[jampa]

You can use OpenAI's developer platform https://platform.openai.com/playground/chat

I haven't used the normal website in a year, it is a way better experience:

- It allows tweaking of the model / temperature.

- You pay only per token used

- It does not use your conversations to train their models

- You can edit both your and the assistant message in the conversation or delete it.

- Allows for easy message replay if the output is not great

Be mindful that you are paying per token for every message in the thread, so if the thread becomes long it gets expensive, but still far more value than subscribing.

[panarky]

The world is changing too fast for knowledge that is nine months old.

------

USER

What is the maximum number of tokens supported by gpt-4o?

ASSISTANT

As of my most recent update in October 2023, GPT-4 does not have an officially designated variant called "gpt-4o". However, OpenAI's GPT-4 model supports different maximum token limits depending on its variant. There are two primary context lengths for GPT-4 models:

1. *GPT-4 with 8K context length*: This variant supports up to 8,000 tokens. 2. *GPT-4 with 32K context length*: This variant supports up to 32,000 tokens.

These limits encompass both input and output tokens in a given interaction. If you intended to refer to a specific or newly introduced variant, such as "gpt-4o," it is essential to look up the most current resources or official announcements from OpenAI, as models and their capabilities can evolve.

[8n4vidtmkvmk]

I don't know what you're trying to point out here. The models aren't trained on themselves.

[panarky]

ChatGPT and Gemini incorporate web search into their results, so they're not limited to stale information.

If you think you can save money by paying per token in the playground, you should know that you're not getting the same results.

For example, if I ask Gemini the identical question, it gives a reasonable answer, even though Gemini was released before ChatGPT was released. It can look up the current OpenAI documentation and summarize it:

USER

What is the maximum number of tokens supported by gpt-4o?

ASSISTANT

GPT-4o has a context window of 128,000 tokens. This means it can process up to 128,000 tokens between your input and its output combined. However, the maximum number of output tokens (the AI's response) is limited to 4,096 tokens.