Thursday, August 08, 2024

OpenAI API: gpt-4o-2024-08-06, 50% cheaper

Structured Outputs, a new feature designed to ensure model-generated outputs will exactly match JSON Schemas that you provide. You can start using Structured Outputs in two forms in the API: through function calling and through the response_format parameter (with a new json_schema option). To get started, check out our docs.

The latest GPT-4o snapshot gpt-4o-2024-08-06 is 50% cheaper for input tokens and 33% cheaper for output tokens than the original GPT-4o. It also supports Structured Outputs.


 Models - OpenAI API

GPT-4o (“o” for “omni”) is ... most advanced model. It is multimodal (accepting text or image inputs and outputting text), and it has the same high intelligence as GPT-4 Turbo but is much more efficient—it generates text 2x faster and is 50% cheaper. Additionally, GPT-4o has the best vision and performance across non-English languages of any of our models. GPT-4o is available in the OpenAI API to paying customers. Learn how to use GPT-4o in our text generation guide.

ModelDescriptionContext windowMax output tokensTraining data
gpt-4oGPT-4o
Our high-intelligence flagship model for complex, multi-step tasks. GPT-4o is cheaper and faster than GPT-4 Turbo. Currently points to gpt-4o-2024-05-13.
128,000 tokens4,096 tokensUp to Oct 2023
gpt-4o-2024-05-13gpt-4o currently points to this version.128,000 tokens4,096 tokensUp to Oct 2023
gpt-4o-2024-08-06Latest snapshot that supports Structured Outputs128,000 tokens16,384 tokensUp to Oct 2023

No comments: