News
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

Hunyuan-Large 馃嚚馃嚦 ChinaHunyuan-Large Open-source mixture of experts model with 389 billion parametersGeneral 路 Open weights 路 2024 Param-1 馃嚠馃嚦 IndiaParam-1 Bilingual and multilingual language models from India.General 路 Conditional licence imgSalamandra 馃嚜馃嚫 SpainSalamandra Open multilingual language models for European languagesGeneral 路 Open weights 路 2025 Falcon Mamba 7B 馃嚘馃嚜 United Arab EmiratesFalcon Mamba 7B A 7-billion parameter language model using the Mamba architecture.General 路 Open weights 路 2024 fnMiniMax-M2 馃嚚馃嚦 ChinaMiniMax-M2 Open-source MoE model for coding and agentsCode 路 Open weights 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 imgvidfnKimi K3 馃嚚馃嚦 ChinaKimi K3 Open-weight multimodal agentic model with 2.8T parametersGeneral 路 Open weights 路 2026 PaLM 2 馃嚭馃嚫 United StatesPaLM 2 Google's multilingual Transformer language model in four sizes, from on-device to largestGeneral 路 API only 路 2023 GPT-SW3 馃嚫馃嚜 SwedenGPT-SW3 Generative language model for Nordic languagesGeneral 路 Research only 路 2023 fnToolformer 馃嚭馃嚫 United StatesToolformer A language model that learns on its own when to call external tools through APIs.Research 路 Research only 路 2023 ModernBERT 馃嚭馃嚫 United States and 1 moreModernBERT A modernised encoder model for retrieval and classification tasks.Encoder 路 Open weights 路 2024 Viking 馃嚝馃嚠 FinlandViking Open source language model for Nordic languages and codeGeneral 路 Fully open 路 2023 fnK-EXAONE 馃嚢馃嚪 South KoreaK-EXAONE LG AI Research multilingual Mixture-of-Experts modelGeneral 路 Open weights Granite 3.0 馃嚭馃嚫 United StatesGranite 3.0 IBM's third-generation open enterprise language models, from 2B to 8B parametersGeneral 路 Open weights 路 2024 Aya 101 WorldAya 101 A 13-billion-parameter multilingual model that follows instructions in 101 languagesGeneral 路 Open weights 路 2024 Falcon-7B 馃嚘馃嚜 United Arab EmiratesFalcon-7B Open 7-billion parameter decoder model by TIIGeneral 路 Open weights 路 2023 imgAmazon Nova 馃嚭馃嚫 United StatesAmazon Nova Amazon's family of foundation models on AWS BedrockGeneral 路 API only 路 2024 fnGranite 4.2 馃嚭馃嚫 United StatesGranite 4.2 IBM's open reasoning language model family, released August 2026Reasoning 路 Open weights 路 2026 imgfnAmazon Nova Premier 馃嚭馃嚫 United StatesAmazon Nova Premier Amazon's largest Nova model for complex tasks and model distillationGeneral 路 API only fnGranite 4.0 馃嚭馃嚫 United StatesGranite 4.0 IBM's hybrid Mamba/transformer language models for enterprise workGeneral 路 Open weights 路 2025 imgfnMistral Large 3 馃嚝馃嚪 FranceMistral Large 3 A 675B-parameter open-weight mixture-of-experts multimodal model from Mistral AIGeneral 路 Open weights Apple Foundation Models 馃嚭馃嚫 United StatesApple Foundation Models Apple's on-device and server language models behind Apple IntelligenceGeneral 路 API only 路 2024 imgApple Foundation Models 馃嚭馃嚫 United StatesApple Foundation Models Apple's 2025 on-device and server language models for Apple IntelligenceGeneral 路 API only 路 2025 AlexaTM 20B 馃嚭馃嚫 United StatesAlexaTM 20B A 20-billion-parameter multilingual sequence-to-sequence model from Amazon's Alexa team.General 路 Research