Release v3.20.0

[Christopher-Hayes]

November 25, 2023 (v3.20.0)

• ✨ [Feature] Added support for the gpt-4-1106-preview model. This model supports 128,000 token input context. The output token limit is 4,096. It's ~3x less expensive than gpt-4. - Thank you for the suggestion @xmjiao
• 🔧 [Fixes] Fix highlighting of HTML characters. - Thank you for the PR @ZsgsDesign
• 🎮 [QoL] OpenAI is beginning to have different prompt and complete token limits. The model selector now has more specific model info, including token prompt/complete limits.

Full Changelog: 3.19.1...3.20.0

---

This discussion was created from the release Release v3.20.0.

[Christopher-Hayes]

GPT-4-TURBO added. Model select updated to reflect that newer models have different limits for prompt and completion. The emoji format isn't the prettiest, but I think it better communicates the differences between the models. Will make prettier with svg icons at a future date.

In relation to that, gpt-4-turbo supports 128,000 input tokens. The "token breakdown" will not use the 128,000 tokens as the "max cost", it will use the max "compeletion tokens", which is 4,096.

This is partiallly why I wanted to update the model picker to mention the 128,000 token limit only applies to the user's input, and not chatgpt's output.