News
ReleasesOVHcloud unveils Olala mini, its first in-house LLMChinaA 9B model beats a 1T model on FinQA, trained with Crusoe Managed RLReleasesThe internal metaphysics of an LLMReleasesMapping Language Model Internal Representations to Physical Laws and Scientific ReasoningResearchCan China keep rogue AI in check? Meet the start-up testing the top modelsFrontierMicrosoft aims to challenge OpenAI, Anthropic with cheaper, specialized AI modelsOpen modelsMicrosoft rolls out new first-party models and updates to agentic AI continuous improvementFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIFrontierGoogle is making it easier to opt out of Gemini AI model training – here’s howFrontierOpenAI Unveils New Astra AI Model After Scrapping Prior ReleaseReleasesOVHcloud unveils Olala mini, its first in-house LLMChinaA 9B model beats a 1T model on FinQA, trained with Crusoe Managed RLReleasesThe internal metaphysics of an LLMReleasesMapping Language Model Internal Representations to Physical Laws and Scientific ReasoningResearchCan China keep rogue AI in check? Meet the start-up testing the top modelsFrontierMicrosoft aims to challenge OpenAI, Anthropic with cheaper, specialized AI modelsOpen modelsMicrosoft rolls out new first-party models and updates to agentic AI continuous improvementFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIFrontierGoogle is making it easier to opt out of Gemini AI model training – here’s howFrontierOpenAI Unveils New Astra AI Model After Scrapping Prior Release
EveryLLM

Text

Reads and writes text. 471 models on EveryLLM so far.

Text is the base modality of every language model: it reads a prompt and writes a reply, token by token. A tokenizer first splits text into tokens, which are whole words, pieces of words or single characters; in English a token is roughly three-quarters of a word. Everything else a model does, from code to reasoning to calling tools, is ultimately expressed as text that it reads or writes.

Tokens and context

Most models use byte-pair encoding, which builds a vocabulary of frequent character sequences. Vocabularies have grown from about 50,000 tokens in GPT-2 to around 200,000 in GPT-4o and 256,000 in Gemma. The context window is how many tokens the model can consider at once: GPT-3 handled 2,048 in 2020, while Gemini 1.5 Pro offered one million in 2024. Languages in non-Latin scripts often need more tokens for the same meaning.

What text-only still means

Many models remain text-only, especially smaller ones and older families such as GPT-3, Llama 2 and BERT, and text still carries most business uses: drafting, summarising, pulling fields out of documents, translation and search. Text-only models are cheaper to train and serve, and easier to evaluate, since their inputs and outputs can be checked and compared directly.

Famous text models

Further reading

T5 🇺🇸 United StatesT5 Encoder-decoder language model family from Google AI using a text-to-text framework.General · Fully open · 2019 wavWhisper WorldWhisper OpenAI's open-source model for turning speech into text and translating it.General · Open weights · 2022 imgPaliGemma WorldPaliGemma A 3B open vision-language model built on SigLIP and Gemma-2BMultimodal · Open weights · 2024 MT5 🇺🇸 United StatesMT5 A multilingual text-to-text transformer pretrained on 101 languagesGeneral · Open weights · 2020 imgvidFlamingo 🇬🇧 United KingdomFlamingo A visual language model family that learns new image and video tasks from a few examples.Multimodal · Research only · 2022 BART 🇺🇸 United StatesBART A denoising encoder-decoder transformer for generation and comprehension tasksGeneral · Conditional licence · 2019 NLLB-200 🇺🇸 United StatesNLLB-200 A research translation model covering 200 languages, built for low-resource ones.General · Conditional licence · 2022 T0 🇫🇷 FranceT0 Encoder-decoder model for zero-shot task generalisation via promptsGeneral · Open weights · 2021 IndicBART 🇮🇳 IndiaIndicBART Sequence-to-sequence model for Indic languagesRegional · Open weights · 2021 CodeBERT 🇨🇳 ChinaCodeBERT Bimodal pre-trained model for code and textCode · Open weights · 2020 imgDeepSeek-V4.1-Flash 🇨🇳 ChinaDeepSeek-V4.1-Flash Multimodal MoE model with efficient KV cache compressionMultimodal · Open weights wavShuka v1 🇮🇳 IndiaShuka v1 Audio-native language model for Indic languagesMultimodal · Open weights imgNVLM 1.0 🇺🇸 United StatesNVLM 1.0 Open multimodal language models from NVIDIA for vision and language tasksMultimodal · Open weights · 2024 Flan-T5 🇺🇸 United StatesFlan-T5 Instruction-finetuned T5 checkpoints released by Google for zero-shot and few-shot workGeneral · Open weights · 2022 imgvidDiffusionGemma 🇺🇸 United StatesDiffusionGemma A multimodal Gemma 4 model that writes text by denoising blocks of tokens.Multimodal · Open weights imgDeepSeek-OCR WorldDeepSeek-OCR Optical character recognition model using visual compressionMultimodal · Open weights · 2025 Aya 101 WorldAya 101 A 13-billion-parameter multilingual model that follows instructions in 101 languagesGeneral · Open weights · 2024 imgPaLM-E WorldPaLM-E An embodied multimodal language model that grounds words in robot sensor inputMultimodal · Research only · 2023 AlexaTM 20B 🇺🇸 United StatesAlexaTM 20B A 20-billion-parameter multilingual sequence-to-sequence model from Amazon's Alexa team.General · Research only · 2022

The weekly digest

Every Monday: the model of the day, new pages on EveryLLM, and the conferences and anniversaries of the week ahead.