GPT-4o is the most advanced multimodal model from OpenAI, and it is set to become more accessible. The company announced that the new model gpt-4o-2024-08-06 is now available at $2.50 per 1 million input tokens and $10.00 per 1 million output tokens.
Compared to gpt-4o-2024-05-13, these new prices reflect a 50% reduction for input tokens and a 33% reduction for output tokens. In contrast, the Gemini 1.5 Pro model costs $3.50 per 1 million input tokens and $10.50 per 1 million output tokens.
The ongoing price war between OpenAI and Google, highlighted by significant recent price drops from both companies, presents a promising development for developers. This intensified competition is expected to drive innovation, leading to even more powerful and affordable large language models in the future.
During DevDay 2023, OpenAI first introduced JSON mode, which generates valid JSON outputs from the model, though the response did not conform to a specific schema. Now, OpenAI has announced Structured Outputs in the API, ensuring that outputs generated by the model will accurately adhere to the JSON schemas provided by developers. This Structured Outputs feature is now publicly available in the API.
OpenAI has updated its Python and Node SDK with built-in support for Structured Outputs. Structured Outputs with function calling are now accessible across all OpenAI models that support function calls in the API. This includes gpt-4o, gpt-4o-mini, gpt-4-0613, and gpt-3.5-turbo-0613. This functionality can be utilized in the Chat Completions API, Assistants API, and Batch API, even with visual inputs.
Structured Outputs with response formats are available for gpt-4o-mini and gpt-4o-2024-08-06, as well as any models fine-tuned based on these models. This feature can be employed in the Chat Completions API, Assistants API, and Batch API, including visual inputs.
Source: neowin
Comments (0)
There are no comments for now