Free LLM Models Directory
Discover free and open-source large language models for text generation, code completion, and embeddings.
The Ultimate Free LLM Models Directory
Welcome to the most comprehensive directory of free and open-source LLM models. Whether you're a developer, researcher, or AI enthusiast, our curated collection helps you discover powerful language models that you can run locally, fine-tune, or integrate into your applications.
Our directory features models from leading providers including Meta's Llama 2, Mistral AI, Microsoft's Phi, and hundreds more on Hugging Face. All models are verified to have permissive licenses allowing commercial use.
From text generation and code completion to embeddings and multimodal models - find everything you need to build the next generation of AI applications!
Showing 241-288 of 576 models
Arcee AI: Coder Large
LLM Models
Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file. Arcee AI: Coder Large is listed as a large language or generative AI model associated with arcee-ai, with the model identifier arcee-ai/coder-large. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Meta: Llama Guard 4 12B
LLM Models
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM. Meta: Llama Guard 4 12B is listed as a large language or generative AI model associated with meta-llama, with the model identifier meta-llama/llama-guard-4-12b. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Qwen: Qwen3 30B A3B
LLM Models
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique. Qwen: Qwen3 30B A3B is listed as a large language or generative AI model associated with qwen, with the model identifier qwen/qwen3-30b-a3b. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Qwen: Qwen3 8B
LLM Models
Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,. Qwen: Qwen3 8B is listed as a large language or generative AI model associated with qwen, with the model identifier qwen/qwen3-8b. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Qwen: Qwen3 14B
LLM Models
Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for. Qwen: Qwen3 14B is listed as a large language or generative AI model associated with qwen, with the model identifier qwen/qwen3-14b. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Qwen: Qwen3 32B
LLM Models
Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for. Qwen: Qwen3 32B is listed as a large language or generative AI model associated with qwen, with the model identifier qwen/qwen3-32b. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Qwen: Qwen3 235B A22B
LLM Models
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and. Qwen: Qwen3 235B A22B is listed as a large language or generative AI model associated with qwen, with the model identifier qwen/qwen3-235b-a22b. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
OpenAI: o4 Mini High
LLM Models
OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining. OpenAI: o4 Mini High is listed as a large language or generative AI model associated with openai, with the model identifier openai/o4-mini-high. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
OpenAI: o3
LLM Models
o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. OpenAI: o3 is listed as a large language or generative AI model associated with openai, with the model identifier openai/o3. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
OpenAI: o4 Mini
LLM Models
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning. OpenAI: o4 Mini is listed as a large language or generative AI model associated with openai, with the model identifier openai/o4-mini. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
OpenAI: GPT-4.1
LLM Models
GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and. OpenAI: GPT-4.1 is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-4.1. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
OpenAI: GPT-4.1 Mini
LLM Models
GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard. OpenAI: GPT-4.1 Mini is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-4.1-mini. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
OpenAI: GPT-4.1 Nano
LLM Models
For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million. OpenAI: GPT-4.1 Nano is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-4.1-nano. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Meta: Llama 4 Maverick
LLM Models
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward. Meta: Llama 4 Maverick is listed as a large language or generative AI model associated with meta-llama, with the model identifier meta-llama/llama-4-maverick. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Meta: Llama 4 Scout
LLM Models
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input. Meta: Llama 4 Scout is listed as a large language or generative AI model associated with meta-llama, with the model identifier meta-llama/llama-4-scout. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
DeepSeek: DeepSeek V3 0324
LLM Models
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well. DeepSeek: DeepSeek V3 0324 is listed as a large language or generative AI model associated with deepseek, with the model identifier deepseek/deepseek-chat-v3-0324. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
OpenAI: o1-pro
LLM Models
The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide. OpenAI: o1-pro is listed as a large language or generative AI model associated with openai, with the model identifier openai/o1-pro. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Mistral: Mistral Small 3.1 24B
LLM Models
Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and. Mistral: Mistral Small 3.1 24B is listed as a large language or generative AI model associated with mistralai, with the model identifier mistralai/mistral-small-3.1-24b-instruct. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Google: Gemma 3 4B
LLM Models
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,. Google: Gemma 3 4B is listed as a large language or generative AI model associated with google, with the model identifier google/gemma-3-4b-it. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Google: Gemma 3 12B
LLM Models
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,. Google: Gemma 3 12B is listed as a large language or generative AI model associated with google, with the model identifier google/gemma-3-12b-it. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Cohere: Command A
LLM Models
Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary. Cohere: Command A is listed as a large language or generative AI model associated with cohere, with the model identifier cohere/command-a. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
OpenAI: GPT-4o-mini Search Preview
LLM Models
GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries. OpenAI: GPT-4o-mini Search Preview is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-4o-mini-search-preview. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
OpenAI: GPT-4o Search Preview
LLM Models
GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries. OpenAI: GPT-4o Search Preview is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-4o-search-preview. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Reka Flash 3
LLM Models
Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a. Reka Flash 3 is listed as a large language or generative AI model associated with rekaai, with the model identifier rekaai/reka-flash-3. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Google: Gemma 3 27B
LLM Models
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,. Google: Gemma 3 27B is listed as a large language or generative AI model associated with google, with the model identifier google/gemma-3-27b-it. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
TheDrummer: Skyfall 36B V2
LLM Models
Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling. TheDrummer: Skyfall 36B V2 is listed as a large language or generative AI model associated with thedrummer, with the model identifier thedrummer/skyfall-36b-v2. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Perplexity: Sonar Reasoning Pro
LLM Models
Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for. Perplexity: Sonar Reasoning Pro is listed as a large language or generative AI model associated with perplexity, with the model identifier perplexity/sonar-reasoning-pro. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Perplexity: Sonar Pro
LLM Models
Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like. Perplexity: Sonar Pro is listed as a large language or generative AI model associated with perplexity, with the model identifier perplexity/sonar-pro. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Perplexity: Sonar Deep Research
LLM Models
Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers. Perplexity: Sonar Deep Research is listed as a large language or generative AI model associated with perplexity, with the model identifier perplexity/sonar-deep-research. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Mistral: Saba
LLM Models
Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional. Mistral: Saba is listed as a large language or generative AI model associated with mistralai, with the model identifier mistralai/mistral-saba. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Llama Guard 3 8B
LLM Models
Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification). Llama Guard 3 8B is listed as a large language or generative AI model associated with meta-llama, with the model identifier meta-llama/llama-guard-3-8b. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
OpenAI: o3 Mini High
LLM Models
OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and. OpenAI: o3 Mini High is listed as a large language or generative AI model associated with openai, with the model identifier openai/o3-mini-high. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
AionLabs: Aion-1.0
LLM Models
Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as Tree. AionLabs: Aion-1.0 is listed as a large language or generative AI model associated with aion-labs, with the model identifier aion-labs/aion-1.0. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
AionLabs: Aion-1.0-Mini
LLM Models
Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant. AionLabs: Aion-1.0-Mini is listed as a large language or generative AI model associated with aion-labs, with the model identifier aion-labs/aion-1.0-mini. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
AionLabs: Aion-RP 1.0 (8B)
LLM Models
Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model. AionLabs: Aion-RP 1.0 (8B) is listed as a large language or generative AI model associated with aion-labs, with the model identifier aion-labs/aion-rp-llama-3.1-8b. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Qwen: Qwen2.5 VL 72B Instruct
LLM Models
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images. Qwen: Qwen2.5 VL 72B Instruct is listed as a large language or generative AI model associated with qwen, with the model identifier qwen/qwen2.5-vl-72b-instruct. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Qwen: Qwen-Plus
LLM Models
Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination. Qwen: Qwen-Plus is listed as a large language or generative AI model associated with qwen, with the model identifier qwen/qwen-plus. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
