LLM Models (125)
Description
AI models to test and tools to learn how to master them
[Update Sep 2025] 125 Links
| Website | URL | Category | Pricing | Notes |
|---|---|---|---|---|
| OpenAI GPT-4o | Visit | Multimodal LLM (Hosted API) | Paid | General + vision/audio; production API |
| OpenAI GPT-4 Turbo | Visit | Text LLM (Hosted API) | Paid | High‑capability GPT‑4 family |
| OpenAI GPT-3.5 Turbo | Visit | Text LLM (Hosted API) | Paid | Lightweight, low‑cost GPT‑3.5 |
| OpenAI o3 | Visit | Reasoning LLM (Hosted API) | Paid | Reasoning‑optimized family |
| OpenAI o1 | Visit | Reasoning LLM (Hosted API) | Paid | OpenAI reasoning models |
| OpenAI GPT-4o mini | Visit | Small Multimodal LLM | Paid | Cheaper, fast multimodal GPT‑4o variant |
| OpenAI Whisper | Visit | ASR Model (LLM‑adjacent) | Free | Open‑source speech‑to‑text model |
| OpenAI Embeddings (text-embedding-3) | Visit | Embedding Model (Hosted API) | Paid | High‑dimensional text embeddings |
| Anthropic Claude 3 Opus | Visit | Text/Multimodal LLM (Hosted API) | Paid | Most capable Claude 3 series |
| Google Gemini 1.5 Pro | Visit | Multimodal LLM (Hosted API) | Paid | Long‑context multimodal model |
| Google Gemini Pro 1.0 | Visit | Text/Multimodal LLM (Hosted API) | Paid | General‑purpose Gemini |
| Google PaLM 2 (Text‑Bison) | Visit | Text LLM (Hosted API) | Paid | Vertex AI classic text model |
| Microsoft Phi-3-mini | Visit | Small Instruct LLM (Open Source) | Free | Compact high‑quality small LLM |
| Microsoft Phi-3-medium | Visit | Small/Medium LLM (Open Source) | Free | Instruction‑tuned medium model |
| Microsoft Phi-2 | Visit | Small LLM (Open Source) | Free | Research small language model |
| Microsoft Orca 2 | Visit | Reasoning LLM (Open Source) | Free | Instruction/Reasoning finetune |
| Meta Llama 3 8B Instruct | Visit | Text LLM (Open Source) | Free | Open‑weights instruction model |
| Meta Llama 3 70B Instruct | Visit | Text LLM (Open Source) | Free | Large open model |
| Meta Llama 2 7B Chat | Visit | Text LLM (Open Source) | Free | Llama 2 chat variant |
| Meta Llama 2 13B Chat | Visit | Text LLM (Open Source) | Free | 13B chat model |
| Mistral 7B Instruct v0.3 | Visit | Text LLM (Open Source) | Free | Efficient 7B instruct model |
| Mixtral 8x7B Instruct | Visit | MoE LLM (Open Source) | Free | Sparse MoE 8x7B routing |
| Mixtral 8x22B | Visit | MoE LLM (Open Source) | Free | Larger Mixture‑of‑Experts |
| Mistral Large (API) | Visit | Text LLM (Hosted API) | Paid | Proprietary hosted model |
| Cohere Command R | Visit | Text LLM (Hosted API) | Paid | Retrieval‑optimized command model |
| Cohere Embed v3 | Visit | Embedding Model (Hosted API) | Paid | Text embeddings for RAG |
| xAI Grok-2 | Visit | Text LLM (Hosted API) | Paid | Latest Grok series (X integrations) |
| xAI Grok-1 | Visit | Text LLM (Open Source License) | Free | Weights/code for Grok‑1 (research) |
| Alibaba Qwen2 7B Instruct | Visit | Text LLM (Open Source) | Free | Strong bilingual open model |
| Alibaba Qwen2 72B Instruct | Visit | Text LLM (Open Source) | Free | Large Qwen2 |
| Alibaba Qwen2-VL | Visit | Vision-Language LLM (Open Source) | Free | Multimodal VL model |
| Alibaba Qwen-Long | Visit | Long-Context LLM (Open Source) | Free | Extended context window |
| Baidu ERNIE Bot | Visit | Text LLM (Hosted API) | Paid | Chinese LLM by Baidu |
| 01.AI Yi-34B-Chat | Visit | Text LLM (Open Source) | Free | Yi series chat model |
| Baichuan 13B Chat | Visit | Text LLM (Open Source) | Free | Bilingual Chinese/English |
| DeepSeek V2 | Visit | Text LLM (Open Source) | Free | MoE style Chinese/English |
| DeepSeek Coder V2 | Visit | Code LLM (Open Source) | Free | High‑quality coding model |
| AI21 Jamba | Visit | Hybrid Mamba-Transformer (Hosted) | Paid | Long‑context hybrid architecture |
