Documentation · V1.0

Aevon API Docs.

Aevon is an OpenAI-compatible AI gateway giving you access to 30+ frontier models — Claude, GPT-4o, DeepSeek, Gemini, and more — through a single API key and base URL. Drop it into any existing client in under 60 seconds.

Quickstart

Get up and running in 4 steps. No SDK needed — works with any OpenAI-compatible client.

1. Get your API key

2. Set your base URL

Shell

# OpenAI-compatible
export OPENAI_BASE_URL="https://aevon.sh/v1"
export OPENAI_API_KEY="your_key_here"

# For Claude Code
export ANTHROPIC_BASE_URL="https://aevon.sh"
export ANTHROPIC_API_KEY="your_key_here"
        

3. Make your first request

Python
Node.js
cURL

import openai

client = openai.OpenAI(
    base_url="https://aevon.sh/v1",
    api_key="your_key_here"
)

response = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
        

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://aevon.sh/v1',
  apiKey: 'your_key_here',
});

const res = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(res.choices[0].message.content);
        

curl https://aevon.sh/v1/chat/completions \
  -H "Authorization: Bearer your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-r1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
        

Authentication

All requests require a Bearer token in the Authorization header.

HTTP Header

Authorization: Bearer your_key_here

⚠

Keep your API key secret. Never expose it in frontend code, public repos, or client-side JavaScript. Regenerate immediately if compromised.

Chat Completions

The primary endpoint. Fully compatible with the OpenAI Chat Completions API.

Endpoint
POSThttps://aevon.sh/v1/chat/completions

Request Parameters

Parameter	Type	Required	Description
model	string	Required	Model ID. See full list below.
messages	array	Required	Array of message objects with `role` and `content`.
max_tokens	integer	Optional	Maximum tokens to generate.
temperature	float	Optional	Sampling temperature 0–2. Default: 1.
stream	boolean	Optional	Enable streaming via SSE. Default: false.
system	string	Optional	System prompt (for supported models).

Available Models

Pass any of these model IDs in the model parameter. Switch models by changing a single string.

Loading models...

Cursor Integration

Use Aevon as a drop-in replacement in Cursor. Go to Settings → Models → OpenAI API Key and set:

Cursor Settings

API Key:  your_key_here
Base URL: https://aevon.sh/v1
        

✓

All Cursor models work. GPT-4o, Claude, and DeepSeek are all accessible once configured.

Claude Code Integration

Run Claude Code through Aevon by overriding the Anthropic base URL:

Shell

export ANTHROPIC_BASE_URL="https://aevon.sh"
export ANTHROPIC_API_KEY="your_key_here"
claude  # run claude code normally
        

Python SDK

Python

pip install openai

import openai
client = openai.OpenAI(
    base_url="https://aevon.sh/v1",
    api_key="your_key_here"
)
stream = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Write a haiku"}],
    stream=True
)
for chunk in stream:
    print(chunk.choices[0].delta.content, end="")
        

Node.js SDK

JavaScript

npm install openai

import OpenAI from 'openai';
const client = new OpenAI({
  baseURL: 'https://aevon.sh/v1',
  apiKey: 'your_key_here',
});
const res = await client.chat.completions.create({
  model: 'deepseek-r1',
  messages: [{ role: 'user', content: 'Hello' }],
});
console.log(res.choices[0].message.content);
        

Error Codes

Code	Meaning	Fix
401	Unauthorized	Invalid or missing API key.
402	Insufficient Credits	Top up at aevon.sh/billing.
429	Rate Limited	Slow down or upgrade plan.
500	Gateway Error	Retry or switch models.

Credits & Billing

Aevon is usage-based — charged per token, not per month. Free tier models consume zero credits.

ℹ

$100 free on signup. No credit card needed. Covers ~1–2M tokens depending on model.

Rate Limits

Tier	Requests/min	Tokens/min
Free	20 RPM	100K TPM
Credits	60 RPM	500K TPM
Pro	300 RPM	2M TPM

← BackHome Next →Get API Key