OpenAI introduces Structured Outputs and reduces GPT-4 pricing by 50%. Structured Outputs ensure model outputs match developer-supplied JSON Schemas, addressing a challenge since function calling was introduced. Developers can implement this by setting `strict: true` in function definitions or as a `response_format` option. The latest GPT-4 version also offers a 50% reduction in input token pricing and a 33% reduction in output token pricing.
Get the most out of your Google Analytics data with Marketing Auditor – a powerful tool that helps you uncover and fix errors in minutes. Generate white-label reports packed with actionable insights and a customized action plan to optimize your analytics setup effortlessly. Customize reports with professional themes or your branding, and export them in editable formats like PowerPoint or Google Slides.
OpenAI has announced fine-tuning for GPT-4o-mini, allowing users to customize the model for specific applications. Available to tier 4 and 5 users, with plans to expand, the first 2 million training tokens per day are free through September 23, 2023. Benefits include higher quality results, token savings, and lower latency. Supported models include gpt-4o-mini-2024-07-18 and others. Fine-tuning is recommended after exploring prompt engineering.
OpenAI has introduced the Batch API, which offers cost savings and higher rate limits for asynchronous tasks like summarization, translation, and image classification. Users can upload a file of bulk requests and expect results within 24 hours, all while enjoying a 50% discount on API prices.