| AI21 Jurassic-2 | Visit | Text LLM (Hosted API) | Paid | Earlier AI21 Jurassic series |
| Amazon Titan Text | Visit | Text LLM (Hosted API) | Paid | AWS Bedrock native text model |
| IBM Granite 13B Instruct | Visit | Text LLM (Open Source) | Free | IBM open Granite series |
| IBM Granite 34B Code | Visit | Code LLM (Open Source) | Free | Granite code specialization |
| Salesforce XGen-7B-8K | Visit | Text LLM (Open Source) | Free | Long‑context base model |
| Salesforce CodeGen2 7B | Visit | Code LLM (Open Source) | Free | Updated code generation model |
| Google Codey (Vertex) | Visit | Code LLM (Hosted API) | Paid | Code generation & chat |
| Google Gemma 7B | Visit | Text LLM (Open Source) | Free | Lightweight open LLM |
| Google Gemma 2 9B | Visit | Text LLM (Open Source) | Free | Instruction‑tuned Gemma 2 |
| Pythia 12B | Visit | Text LLM (Open Source) | Free | Pretrained Eleuther model |
| GPT‑NeoX‑20B | Visit | Text LLM (Open Source) | Free | 20B parameter open model |
| GPT‑J‑6B | Visit | Text LLM (Open Source) | Free | Popular 6B model |
| Falcon-7B-Instruct | Visit | Text LLM (Open Source) | Free | Efficient 7B instruct |
| Falcon-40B | Visit | Text LLM (Open Source) | Free | 40B open model |
| Stable LM 3B | Visit | Text LLM (Open Source) | Free | Stable LM small model |
| Stable LM 7B | Visit | Text LLM (Open Source) | Free | 7B StableLM |
| Zephyr-7B-β | Visit | Text LLM (Open Source) | Free | Chat‑tuned open model |
| OpenHermes-2.5 Mistral 7B | Visit | Text LLM (Open Source) | Free | DPO‑tuned Mistral‑base |
| Nous Hermes Llama2 13B | Visit | Text LLM (Open Source) | Free | Popular Llama2 chat finetune |
| Databricks DBRX Instruct | Visit | MoE LLM (Open Source) | Free | Open DBRX instruct model |
| Databricks DBRX Base | Visit | MoE LLM (Open Source) | Free | Base mixture‑of‑experts |
| Snowflake Arctic | Visit | Text LLM (Open Source) | Free | Arctic instruct model |
| MPT‑7B Instruct | Visit | Text LLM (Open Source) | Free | MPT instruct tuning |
| MPT‑30B | Visit | Text LLM (Open Source) | Free | 30B parameter model |
| LLaVA‑1.5 7B | Visit | Vision-Language LLM (Open Source) | Free | Visual instruction tuning |
| MiniGPT‑4 | Visit | Vision-Language LLM (Open Source) | Free | VLM built on Llama |
| IDEFICS 9B | Visit | Vision-Language LLM (Open Source) | Free | M4 multimodal model |
| BLOOM 176B | Visit | Text LLM (Open Source) | Free | Multilingual open 176B |
| BLOOMZ 7B1 | Visit | Text LLM (Open Source) | Free | Instruction‑tuned BLOOM |
| NAVER HyperCLOVA X | Visit | Text LLM (Hosted API) | Paid | Korean enterprise LLM |
| rinna Japanese GPT‑Neox 3.6B | Visit | JP Text LLM (Open Source) | Free | Japanese instruction model |
| ELYZA Japanese Llama‑2‑7b | Visit | JP Text LLM (Open Source) | Free | Japanese Llama 2 finetune |
| Noor (Arabic GPT) | Visit | Arabic Text LLM (Open Source) | Free | Arabic pretrained model |
| IndicTrans2 | Visit | Translation Model (Open Source) | Free | Indic translation (LLM‑adjacent) |
| Code Llama 7B Instruct | Visit | Code LLM (Open Source) | Free | Code generation/chat |
| Code Llama 34B Instruct | Visit | Code LLM (Open Source) | Free | Large code model |
| WizardCoder 15B | Visit | Code LLM (Open Source) | Free | Python‑focused code model |
| StarCoder2 15B | Visit | Code LLM (Open Source) | Free | Open code LLM by BigCode |
| MedPaLM | Visit | Medical QA LLM (Research) | Free | Research medical QA model |
| BloombergGPT | Visit | Financial LLM (Research) | Free | Finance domain model (research) |
| Lawyer LLaMA | Visit | Legal LLM (Open Source) | Free | Legal domain chat model |
| MAmmoTH Math 7B | Visit | Math Reasoning (Open Source) | Free | Mathematics instruction model |
| Aya 23 8B | Visit | Multilingual LLM (Open Source) | Free | Community multilingual model |
| NLLB‑200 | Visit | Translation Model (Open Source) | Free | 200‑language translation |
