OriginalPoint API

Authentication

All API requests must include your API key in the Authorization header using the Bearer scheme. API keys are prefixed with op_sk_ and can be created from your dashboard.

Authorization: Bearer op_sk_your_api_key

Quickstart

Send your first request in under a minute. Install the OpenAI SDK for your language, point it at the OriginalPoint base URL, and make a chat completion request.

import openai

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

response = client.chat.completions.create(
    model="claude-sonnet-4",
    messages=[
        {"role": "user", "content": "Explain quantum computing in one paragraph."}
    ],
)

print(response.choices[0].message.content)

Models

List all models available through the API. The response follows the OpenAI list models format and includes models from every supported provider.

List models

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o",
      "object": "model",
      "created": 1700000000,
      "owned_by": "openai"
    },
    {
      "id": "claude-sonnet-4",
      "object": "model",
      "created": 1700000000,
      "owned_by": "anthropic"
    }
  ]
}

See the Model Directory for a full list of supported models, pricing, and capabilities.

Chat Completions

Create a chat completion by sending a list of messages. The API will return the model's response. This is the primary endpoint for interacting with language models.

Request body

{
  "model": "claude-sonnet-4",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "What is the capital of France?"
    }
  ],
  "max_tokens": 256,
  "temperature": 0.7,
  "stream": false
}

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "claude-sonnet-4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 8,
    "total_tokens": 32
  }
}

Streaming

Enable streaming by setting stream: true in your request. The API returns server-sent events (SSE) where each event contains a delta of the response. Streaming works across all supported models and providers.

const stream = await client.chat.completions.create({
  model: "claude-sonnet-4",
  messages: [{ role: "user", content: "Write a haiku about APIs." }],
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) process.stdout.write(content);
}

Each streamed chunk follows the OpenAI format with a delta object containing incremental content. The stream ends with a [DONE] message.

Error Handling

The API uses standard HTTP status codes to indicate the success or failure of a request. Errors include a JSON body with a descriptive message and error type.

{
  "error": {
    "message": "Invalid API key provided.",
    "type": "authentication_error",
    "code": 401
  }
}

Rate Limits

Rate limits are applied per API key and vary by plan. When you exceed your rate limit, the API returns a 429 status code with a Retry-After header indicating how many seconds to wait before retrying.

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

SDKs

OriginalPoint is compatible with the official OpenAI SDK for every language. Simply set the base URL to https://api.originalpoint.ai/v1 and use your OriginalPoint API key.