Model Distillation in the API
OpenAI has launched a model distillation feature within its API platform, enabling developers to fine-tune smaller, cost-efficient models using outputs generated by large frontier models. The workflow is entirely contained within the OpenAI platform. This lowers the barrier to deploying capable but cheaper models by leveraging knowledge transfer from frontier systems like GPT-4o.
Related guides (4)
Related events (8)
OpenAI Improves Fine-Tuning API and Expands Custom Models Program
OpenAI announced enhancements to its fine-tuning API giving developers greater control over the training process, alongside an expansion of its custom models program. The updates aim to provide more flexibility for enterprise and developer use cases requiring tailored model behavior. Specific new features include additional hyperparameter controls and tooling improvements, while the custom models program expansion opens new pathways for organizations to build bespoke models with OpenAI's assistance.
Fine-tuning now available for GPT-4o
OpenAI has launched fine-tuning support for GPT-4o, its flagship multimodal model, as of August 20, 2024. This allows developers to customize GPT-4o on their own datasets via the OpenAI API. The release extends the fine-tuning capability previously available on GPT-3.5 and GPT-4 to the most capable model in OpenAI's lineup, enabling task-specific optimization at the frontier.
GPT-3.5 Turbo fine-tuning and API updates
OpenAI has opened fine-tuning access for GPT-3.5 Turbo, allowing developers to customize the model with their own data for specific use cases. This extends fine-tuning capabilities previously available on older GPT-3 models to the more capable Turbo variant. The announcement also includes associated API updates to support this functionality.
Customizing GPT-3 for your application
OpenAI announced fine-tuning capabilities for GPT-3, enabling developers to customize the model for specific applications via a single command. This feature allows users to adapt GPT-3's behavior to their use case by training on domain-specific data. The announcement marks an early milestone in making large language model customization accessible through an API.
Introducing GPT-4.1 in the API
OpenAI is releasing GPT-4.1, a new family of models available via API to developers worldwide, featuring improvements in coding, instruction following, and long-context understanding. The release also includes GPT-4.1 nano, OpenAI's first nano-scale model. The models are positioned as developer-facing API products rather than consumer-facing releases.
OpenAI API Launch
OpenAI announced the release of an API providing programmatic access to its AI models. This marked a significant infrastructure and commercialization milestone, enabling third-party developers to integrate OpenAI's models into their own applications. The launch established the foundation for OpenAI's developer ecosystem and API-first business model.
Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models
ServiceNow AI introduces Apriel-H1, a reasoning model developed via knowledge distillation aimed at producing efficient inference. The blog post discusses techniques for distilling reasoning capabilities from larger models into smaller, more deployable ones. This work targets enterprise deployment scenarios where inference cost and latency matter alongside reasoning quality.
OpenAI Announces Function Calling, Longer Context, and API Price Reductions
OpenAI introduced function calling capabilities to its API, enabling models to reliably output structured JSON for calling developer-defined functions. The update also includes longer context windows, more steerable models (gpt-3.5-turbo-16k and gpt-4 updates), and reduced pricing on several API tiers. These changes significantly expand the practical utility of OpenAI models for agentic and tool-use applications.