| Qwen2.5 7B Instruct | Visit | Text LLM (Open Source) | Free | Latest Qwen instruct |
| MiniCPM-Llama3-V 2.5 | Visit | Vision-Language (Open Source) | Free | Small multimodal VLM |
| MiniCPM 2.6 | Visit | Small LLM (Open Source) | Free | Compact LLM by OpenBMB |
| TinyLlama-1.1B-chat | Visit | Small LLM (Open Source) | Free | 1.1B compact chat model |
| SmolLM 1.7B Instruct | Visit | Small LLM (Open Source) | Free | Tiny but capable LLM |
| Vicuna‑13B v1.5 | Visit | Text LLM (Open Source) | Free | Instruction‑tuned Vicuna |
| Alpaca 7B | Visit | Text LLM (Research/Open) | Free | Instruction‑tuned LLaMA prototype |
| BGE Large v1.5 | Visit | Embedding Model (Open Source) | Free | Strong English embeddings |
| Instructor XL | Visit | Embedding Model (Open Source) | Free | Instruction‑tuned embeddings |
| Open‑Assistant SFT | Visit | Community Assistant (Open) | Free | OASST finetune |
| OLMo‑7B | Visit | Text LLM (Open Source) | Free | AllenAI open model |
| Llama Guard 2 | Visit | Safety Classifier (Open Source) | Free | Safety moderation model |
| OpenAI Moderation | Visit | Moderation Model (Hosted) | Paid | Text & image moderation |
| Perspective API | Visit | Toxicity Classifier (Hosted) | Free | Comment toxicity detection |
| Perplexity Sonar (API) | Visit | Text LLM (Hosted API) | Paid | Models powering Perplexity answers |
| Together AI Endpoints | Visit | Hosted Open Models | Freemium | Hosted OSS like Mixtral/Llama |
| Anyscale Endpoints | Visit | Hosted Open Models | Freemium | Serve OSS models with endpoints |
| Fireworks.ai | Visit | Hosted Open Models | Freemium | High‑throughput OSS/partner models |
| Replicate Models | Visit | Hosted Models Marketplace | Freemium | Run many OSS LLMs via API |
| HF Inference Endpoints | Visit | Hosted Models | Paid | Managed serving for HF models |
| OctoAI | Visit | Hosted Open Models | Freemium | Deploy/serve OSS LLMs |
| Replit Code v1.5 3B | Visit | Code LLM (Open Source) | Free | Replit code model 3B |
| DeepSeek Coder 33B | Visit | Code LLM (Open Source) | Free | Powerful code instruct |
| CodeGen2.5 7B | Visit | Code LLM (Open Source) | Free | Salesforce code model update |
| DeepSeek‑R1 | Visit | Reasoning LLM (Open Source) | Free | Reinforced reasoning open model |
| Qwen2.5‑Math 7B | Visit | Math/Reasoning LLM (Open Source) | Free | Math‑optimized instruct (Qwen) |
| Longformer LED | Visit | Long‑Context Seq2Seq (Open Source) | Free | Long‑context summarization |
| MPT‑7B StoryWriter | Visit | Long‑Context Text LLM (Open Source) | Free | 65k context for stories |
| Whisper Large‑v3 | Visit | ASR Model (Open Source) | Free | OpenAI whisper large v3 |
| SeamlessM4T | Visit | Speech/Text Multimodal (Open Source) | Free | Speech‑to‑speech & translation |
| OLLaMA | Visit | Local Serving (Runner) | Free | Run LLMs locally easily |
| LM Studio | Visit | Local Serving (Runner) | Free | Desktop app to run chat models locally |
| vLLM | Visit | Inference Engine (Adj.) | Free | High‑throughput LLM inference |
| Text Gen WebUI | Visit | Local WebUI (Adj.) | Free | Popular local chat UI |
| Axolotl | Visit | Finetuning Framework | Free | SFT/QLoRA training toolkit |
| T5‑XXL (11B) | Visit | Seq2Seq LLM (Open Source) | Free | Classic T5 XXL with SSM |
| UL2 20B | Visit | Seq2Seq LLM (Open Source) | Free | Unifying Language Learning |
| OPT‑IML‑Max 30B | Visit | Text LLM (Open Source) | Free | OPT instruction‑tuned 30B |
| RedPajama‑INCITE 7B | Visit | Text LLM (Open Source) | Free | RedPajama instruct |
| LLaVA‑Next 34B | Visit | Vision‑Language (Open Source) | Free | Large VLM |
| Qwen2‑VL 72B | Visit | Vision‑Language (Open Source) | Free | Large VL model |
| InternVL 2 8B | Visit | Vision‑Language (Open Source) | Free | OpenGVLab VLM |
| Gemini 1.5 Nano | Visit | Small LLM (Device) | Free | On‑device Gemini variant |




