ProductDecember 10, 20244 min read

Introducing GPT-4 Turbo Support on Infiner

We're excited to announce full support for OpenAI's GPT-4 Turbo model with 128K context window and improved performance.

Marcus Johnson

Product Manager

Introducing GPT-4 Turbo Support on Infiner

Today we're thrilled to announce that GPT-4 Turbo is now available on the Infiner platform. This represents a significant upgrade in capabilities for our users.

What's New

GPT-4 Turbo brings several improvements:

128K Context Window: Process documents up to ~300 pages in a single request
Knowledge Cutoff: Updated to April 2024
Improved Instruction Following: Better adherence to complex system prompts
JSON Mode: Native support for structured output generation

How to Use It

Simply update your model parameter to gpt-4-turbo in your API calls:

javascript

const response = await infiner.chat.completions.create({
  model: "gpt-4-turbo",
  messages: [
    { role: "user", content: "Analyze this document..." }
  ]
});

Pricing

GPT-4 Turbo is available at competitive rates:

Input: $10.00 / 1M tokens
Output: $30.00 / 1M tokens

This represents significant savings compared to the previous GPT-4 model while delivering improved performance.

Get Started

GPT-4 Turbo is available now for all Infiner users. Check out our updated documentation for migration guides and best practices.