Harmony is a response format developed by OpenAI for use with the gpt-oss model series. It defines a structured way for language models to produce outputs, including regular text, reasoning traces, tool calls, and structured data. By mimicking the OpenAI Responses API, Harmony provides developers with a familiar interface while enabling more advanced capabilities such as multiple output channels, instruction hierarchies, and tool namespaces. The format is essential for ensuring gpt-oss models operate correctly, as they are trained to rely on this structure for generating and organizing their responses. For users accessing gpt-oss through third-party providers like HuggingFace, Ollama, or vLLM, Harmony formatting is handled automatically, but developers building custom inference setups must implement it directly. With its flexible design, Harmony serves as the foundation for creating more interpretable, controlled, and extensible interactions with open-weight language models.
Features
- Defines a structured response format for gpt-oss models
- Mimics OpenAI Responses API for easier adoption
- Supports multiple output channels including reasoning and tool calls
- Enables tool namespaces and structured data outputs
- Provides clear instruction hierarchy for better control
- Required for correct use of gpt-oss in custom inference setups
Project Samples
