← Back to Rhodes

RHODES API

OpenAI-compatible API with simple, predictable pricing

Pricing

$2
per million tokens
Input
$10
per million tokens
Output

No hidden fees. No rate limit surprises. Pay only for what you use.

Quick Start

Chat Completion
curl https://rhodesagi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "rhodes",
    "messages": [
      {"role": "user", "content": "Hello, Rhodes!"}
    ]
  }'
Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://rhodesagi.com/v1"
)

response = client.chat.completions.create(
    model="rhodes",
    messages=[
        {"role": "user", "content": "Hello, Rhodes!"}
    ]
)

print(response.choices[0].message.content)
Node.js
import OpenAI from 'openai';

const client = new OpenAI({
    apiKey: 'YOUR_API_KEY',
    baseURL: 'https://rhodesagi.com/v1'
});

const response = await client.chat.completions.create({
    model: 'rhodes',
    messages: [
        { role: 'user', content: 'Hello, Rhodes!' }
    ]
});

console.log(response.choices[0].message.content);

Endpoints

Method Endpoint Description
POST /v1/chat/completions Create chat completion (streaming supported)
GET /v1/usage Get your usage statistics
GET /v1/account Get account information

Features

OpenAI Compatible

Drop-in replacement. Use existing SDKs and tools with just a URL change.

Streaming

Real-time SSE streaming for interactive applications. Same format as OpenAI.

200K Context

Process long documents, codebases, and conversations.

Simple Pricing

One price. No confusing tiers. Pay only for what you use.

Fast & Reliable

Low latency with high availability. Built for production.

No Rate Surprises

Generous limits included. Scale seamlessly.

Get Started

Create an account to get your API key

Get API Key Sign Up