only 路 2022 Grok-1.5 馃嚭馃嚫 United StatesGrok-1.5 xAI's long-context Grok model with stronger reasoning and coding skillsGeneral 路 API only 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 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 ALLaM 馃嚫馃嚘 Saudi ArabiaALLaM Bilingual Arabic and English language model seriesGeneral 路 Open weights 路 2024 Command R WorldCommand R Cohere's model built for retrieval-augmented generation in productionGeneral 路 API only fnSolar Open 2 馃嚢馃嚪 South KoreaSolar Open 2 250B parameter open-weight model for agentic tasksGeneral 路 Open weights 路 2026 Mixtral 8x22B 馃嚝馃嚪 FranceMixtral 8x22B Sparse mixture-of-experts open model with 39B active parameters out of 141BGeneral 路 Open weights Grok 4.1 馃嚭馃嚫 United StatesGrok 4.1 xAI's Grok 4.1, tuned for personality, emotional tone and fewer factual errorsGeneral 路 API only 路 2025 fnCommand A WorldCommand A Cohere's enterprise-focused large language model for agents, search and tool useGeneral 路 Research only 路 2025 Command R+ 馃嚚馃嚘 CanadaCommand R+ Cohere's large language model built for enterprise workloads and retrieval-augmented use.General 路 API only Phi-2 馃嚭馃嚫 United StatesPhi-2 A 2.7 billion parameter Microsoft research model for QA, chat and codeResearch 路 Open weights InstructGPT 馃嚭馃嚫 United StatesInstructGPT GPT-3 models fine-tuned with human feedback to follow instructionsGeneral 路 API only 路 2022 fnWebGPT 馃嚭馃嚫 United StatesWebGPT A GPT-3 model fine-tuned to answer questions while browsing the webGeneral 路 Research only 路 2021 fnGpt-oss-120b 馃嚭馃嚫 United StatesGpt-oss-120b OpenAI's open-weight reasoning model that fits on one 80GB GPUReasoning 路 Open weights 路 2025 fnGpt-oss-20b 馃嚭馃嚫 United StatesGpt-oss-20b OpenAI's smaller open-weight reasoning model for local and low-latency useReasoning 路 Open weights 路 2025 Claude 1 馃嚭馃嚫 United StatesClaude 1 Anthropic's first AI assistant model, offered in two versions via chat and API.Assistant 路 API only Claude 2 馃嚭馃嚫 United StatesClaude 2 Anthropic's 2023 assistant model with a 100K-token window and stronger coding.General 路 API only 路 2023 imgClaude 3 Opus 馃嚭馃嚫 United StatesClaude 3 Opus Anthropic's largest Claude 3 model, aimed at complex reasoning and analysisGeneral 路 API only imgClaude 3 Haiku 馃嚭馃嚫 United StatesClaude 3 Haiku Anthropic's fastest and lowest-cost model in the Claude 3 familyGeneral 路 API only 路 2024 imgClaude 3.5 Haiku 馃嚭馃嚫 United StatesClaude 3.5 Haiku Anthropic's fast, low-latency model for coding, tools and user-facing productsGeneral 路 API only 路 2024 imgfnClaude 3.7 Sonnet 馃嚭馃嚫 United StatesClaude 3.7 Sonnet Anthropic's hybrid reasoning model with a controllable thinking budgetGeneral 路 API only 路 2025 fnClaude 4 馃嚭馃嚫 United StatesClaude 4 Anthropic's fourth-generation coding and reasoning models, Opus 4 and Sonnet 4General 路 API only 路 2025 fnClaude Opus 4.1 馃嚭馃嚫 United StatesClaude Opus 4.1 Anthropic's upgraded Claude Opus 4 model for coding, agents and reasoningGeneral 路 API only 路 2025 fnClaude Sonnet 4.5 馃嚭馃嚫 United StatesClaude Sonnet 4.5 Anthropic's coding and agentic Claude model, released in 2025.General 路 API only 路 2025

The weekly digest

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