Vincony Developer API: One Endpoint for 400+ Models

OpenAI-Compatible API

Vincony's API follows the OpenAI chat completions format. If your app already uses the OpenAI SDK, switching to Vincony is a one-line change — just update the base URL and API key. You gain access to 400+ models without changing any other code.

import vincony

client = vincony.Client(api_key="YOUR_KEY")

# Works exactly like OpenAI's API
response = client.chat.completions.create(
    model="claude-opus-4.6",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain WebSockets vs SSE"}
    ],
    stream=True
)

for chunk in response:
    print(chunk.choices[0].delta.content, end="")

TypeScript SDK

import Vincony from 'vincony';

const client = new Vincony({ apiKey: 'YOUR_KEY' });

const response = await client.chat.completions.create({
  model: 'gpt-5',
  messages: [{ role: 'user', content: 'Build a React hook for infinite scroll' }],
});

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

Key Features

• • Streaming: Server-sent events for real-time responses
• • Function calling: Tool use across all supported models
• • Rate limiting: Configurable per-key limits with 429 headers
• • Webhooks: Get notified on batch completion or errors
• • Usage analytics: Per-request cost tracking and dashboards

Getting Started

Sign up for a free Developer account at vincony.com to get your API key with 100 free credits. Full API documentation is available at docs.vincony.com.