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 97-144 of 576 models
Qwen: Qwen3 Max Thinking
LLM Models
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it. Qwen: Qwen3 Max Thinking is listed as a large language or generative AI model associated with qwen, with the model identifier qwen/qwen3-max-thinking. 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.
Anthropic: Claude Opus 4.6
LLM Models
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective. Anthropic: Claude Opus 4.6 is listed as a large language or generative AI model associated with anthropic, with the model identifier anthropic/claude-opus-4.6. 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 Coder Next
LLM Models
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per. Qwen: Qwen3 Coder Next is listed as a large language or generative AI model associated with qwen, with the model identifier qwen/qwen3-coder-next. 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.
Free Models Router
LLM Models
The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that. Free Models Router is listed as a large language or generative AI model associated with openrouter, with the model identifier openrouter/free. 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.
StepFun: Step 3.5 Flash
LLM Models
Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. StepFun: Step 3.5 Flash is listed as a large language or generative AI model associated with stepfun, with the model identifier stepfun/step-3.5-flash. 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.
MoonshotAI: Kimi K2.5
LLM Models
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed. MoonshotAI: Kimi K2.5 is listed as a large language or generative AI model associated with moonshotai, with the model identifier moonshotai/kimi-k2.5. 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.
Upstage: Solar Pro 3
LLM Models
Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized. Upstage: Solar Pro 3 is listed as a large language or generative AI model associated with upstage, with the model identifier upstage/solar-pro-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.
MiniMax: MiniMax M2-her
LLM Models
MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message. MiniMax: MiniMax M2-her is listed as a large language or generative AI model associated with minimax, with the model identifier minimax/minimax-m2-her. 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.
Writer: Palmyra X5
LLM Models
Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million. Writer: Palmyra X5 is listed as a large language or generative AI model associated with writer, with the model identifier writer/palmyra-x5. 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.
LiquidAI: LFM2.5-1.2B-Thinking (free)
LLM Models
LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is. LiquidAI: LFM2.5-1.2B-Thinking (free) is listed as a large language or generative AI model associated with liquid, with the model identifier liquid/lfm-2.5-1.2b-thinking:free. 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.
LiquidAI: LFM2.5-1.2B-Instruct (free)
LLM Models
LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support. LiquidAI: LFM2.5-1.2B-Instruct (free) is listed as a large language or generative AI model associated with liquid, with the model identifier liquid/lfm-2.5-1.2b-instruct:free. 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 Audio
LLM Models
The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced. OpenAI: GPT Audio is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-audio. 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 Audio Mini
LLM Models
A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million. OpenAI: GPT Audio Mini is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-audio-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.
Z.ai: GLM 4.7 Flash
LLM Models
As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,. Z.ai: GLM 4.7 Flash is listed as a large language or generative AI model associated with z-ai, with the model identifier z-ai/glm-4.7-flash. 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-5.2-Codex
LLM Models
GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. OpenAI: GPT-5.2-Codex is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-5.2-codex. 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.
ByteDance Seed: Seed 1.6 Flash
LLM Models
Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of. ByteDance Seed: Seed 1.6 Flash is listed as a large language or generative AI model associated with bytedance-seed, with the model identifier bytedance-seed/seed-1.6-flash. 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.
ByteDance Seed: Seed 1.6
LLM Models
Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window. ByteDance Seed: Seed 1.6 is listed as a large language or generative AI model associated with bytedance-seed, with the model identifier bytedance-seed/seed-1.6. 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 M2.1
LLM Models
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world. MiniMax: MiniMax M2.1 is listed as a large language or generative AI model associated with minimax, with the model identifier minimax/minimax-m2.1. 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.
Z.ai: GLM 4.7
LLM Models
GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while. Z.ai: GLM 4.7 is listed as a large language or generative AI model associated with z-ai, with the model identifier z-ai/glm-4.7. 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: Gemini 3 Flash Preview
LLM Models
Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool. Google: Gemini 3 Flash Preview is listed as a large language or generative AI model associated with google, with the model identifier google/gemini-3-flash-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.
Xiaomi: MiMo-V2-Flash
LLM Models
MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a. Xiaomi: MiMo-V2-Flash is listed as a large language or generative AI model associated with xiaomi, with the model identifier xiaomi/mimo-v2-flash. 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.
NVIDIA: Nemotron 3 Nano 30B A3B (free)
LLM Models
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully. NVIDIA: Nemotron 3 Nano 30B A3B (free) is listed as a large language or generative AI model associated with nvidia, with the model identifier nvidia/nemotron-3-nano-30b-a3b:free. 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.
NVIDIA: Nemotron 3 Nano 30B A3B
LLM Models
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully. NVIDIA: Nemotron 3 Nano 30B A3B is listed as a large language or generative AI model associated with nvidia, with the model identifier nvidia/nemotron-3-nano-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.
OpenAI: GPT-5.2 Chat
LLM Models
GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on. OpenAI: GPT-5.2 Chat is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-5.2-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.
OpenAI: GPT-5.2 Pro
LLM Models
GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,. OpenAI: GPT-5.2 Pro is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-5.2-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.
OpenAI: GPT-5.2
LLM Models
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly. OpenAI: GPT-5.2 is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-5.2. 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: Devstral 2 2512
LLM Models
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring. Mistral: Devstral 2 2512 is listed as a large language or generative AI model associated with mistralai, with the model identifier mistralai/devstral-2512. 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.
Relace: Relace Search
LLM Models
The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic. Relace: Relace Search is listed as a large language or generative AI model associated with relace, with the model identifier relace/relace-search. 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.
Z.ai: GLM 4.6V
LLM Models
GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts. Z.ai: GLM 4.6V is listed as a large language or generative AI model associated with z-ai, with the model identifier z-ai/glm-4.6v. 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.
Nex AGI: DeepSeek V3.1 Nex N1
LLM Models
DeepSeek V3.1 Nex-N1 is the flagship release of the Nex-N1 series — a post-trained model designed to highlight agent autonomy, tool use, and real-world productivity. Nex-N1 demonstrates competitive performance across. Nex AGI: DeepSeek V3.1 Nex N1 is listed as a large language or generative AI model associated with nex-agi, with the model identifier nex-agi/deepseek-v3.1-nex-n1. 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.
EssentialAI: Rnj 1 Instruct
LLM Models
Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained from scratch with a focus on programming, math, and scientific reasoning. The model demonstrates strong performance. EssentialAI: Rnj 1 Instruct is listed as a large language or generative AI model associated with essentialai, with the model identifier essentialai/rnj-1-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.
Body Builder (beta)
LLM Models
Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:. Body Builder (beta) is listed as a large language or generative AI model associated with openrouter, with the model identifier openrouter/bodybuilder. 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-5.1-Codex-Max
LLM Models
GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic. OpenAI: GPT-5.1-Codex-Max is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-5.1-codex-max. 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.
Amazon: Nova 2 Lite
LLM Models
Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing. Amazon: Nova 2 Lite is listed as a large language or generative AI model associated with amazon, with the model identifier amazon/nova-2-lite-v1. 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: Ministral 3 14B 2512
LLM Models
The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language. Mistral: Ministral 3 14B 2512 is listed as a large language or generative AI model associated with mistralai, with the model identifier mistralai/ministral-14b-2512. 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: Ministral 3 8B 2512
LLM Models
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities. Mistral: Ministral 3 8B 2512 is listed as a large language or generative AI model associated with mistralai, with the model identifier mistralai/ministral-8b-2512. 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: Ministral 3 3B 2512
LLM Models
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities. Mistral: Ministral 3 3B 2512 is listed as a large language or generative AI model associated with mistralai, with the model identifier mistralai/ministral-3b-2512. 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 Large 3 2512
LLM Models
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license. Mistral: Mistral Large 3 2512 is listed as a large language or generative AI model associated with mistralai, with the model identifier mistralai/mistral-large-2512. 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.
Arcee AI: Trinity Mini
LLM Models
Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function. Arcee AI: Trinity Mini is listed as a large language or generative AI model associated with arcee-ai, with the model identifier arcee-ai/trinity-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.
DeepSeek: DeepSeek V3.2
LLM Models
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism. DeepSeek: DeepSeek V3.2 is listed as a large language or generative AI model associated with deepseek, with the model identifier deepseek/deepseek-v3.2. 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.
Prime Intellect: INTELLECT-3
LLM Models
INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math,. Prime Intellect: INTELLECT-3 is listed as a large language or generative AI model associated with prime-intellect, with the model identifier prime-intellect/intellect-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.
Anthropic: Claude Opus 4.5
LLM Models
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and. Anthropic: Claude Opus 4.5 is listed as a large language or generative AI model associated with anthropic, with the model identifier anthropic/claude-opus-4.5. 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.
AllenAI: Olmo 3 32B Think
LLM Models
Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and. AllenAI: Olmo 3 32B Think is listed as a large language or generative AI model associated with allenai, with the model identifier allenai/olmo-3-32b-think. 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.
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and. Google: Nano Banana Pro (Gemini 3 Pro Image Preview) is listed as a large language or generative AI model associated with google, with the model identifier google/gemini-3-pro-image-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.
Deep Cogito: Cogito v2.1 671B
LLM Models
Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning. Deep Cogito: Cogito v2.1 671B is listed as a large language or generative AI model associated with deepcogito, with the model identifier deepcogito/cogito-v2.1-671b. 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-5.1
LLM Models
GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning. OpenAI: GPT-5.1 is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-5.1. 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-5.1 Chat
LLM Models
GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on. OpenAI: GPT-5.1 Chat is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-5.1-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.
OpenAI: GPT-5.1-Codex
LLM Models
GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. OpenAI: GPT-5.1-Codex is listed as a large language or generative AI model associated with openai, with the model identifier openai/gpt-5.1-codex. 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.