon/fast101006,00060,000

API Rate Limit

MODEL IDRPMRPKTPMTPK
arxon/main101006,000100,000
arxon/agentic1010012,000100,000
arxon/r11010012,000100,000
arxon/fast101006,000100,000
Key Expiry7 days

Errors

401Invalid or missing API key
429Rate limit or quota exceeded
502AI service unavailable
504AI service timed out