OpenAI: o3 Mini
LLM Models
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to. OpenAI: o3 Mini is listed as a large language or generative AI model associated with openai, with the model identifier openai/o3-mini. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Mistral: Mistral Small 3
LLM Models
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed. Mistral: Mistral Small 3 is listed as a large language or generative AI model associated with mistralai, with the model identifier mistralai/mistral-small-24b-instruct-2501. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
DeepSeek: R1 Distill Qwen 32B
LLM Models
DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new. DeepSeek: R1 Distill Qwen 32B is listed as a large language or generative AI model associated with deepseek, with the model identifier deepseek/deepseek-r1-distill-qwen-32b. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Perplexity: Sonar
LLM Models
Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features. Perplexity: Sonar is listed as a large language or generative AI model associated with perplexity, with the model identifier perplexity/sonar. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
DeepSeek: R1 Distill Llama 70B
LLM Models
DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across. DeepSeek: R1 Distill Llama 70B is listed as a large language or generative AI model associated with deepseek, with the model identifier deepseek/deepseek-r1-distill-llama-70b. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
DeepSeek: R1
LLM Models
DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. DeepSeek: R1 is listed as a large language or generative AI model associated with deepseek, with the model identifier deepseek/deepseek-r1. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
MiniMax: MiniMax-01
LLM Models
MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context. MiniMax: MiniMax-01 is listed as a large language or generative AI model associated with minimax, with the model identifier minimax/minimax-01. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Microsoft: Phi 4
LLM Models
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion. Microsoft: Phi 4 is listed as a large language or generative AI model associated with microsoft, with the model identifier microsoft/phi-4. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Sao10K: Llama 3.1 70B Hanami x1
LLM Models
This is [Sao10K](/sao10k)'s experiment over [Euryale v2.2](/sao10k/l3.1-euryale-70b). Sao10K: Llama 3.1 70B Hanami x1 is listed as a large language or generative AI model associated with sao10k, with the model identifier sao10k/l3.1-70b-hanami-x1. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
DeepSeek: DeepSeek V3
LLM Models
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations. DeepSeek: DeepSeek V3 is listed as a large language or generative AI model associated with deepseek, with the model identifier deepseek/deepseek-chat. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Sao10K: Llama 3.3 Euryale 70B
LLM Models
Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b). Sao10K: Llama 3.3 Euryale 70B is listed as a large language or generative AI model associated with sao10k, with the model identifier sao10k/l3.3-euryale-70b. It can be considered by developers, researchers, and AI application builders when evaluating models for programmatic AI workflows, experimentation, prototyping, model comparison, or integration into applications. The supplied description above captures the model-specific capabilities available in this dataset; exact context limits, supported input and output modalities, tool-calling behavior, structured-output support, pricing, rate limits, licensing, deployment options, and availability should be confirmed from the linked provider or model documentation because these technical details can vary between model versions and may change over time. For production use, developers should also evaluate output quality, latency, reliability, safety behavior, privacy requirements, and workload-specific performance against their own application requirements rather than assuming that one model configuration is suitable for every use case.
Frequently Asked Questions About LLM Models
What are LLM models and how do they work?
Large Language Models (LLMs) are AI models trained on vast amounts of text data to understand and generate human-like text. They use transformer architecture and can perform tasks like text generation, translation, summarization, and code completion.
Which LLM models are free to use?
Many LLM models are freely available including Llama 2, Mistral, Mixtral, Phi-2, and various models on Hugging Face. Our directory features only models with permissive licenses that allow commercial use.
How do I run LLM models locally?
You can run LLMs locally using tools like Ollama, LM Studio, or text-generation-webui. Most models require significant GPU memory (8GB+ VRAM recommended). Smaller models like Phi-2 and Llama 2 7B can run on consumer hardware.
What's the difference between open-source and proprietary LLMs?
Open-source LLMs like Llama 2 and Mistral have publicly available weights and can be run locally or fine-tuned. Proprietary models like GPT-4 are only accessible via API. Open-source models offer more control and privacy.
Can I use these LLM models for commercial projects?
Most models in our directory have permissive licenses (Apache 2.0, MIT) allowing commercial use. Always check the specific model's license on Hugging Face or the provider's website before using in production.