OpenAI Introduces Free Fine-Tuning for GPT-4o Mini Model with 2M Tokens/Day

Jul 23, 2024, 08:05 PM

OpenAI has announced the availability of fine-tuning for its GPT-4o mini model, offering developers the ability to customize the AI for specific applications. This feature is initially available to tier 4 and 5 users, with plans to expand access to all tiers. Developers can utilize up to 2 million training tokens per day for free through September 23. The GPT-4o mini model boasts 4 times the training context (64k tokens) and 8 times the inference context (128k tokens) compared to GPT-3.5 Turbo, making it a more capable and cost-effective option. Fine-tuning GPT-4o mini is also cheaper and available for a trial period.