Models

All models available on EgmontGPT

Default
GPT 4o
GPT 4 Omni is the newest release from OpenAI, 40% better than 3.5, more concise and 9 times faster than 3.5 with an average response latency of 0.32 seconds.
GPT 4.0 Turbo
GPT 4.0 Turbo is the latest generation model from OpenAI with an updated knowledge cutoff at April 2023 and has a larger context window up to 128k. This model is currently in preview and not suited for production environments.
GPT 4.0
GPT 4.0 is the biggest release from OpenAI, with 10x more parameters than GPT-3. It is trained on 1.6 trillion parameters, 10x more than GPT-3, and is the largest language model ever trained.
GPT 3.5 Turbo
GPT 3.5 Turbo is the cheaper and faster version of GPT 4.0 Turbo. It has a smaller context window up to 16k and is trained on 1.6 trillion parameters, 10x more than GPT-3. It has less context but is faster than GPT 4.0 and more powerful than GPT 3.5.
Mistral Large
Mistral Large is Mistral AI's most advanced Large Language Model (LLM). It can be used on any language-based task thanks to its state-of-the-art reasoning and knowledge capabilities.
Cohere Command R Plus
Command R+ is a highly performant generative large language model, optimized for a variety of use cases including reasoning, summarization, and question answering. It is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model uses supervised fine-tuning (SFT) and preference training to align model behavior to human preferences for helpfulness and safety. The model is optimized to perform well in the following languages: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Simplified Chinese, and Arabic. Command R+ has a context window up to 128k.