API Documentation

Overview

Opulon API is a Claude-compatible AI gateway. Point your existing Claude integration to our endpoint, swap in your Opulon API key and everything works instantly , no code rewrites, no new SDKs.

We support the Messages API with full streaming support, all current Claude models and the same request/response format you already use.

Quickstart

export ANTHROPIC_API_KEY="op-ul-e4st85dasf"
export ANTHROPIC_BASE_URL="https://api.opulonapi.com"

curl https://api.opulonapi.com/v1/messages \
  --header "x-api-key: $ANTHROPIC_API_KEY" \
  --header "anthropic-version: 2023-06-01" \
  --header "content-type: application/json" \
  --data '{
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello, Claude"}
    ]
  }'

{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I assist you today?"
    }
  ],
  "model": "claude-sonnet-4-20250514",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 8
  }
}

Authentication

All requests must include these headers:

If you're using the official Anthropic SDK, set the API key and base URL , the SDK handles headers automatically.

Base URL

https://api.opulonapi.com

Replace Anthropic's default base URL (https://api.anthropic.com) with the Opulon endpoint. All paths remain identical.

import anthropic

client = anthropic.Anthropic(
    api_key="op-ul-e4st85dasf",
    base_url="https://api.opulonapi.com"
)

message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello, Claude"}
    ]
)
print(message.content[0].text)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: "op-ul-e4st85dasf",
  baseURL: "https://api.opulonapi.com"
});

const message = await client.messages.create({
  model: "claude-sonnet-4-20250514",
  max_tokens: 1024,
  messages: [
    { role: "user", content: "Hello, Claude" }
  ]
});
console.log(message.content[0].text);

from openai import OpenAI

client = OpenAI(
    api_key="op-ul-e4st85dasf",
    base_url="https://api.opulonapi.com/v1"
)

response = client.chat.completions.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello, Claude"}
    ]
)
print(response.choices[0].message.content)

Messages API

Send a structured list of messages to Claude and receive a response. Supports multi-turn conversations, system prompts and tool use.

Request Body

Streaming

Set stream: true to receive responses as server-sent events (SSE). Tokens are delivered as they are generated.

curl https://api.opulonapi.com/v1/messages \
  --header "x-api-key: $ANTHROPIC_API_KEY" \
  --header "anthropic-version: 2023-06-01" \
  --header "content-type: application/json" \
  --data '{
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 1024,
    "stream": true,
    "messages": [
      {"role": "user", "content": "Write a haiku about APIs"}
    ]
  }'

Event Types

Models

The following models are available through Opulon API. Use the model ID in your requests.

All models support 200K token context windows. Model availability may vary by plan.

Rate Limits

Rate limits are configured per API key based on your plan. When limits are reached, the API returns a 429 status code.

View your current usage and remaining limits in your status page.

Error Handling

Errors are returned as JSON with an error object:

{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "model: field required"
  }
}

HTTP Status Codes

SDKs & Libraries

Since Opulon is fully Claude-compatible, you can use the official Anthropic SDKs. Just set the base URL to https://api.opulonapi.com.

You can also use the OpenAI SDK with Opulon , set the base URL to https://api.opulonapi.com/v1 and use your Opulon key as the API key.