With visual capabilities, context 128k
The main information includes:
Overview:
The OpenAI API is supported by multiple models with different features and price points. You can also customize our models for your specific use cases through fine-tuning.
- Fully open, this model can be used through “gpt-4-turbo”. The latest version is “gpt-4-turbo-2024-04-09”
- Basic capabilities update, according to official statement: Majorly improved GPT-4 Turbo model
- Comes with visual capabilities, no need to use 4v interface
- 128k context
- Vision requests can now also use JSON schema and function calls.
- Training data as of December 2023
Models continue to be upgraded
gpt-4-turbo, gpt-4, and gpt-3.5-turbo point to the latest model versions of their respective ones. You can verify this by looking at the response after sending the request. The response will include the specific model version used (e.g. gpt-3.5-turbo-0613).
We also provide fixed model versions that developers can continue to use for at least three months after introducing the updated model. With the new pace of model updates, we are also enabling people to contribute assessments to help us improve the model for different use cases. If you are interested, check out the OpenAI Evals repository.
Learn more about model deprecation on our deprecation page.
Check the interface information here:https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4
(Check the interface information and open the link below the video)
In terms of price, it is consistent with the previous GPT-4-Turbo, namely:
- Input: $10.00 /1 million tokens
- Output: $30.00 /1 million tokens
- Picture reading: Minimum $0.00085 /picture
Check the price information here:https://openai.com/pricing
In terms of frequency restrictions, take the most advanced Tire 5 as an example. In the official description:
- Maximum concurrency: 10,000 times/minute
- Maximum processing: 1,500,000 tokens /minute
Check out the relevant restrictions here:https://platform.openai.com/docs/guides/rate-limits/usage-tiers? context=tier-five
If you want to learn more in detail, you can click on the link below the video.
Thank you for watching this video. If you like it, please subscribe and like it. thank
Video: