Modelli di testo e chat

Anthropic's most powerful model. Exceptional at complex analysis, agentic tasks, and extended reasoning.

reasoningagentic

Google's fastest multimodal model. Supports text, images, audio, and video input.

fastmultimodalaffordable

The original Bio_ClinicalBERT from Alsentzer et al., a BERT model initialized from BioBERT and further pretrained on all MIMIC-III clinical notes. Served as a fill-mask endpoint it predicts masked tokens in clinical text and produces clinical embeddings. It is the standard encoder backbone behind many downstream clinical NLP fine-tunes.

medicalresearchnlp

Token-classification model from d4data that tags 84 biomedical entity types in clinical and medical text, including disease, sign, symptom, medication, dosage, lab value, body part and procedure. Trained on the Maccrobat clinical case corpus on a DistilBERT base, so it runs cheaply for high-volume tagging.

medicalresearchnlp

Anthropic's most capable model. Excellent for complex analysis, coding, math, and creative writing.

codinganalysis

DeepSeek's refreshed V3.1 release. 671B MoE / 37B active. Tops open-weights leaderboards on coding and reasoning.

open-weightsmoecoding

xAI's flagship reasoning model with vision and tool use. 256k context, strong at complex reasoning and STEM tasks.

reasoningvisiontools

xAI's Grok 4.20 reasoning snapshot. Runs an extended thinking pass before answering for multi-step analysis, math and STEM, with a 1M token context window and strong agentic tool calling.

grokreasoninglong-context

Moonshot AI's 1T-parameter MoE model. Industry-leading agentic coding and tool-use benchmarks.

moonshotkimimoe

Token-classification model that extracts 41 medical entity types from clinical text, such as disease, medication, dosage, frequency, lab test, sign and symptom. Fine-tuned on a DeBERTa v3 base, which gives more accurate spans than older BERT-based taggers on the same corpus.

medicalresearchnlp

MiniMax's 456B hybrid lightning-attention model with native 4M-token context. Industry-leading long-context.

long-contextlightning-attentionopen-weights

Perplexity's premium web-grounded search model with multi-step reasoning over live sources.

web-searchcitationsrag

Alibaba's Qwen 3 flagship MoE: 235B total / 22B active. Strong reasoning and tool use, open-weights.

moeopen-weights

DeepSeek's reasoning model with chain-of-thought capabilities. Excellent for complex problem-solving.

reasoningmath

xAI's flagship model. Strong at reasoning, coding, and real-time knowledge with web search capabilities.

reasoningreal-time

AI21's flagship hybrid Mamba-Transformer model with a 256k context window for long-document tasks.

long-contextmambahybrid

Cost-efficient hybrid Mamba-Transformer model with 256k context. Tuned for high-throughput RAG.

long-contextmambahybrid

BioBERT fine-tuned on the NCBI Disease corpus for disease-name recognition. Given biomedical text it tags spans that mention a disease or condition, using BIO labels. Useful for pulling diagnoses and disease mentions out of abstracts, case reports and clinical notes.

medicalresearchnlp

Anthropic's fast and affordable model. Great for quick tasks, summarization, and simple coding.

fastaffordable

Text-classification model from Betty van Aken that decides whether a medical condition mentioned in a clinical note is present, absent or possible. The target entity is marked in the input with [entity] tags, and the model returns the assertion status. Built on Bio_ClinicalBERT and trained on the 2010 i2b2/VA assertion data.

medicalresearchnlp

Token-classification model that tags the three core i2b2 clinical entity types in patient notes: problem, test and treatment. Given a sentence from a discharge summary or progress note it marks which spans are medical problems, which are diagnostic tests and which are treatments or medications.

medicalresearchnlp

Open-weights multilingual research model from Cohere covering 23 languages. 35B parameters.

coheremultilingualopen-weights

Cohere's fast lightweight chat model (deprecated Sep 2025). Kept as comparison tombstone.

Cohere's mid-tier RAG/tool model. Cost-efficient sibling of Command R+ with 128k context.

ragtoolsmultilingual

Cohere's flagship RAG- and tool-optimized chat model. 128k context, refreshed August 2024.

ragtoolsmultilingual

xAI's Grok 4.20 standard snapshot. Skips the extended thinking pass for lower-latency answers on tasks that do not need deep deliberation. 1M token context window.

groklong-contextlow-latency

xAI's Grok 4.20 multi-agent snapshot. Coordinates several specialized agents under one call to handle multi-step workflows that mix research, tool use and synthesis. 1M token context window.

grokmulti-agentagentic

Meta's open-source 70B parameter model. Strong all-around performance with multilingual support.

open-source

Meta M2M-100 12B many-to-many translation model. Direct translation between 100 languages without pivoting through English.

translationopen-weightsmany-to-many

Google MADLAD-400 3B multilingual translation model. 419 languages supported, trained on a 5T-token multilingual corpus with strong low-resource performance.

translationopen-weightsmultilingual

Meta mBART-50 many-to-many translation model. 50 supported languages with strong performance on news and conversational text.

translationopen-weightsmany-to-many

Mixture-of-experts Phi-3.5: 42B total / 6.6B active params. 128k context, multilingual.

open-weightsmoemultilingual

Mistral's flagship model. Strong reasoning, multilingual, and coding capabilities.

multilingualcoding

Meta's No Language Left Behind 3.3B translation model. Direct translation between any pair of 200+ languages including many low-resource African and Asian languages.

translationopen-weightsmultilingual

Meta's distilled 600M NLLB. Same 200-language coverage as the 3B model with a fraction of the parameters, ideal for edge or high-throughput deployment.

translationopen-weightsmultilingual

Full-parameter fine-tune of Llama 3.1 405B by Nous Research. Steerable, uncensored, strong tool use.

open-weightstoolsroleplay

Llama-3.1-70B fine-tune from Nous Research with strong tool/agent capabilities and uncensored alignment.

open-weightstoolsroleplay

Perplexity's fastest and cheapest web-grounded chat model. Live-source citations included.

web-searchcitationscost-efficient

Perplexity's reasoning model with chain-of-thought and integrated web search.

web-searchreasoning

Alibaba's powerful open-source model. Excellent at coding, math, and multilingual tasks.

open-sourcecodingmultilingual

Alibaba's flagship pretrained MoE model. Top-tier reasoning and code performance via DashScope API.

qwenalibabamoe

Snowflake's open MoE model: 480B total / 17B active params with dense+MoE hybrid architecture.

snowflakemoeopen-weights

TII's 180B causal decoder chat model fine-tuned on Ultrachat, Platypus and Airoboros.

tiiopen-weights

Unbabel TowerInstruct 13B. Llama-2-based multilingual translation and post-editing model. Strong terminology consistency for enterprise localization.

translationunbabelopen-weights

01.AI's larger general-purpose chat model with 32k context window and strong bilingual performance.

01aichinesebilingual