Tag: API

  • OpenAI | Introducing the Realtime API

    —

    by

    air-beans
    in

    Enabling Low-Latency Speech-to-Speech Experiences OpenAI has launched the Realtime API in public beta, allowing paid developers to create low-latency, multimodal experiences in their applications. The API enables natural speech-to-speech interactions using six preset voices, eliminating the need to combine multiple models for voice experiences. It offers a seamless solution for building conversational applications, such as…

  • OpenAI | Prompt Caching in the API

    —

    by

    air-beans
    in

    Reducing Costs and Latency with Prompt Caching OpenAI has introduced Prompt Caching to reduce costs and improve processing speed for developers who reuse the same context across multiple API calls. By reusing recently seen input tokens, developers can receive a 50% discount and faster prompt processing. This feature is automatically applied to models like GPT-4o,…

  • OpenAI | Model Distillation in the API

    —

    by

    air-beans
    in

    Introducing a Cost-Effective Way to Manage Model Distillation OpenAI has launched a new service that provides an integrated way to manage the entire model distillation process. This allows developers to fine-tune cost-effective models like GPT-4o mini using the outputs from frontier models such as GPT-4o. The platform provides tools like Stored Completions and Evals to…

  • OpenAI｜Introducing Structured Outputs in the API

    —

    by

    air-beans
    in

    OpenAI introduces Structured Outputs in the API, ensuring model-generated outputs exactly match developer-supplied JSON Schemas. This new feature addresses the limitations of the previous JSON mode by guaranteeing schema conformity with the gpt-4o-2024-08-06 model, achieving 100% reliability. The feature supports function calling with strict output matching and a new response_format parameter for structured responses. Both…