News
ResearchOpenAI pens AI safety agreement with four firmsReleasesOVHcloud 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 improvementFrontierOpenAI鈥檚 New Hacking Model Found Dozens Of Holes In Apple TechFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIResearchOpenAI pens AI safety agreement with four firmsReleasesOVHcloud 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 improvementFrontierOpenAI鈥檚 New Hacking Model Found Dozens Of Holes In Apple TechFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAI
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

imgfnGrok 馃嚭馃嚫 United StatesGrok A chatbot and model line from SpaceX Super Intelligence, launched in 2023.General 路 API only 路 2023 imgfnMuse 馃嚭馃嚫 United StatesMuse Meta's multimodal LLM family, successor to Llama, with open and closed variantsGeneral 路 API only 路 2026 Vicuna WorldVicuna An open chat model fine-tuned from LLaMA and Llama 2 by LMSYSGeneral 路 Conditional licence 路 2023 imgwavvidNemotron 馃嚭馃嚫 United StatesNemotron Nvidia family of language and multimodal models for enterprise and reasoningGeneral 路 Conditional licence 路 2023 BLOOM 馃嚝馃嚪 FranceBLOOM A 176-billion-parameter multilingual text model built openly by a volunteer research workshop.General 路 Conditional licence 路 2022 imgLlama 馃嚭馃嚫 United StatesLlama Meta AI's family of open-weight language models, from 1B to 2T parametersGeneral 路 Conditional licence 路 2023 imgAlice AI 馃嚪馃嚭 RussiaAlice AI Yandex's family of language, vision and image models behind the Alice assistantGeneral 路 API only 路 2023 DBRX WorldDBRX A 132-billion-parameter mixture-of-experts language model from Databricks.General 路 Conditional licence 路 2024 imgwavvidGemma 馃嚭馃嚫 United StatesGemma Google DeepMind's open family of Gemini-derived language modelsGeneral 路 Open weights 路 2024 fnNemotron 3 Super 馃嚭馃嚫 United StatesNemotron 3 Super NVIDIA's 120B hybrid MoE language model with 12B active parameters and 1M-token contextGeneral 路 Conditional licence 路 2026 Nemotron-4 340B 馃嚭馃嚫 United StatesNemotron-4 340B NVIDIA's 340B open-access model family for chat and synthetic data generationGeneral 路 Conditional licence 路 2024 fnLlama-3.1-Nemotron-Ultra-253B 馃嚭馃嚫 United StatesLlama-3.1-Nemotron-Ultra-253B A 253B reasoning model derived from Llama-3.1-405B-InstructReasoning 路 Conditional licence imgMistral Medium 3 馃嚝馃嚪 FranceMistral Medium 3 A mid-size language model aimed at enterprise coding and multimodal workGeneral 路 API only 路 2025 DeepSeek LLM 67B 馃嚚馃嚦 ChinaDeepSeek LLM 67B A 67-billion-parameter open-source model trained on English and Chinese text.General 路 Conditional licence 路 2024 Poro 2 馃嚝馃嚠 FinlandPoro 2 Finnish and English instruction-following model based on Llama 3.1General 路 Conditional licence EXAONE 3.5 馃嚢馃嚪 South KoreaEXAONE 3.5 LG AI Research open language model series for real-world tasksGeneral 路 Conditional licence 路 2024 fnEXAONE 4.0 馃嚢馃嚪 South KoreaEXAONE 4.0 Unified language model with reasoning and non-reasoning modesGeneral 路 Conditional licence 路 2025 Solar Open 100B 馃嚢馃嚪 South KoreaSolar Open 100B 102B parameter Mixture-of-Experts model by UpstageGeneral 路 Conditional licence 路 2026 Llama-3-ELYZA-JP-8B 馃嚡馃嚨 JapanLlama-3-ELYZA-JP-8B Japanese-tuned Llama 3 model by ELYZAGeneral 路 Conditional licence Krutrim-1 馃嚠馃嚦 IndiaKrutrim-1 Multilingual language model for Indian languagesGeneral 路 Conditional licence 路 2024 OPT 馃嚭馃嚫 United StatesOPT Meta AI's family of open decoder-only language models from 125M to 175B parametersGeneral 路 Conditional licence 路 2022 fnTyphoon 馃嚬馃嚟 ThailandTyphoon Thai-focused large language model series by SCB 10XGeneral 路 Conditional licence 路 2024 Llama 3 馃嚭馃嚫 United StatesLlama 3 Meta's open-weight language model family in 8B and 70B sizesGeneral 路 Conditional licence 路 2024 fnMinistral 3B and 8B 馃嚝馃嚪 FranceMinistral 3B and 8B Two small Mistral AI models built for on-device and edge computing.Small 路 API only 路 2024 Qwen2 馃嚚馃嚦 ChinaQwen2 Open-weight language model series from AlibabaGeneral 路 Open weights 路 2024 fnLlama 3.3 70B 馃嚭馃嚫 United StatesLlama 3.3 70B A text-only 70B instruction-tuned model from Meta's Llama 3 line.General 路 Conditional licence Param-1 馃嚠馃嚦 IndiaParam-1 Bilingual and multilingual language models from India.General 路 Conditional licence fnNemotron 3 Nano 馃嚭馃嚫 United StatesNemotron 3 Nano NVIDIA's 30B hybrid Mamba-Transformer MoE model for reasoning and agentsGeneral 路 Conditional licence 路 2025 imgwavGemini 2.0 Flash 馃嚭馃嚫 United StatesGemini 2.0 Flash Google DeepMind's fast multimodal workhorse model for agentic appsGeneral 路 API only 路 2024 imgGrok-2 馃嚭馃嚫 United StatesGrok-2 xAI's 2024 chat and reasoning model, with a smaller sibling, Grok-2 miniGeneral 路 Conditional licence 路 2024 imgwavfnGrok 4 馃嚭馃嚫 United StatesGrok 4 xAI's flagship reasoning model with native tool use and live searchGeneral 路 API only 路 2025 Gemma 馃嚭馃嚫 United StatesGemma Small open-weight language models from Google, in 2B and 7B sizesGeneral 路 Conditional licence 路 2024 fnLlama 3.1 405B 馃嚭馃嚫 United StatesLlama 3.1 405B Meta's largest openly available language model, released in 2024General 路 Conditional licence 路 2024 Code Llama 馃嚭馃嚫 United StatesCode Llama Meta's code-specialised family of Llama 2 models in four sizesCode 路 Conditional licence 路 2023 BART 馃嚭馃嚫 United StatesBART A denoising encoder-decoder transformer for generation and comprehension tasksGeneral 路 Conditional licence 路 2019 NLLB-200 馃嚭馃嚫 United StatesNLLB-200 A research translation model covering 200 languages, built for low-resource ones.General 路 Conditional licence 路 2022 PLLuM 馃嚨馃嚤 PolandPLLuM Polish-focused large language model familyGeneral 路 Open weights 路 2024

The weekly digest

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