Promote Sign in Sign up

Catalogs

Models

229 matched .

Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.

Clear search and filters

All types Text · 2,080 Image · 398 Video · 224 Audio · 372 Coding · 40 Multimodal · 885 Structured data · 27 3D · 17
Weights and source · filters active
Open weights Closed On Hugging Face Clear filters
Most downloaded A–Z Recently synced
Explore other catalogs
Models Datasets Demos Devices Robots MCPs Papers Investors Fundraises Repositories News
How to choose models

Start with the task you need the model to perform, then narrow the model type and weight availability. Open weights do not automatically mean unrestricted commercial use. Check the original model card for the license, input requirements, evaluation results and hardware needs before choosing a model.

Understand our sources and data limits

  1. PaLM 2 Google AI model by Google Text · Closed Closed weights
  2. Palmyra X 004 WRITER Palmyra X 004 (X4) is Writer’s advanced enterprise LLM, part of the Palmyra X family. It’s tuned fo… Text · Closed Closed weights
  3. Palmyra X5 WRITER Palmyra X5 is Writer’s enterprise LLM built for multi-agent systems: a hybrid transformer with a 1M… Text · Closed Closed weights
  4. Rerank 2 lite Voyage AI rerank-2-lite is a lightweight multilingual cross-encoder reranker from Voyage AI. It scores and re… Text · Closed Closed weights
  5. rerank 2.5 Voyage AI A reranking model that reorders search results to improve retrieval accuracy, with instruction-foll… Text · Closed Closed weights
  6. Rerank 2.5 lite Voyage AI A latency-optimized reranker that refines retrieval results with instruction-following capabilities… Text · Closed Closed weights
  7. Rerank 3.5 Caldera Labs Rerank 3.5 is a high-accuracy cross-encoder reranking model for search and RAG. It re-scores candid… Text · Closed Closed weights
  8. Rerank 4 Caldera Labs ReRank 4 is Cohere's latest cross-encoder reranking model for enterprise search and RAG, with 32K t… Text · Closed Closed weights
  9. Roar Character Technologies Roar is the middle ground between fast chats and deeper replies. It delivers more thoughtful, detai… Text · Closed Closed weights
  10. Sackett OpenEvidence Sackett is an evidence weighing medical AI model from OpenEvidence that uses interactive questionin… Text · Closed Closed weights
  11. Salesforce Koa Salesforce Salesforce Koa is Salesforce's first CRM reasoning model for Agentforce, post-trained on NVIDIA Nem… Text · Closed Closed weights
  12. Sec Gemini v1 Google Sec-Gemini is Google’s cybersecurity-focused AI system for real-time security knowledge, insights,… Text · Closed Closed weights
  13. Seed 1.6 ByteDance Seed1.6 integrates multimodal capabilities, with "adaptive thinking" balancing model performance wi… Text · Closed Closed weights
  14. Seed Prover 1.5 ByteDance Seed-Prover 1.5 is ByteDance Seed’s formal theorem-proving model for Lean, trained with agentic RL… Text · Closed Closed weights
  15. Seq2Seq Google Seq2Seq LSTM is a classic encoder-decoder model built with LSTM layers that maps a variable-length… Text · Closed Closed weights
  16. Snow OpenEvidence Snow is OpenEvidence's deepest production model, conducting a full medical literature investigation… Text · Closed Closed weights
  17. Solar Mini Upstage Solar Mini is a 10.7 billion parameter large language model built using a Depth Up Scaling method t… Text · Closed Closed weights
  18. Solar Pro 4 Upstage Solar Pro 4 is Upstage's agentic large language model built to carry multi-step work to completion,… Text · Closed Closed weights
  19. Sonar Perplexity Sonar is Perplexity’s family of reasoning models built on the R1 post-training architecture. They’r… Text · Closed Closed weights
  20. Sonar Large 32K Perplexity Perplexity Sonar Large 32K is the top-tier Sonar reasoning model, built on Perplexity’s R1 post-tra… Text · Closed Closed weights
  21. Sonar Pro Perplexity Sonar Pro is Perplexity’s balanced reasoning model, sitting between the smaller Sonar options and t… Text · Closed Closed weights
  22. Sonar Reasoning Pro Perplexity Advanced reasoning model combining multi-step Chain-of-Thought processing with real-time web search… Text · Closed Closed weights
  23. SOTA K KT SOTA K is KT’s flagship Korean-first large language model, built for high-accuracy reasoning, multi… Text · Closed Closed weights
  24. SWE 1.6 Cognition SWE-1.6 is Cognition’s latest model for software engineering agents, built to improve both raw capa… Text · Closed Closed weights
  25. Syn Pro Upstage Syn Pro is a large language model under 32 billion parameters, purpose built for Japanese enterpris… Text · Closed Closed weights
  26. T5 Google AI model by Google Text · Closed Closed weights
  27. T5Gemma 2 Google DeepMind T5Gemma 2 is Google’s encoder-decoder Gemma model collection for input-heavy tasks such as summariz… Text · Closed Closed weights
  28. Tenet Harvey AI Harvey Tenet is Harvey's first post-trained legal AI model, built on a Kimi K3 base with Fireworks… Text · Closed Closed weights
  29. Titan Text Premier Amazon Amazon Titan Text Premier is AWS’s top-tier text generation model on Bedrock, built for enterprise-… Text · Closed Closed weights
  30. TranslateGemma Google DeepMind TranslateGemma is Google’s open Gemma-based translation model family for text and image-text transl… Text · Closed Closed weights
  31. Voyage Voyage AI voyage is a text embedding model that converts text into dense vector representations for semantic… Text · Closed Closed weights
  32. Voyage 01 Voyage AI voyage-01 is a text embedding model by Voyage AI, designed for retrieval-augmented generation (RAG)… Text · Closed Closed weights
  33. Voyage 3 large Voyage AI Text embedding model optimized for general-purpose and multilingual retrieval across law, finance,… Text · Closed Closed weights
  34. Voyage 3 lite Voyage AI Lightweight general-purpose text embedding model optimized for latency and cost. Generates 512-dime… Text · Closed Closed weights
  35. Voyage 4 Voyage AI Text embedding model optimized for general-purpose and multilingual retrieval quality. Supports a 3… Text · Closed Closed weights
  36. Voyage context 3 Voyage AI voyage-context-3 is a contextualized chunk embedding model that produces vectors capturing both chu… Text · Closed Closed weights