Quickstart

Get your first response in under 2 minutes. OriginalPoint is OpenAI-compatible — if you've used the OpenAI SDK, you already know how to use this API.

Step 1: Get your API key

Create a free account at originalpoint.ai/signup. After signup, navigate to Dashboard → API Keys and create your first key. Keys look like: op_xxxxxxxxxxxxxxxxxxxx

Step 2: Install the SDK

# Python
pip install openai

# Node.js
npm install openai

Step 3: Make your first request

from openai import OpenAI

client = OpenAI(
    api_key="op_your_key_here",
    base_url="https://api.originalpoint.ai/v1"
)

response = client.chat.completions.create(
    model="gpt-5",  # or "auto" for smart routing
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is 2+2?"}
    ]
)

print(response.choices[0].message.content)
# → "4"

Authentication

All API requests require a Bearer token in the Authorization header.

Authorization: Bearer op_your_key_here

Managing API Keys

You can create, rotate, and revoke keys from Dashboard → API Keys. Best practices:

• → Use one key per project/environment (dev, staging, prod)
• → Set per-key monthly spend caps to prevent runaway costs
• → Never commit keys to source code — use environment variables
• → Rotate immediately if you suspect a key is compromised

Chat Completions

POST /v1/chat/completions

Creates a model response for the given chat conversation. Fully compatible with the OpenAI Chat Completions API.

Request Parameters

Response Schema

{
  "id": "chatcmpl-op_abc123",
  "object": "chat.completion",
  "created": 1746123456,
  "model": "gpt-5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "4"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 23,
    "completion_tokens": 1,
    "total_tokens": 24,
    "cost_usd": 0.000061  // OriginalPoint extension field
  }
}

Models API

GET /v1/models

Returns a list of all available models with their IDs, providers, and capabilities.

{
  "object": "list",
  "data": [
    {
      "id": "gpt-5",
      "object": "model",
      "created": 1746000000,
      "owned_by": "openai",
      "context_length": 131072,
      "pricing": {
        "input_per_million": 2.50,
        "output_per_million": 10.00
      }
    },
    {
      "id": "claude-opus-4.5",
      "object": "model",
      "created": 1746000000,
      "owned_by": "anthropic",
      "context_length": 204800,
      "pricing": {
        "input_per_million": 15.00,
        "output_per_million": 75.00
      }
    }
    // ... 14 more models
  ]
}

models = client.models.list()
for model in models.data:
    print(model.id, model.owned_by)

Streaming

Set stream=True to receive a Server-Sent Events stream. Tokens are emitted as they're generated — ideal for chat UIs.

import sys

with client.chat.completions.stream(
    model="claude-sonnet-4",
    messages=[{"role": "user", "content": "Write a haiku."}]
) as stream:
    for text in stream.text_stream():
        print(text, end="", flush=True)

Python SDK

Use the official openai Python package — it's fully compatible.

pip install openai

export OPENAI_API_KEY="op_your_key_here"
export OPENAI_BASE_URL="https://api.originalpoint.ai/v1"

from openai import OpenAI
import os

# Reads OPENAI_API_KEY and OPENAI_BASE_URL from environment
client = OpenAI()

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

Node.js SDK

Use the official openai npm package.

npm install openai

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.ORIGINALPOINT_API_KEY,
  baseURL: 'https://api.originalpoint.ai/v1'
});

const response = await client.chat.completions.create({
  model: 'gemini-3-pro',
  messages: [{role: 'user', content: 'Explain quantum entanglement simply.'}],
  max_tokens: 256
});

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

Smart Routing

Set model="auto" to enable smart routing. The OriginalPoint router selects the optimal model in real-time based on your configured routing mode.

response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Summarize this text: ..."}],
    extra_body={
        "routing": "cost"  # Always selects cheapest capable model
    }
)

# Check which model was actually used
print(f"Routed to: {response.model}")
print(f"Cost: ${response.usage.cost_usd:.6f}")

Routing Modes

BYOK Setup

Connect your own provider API keys to route through your credentials and pay provider rates directly.

1. 1
   Go to Dashboard → BYOK
   Navigate to the BYOK section in your OriginalPoint dashboard.
2. 2
   Add your provider key
   Enter your OpenAI (sk-...), Anthropic (sk-ant-...), or Google API key. It's encrypted immediately.
3. 3
   Use as normal
   Your API requests automatically use your BYOK credentials when available. No code changes needed.

Error Handling

OriginalPoint uses standard HTTP status codes. Error bodies follow the OpenAI error format.

Rate Limits

Rate limit headers are included in every response: X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset.