Model directory · 25 currently available

Free models by use case

A practical directory of models confirmed as truly free by at least one configured source. Use the filters to narrow the roster by use case or search by model ID, capability, modality, or source.

Models25confirmed free
Use cases5directory groups
Sources3OpenRouter, Nous, Zen
25 models

Deep reasoning / research

10 models
Free models for Deep reasoning / research
Use caseModelModel nameEligibilitySourcesContextModalitiesDescription
Deep reasoning / researchstealth/space-bunny-alphaSpace Bunny AlphaVerified $0openrouter · nous1 000 000text+image+video->textSpace Bunny Alpha is an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support. It delivers adjustable reasoning effort, and a 1M-token context window. Space...
Deep reasoning / researchmuse-spark-1.3-contributor-freemuse-spark-1.3-contributor-freeZen microopencode-zen1 048 576textMuse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.
Deep reasoning / researchnemotron-3-ultra-freenemotron-3-ultra-freeZen freeopencode-zen131 072textLargest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
Deep reasoning / researchgoogle/gemma-4-31b-it:freeGoogle: Gemma 4 31B (free)Verified $0openrouter262 144text+image+video->textGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Deep reasoning / researchliquid/lfm-2.5-2.6b:freeLiquidAI: LFM2.5-2.6B (free)Verified $0openrouter65 536text->textLFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
Deep reasoning / researchnvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeNVIDIA: Nemotron 3 Nano Omni (free)Verified $0openrouter256 000text+image+audio+video->textNVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
Deep reasoning / researchnvidia/nemotron-3-ultra-550b-a55b:freeNVIDIA: Nemotron 3 Ultra (free)Verified $0openrouter1 000 000text->textNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
Deep reasoning / researchthinkingmachines/inkling:freeThinking Machines: Inkling (free)Verified $0openrouter1 048 576text+image+audio->textInkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...
Deep reasoning / researchthinkingmachines/inkling-small:freeThinking Machines: Inkling Small (free)Verified $0openrouter1 048 576text+image+audio->textInkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
Deep reasoning / researchz-ai/glm-5.2:freeZ.ai: GLM 5.2 (free)Verified $0openrouter32 768text->textGLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

Agentic coding

7 models
Free models for Agentic coding
Use caseModelModel nameEligibilitySourcesContextModalitiesDescription
Agentic codingmeituan/longcat-2.0:freeMeituan: LongCat 2.0Verified $0nous1 048 756text->textLongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...
Agentic codingpoolside/laguna-s-2.1:freePoolside: Laguna S 2.1 (free)Verified $0openrouter · nous262 144text->textLaguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...
Agentic codingpoolside/laguna-xs-2.1:freePoolside: Laguna XS 2.1 (free)Verified $0openrouter · nous262 144text->textLaguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...
Agentic codingstepfun/step-3.7-flash:freeStepFun: Step 3.7 FlashVerified $0nous262 144text+image+video->textStep 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
Agentic codingmimo-v2.5-freemimo-v2.5-freeZen freeopencode-zen1 048 576textOpen MiMo model for multimodal coding agents and long-context automation
Agentic codingcohere/north-mini-code:freeCohere: North Mini Code (free)Verified $0openrouter256 000text->textNorth Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
Agentic codingqwen/qwen3.8-27b:freeQwen: Qwen3.8 27B (free)Verified $0openrouter262 144text+image+video->textQwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

Vision / multimodal

1 models
Free models for Vision / multimodal
Use caseModelModel nameEligibilitySourcesContextModalitiesDescription
Vision / multimodalgoogle/gemma-4-26b-a4b-it:freeGoogle: Gemma 4 26B A4B (free)Verified $0openrouter262 144text+image+video->textGemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Fast / lightweight

4 models
Free models for Fast / lightweight
Use caseModelModel nameEligibilitySourcesContextModalitiesDescription
Fast / lightweightinclusionai/ling-3.0-flash-fin:freeinclusionAI: Ling 3.0 Flash Fin (free)Verified $0openrouter · nous262 144text->textLing 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment...
Fast / lightweightinclusionai/ling-3.0-flash-sante:freeinclusionAI: Ling 3.0 Flash Sante (free)Verified $0openrouter · nous262 144text->textLing 3.0 Flash Sante is a health and medicine-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for...
Fast / lightweightnemotron-3.5-lightning-freenemotron-3.5-lightning-freeZen freeopencode-zen262 144textFast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
Fast / lightweightnvidia/nemotron-3.5-lightning:freeNVIDIA: Nemotron 3.5 Lightning (free)Verified $0openrouter1 000 000text->textNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

General purpose fallback

3 models
Free models for General purpose fallback
Use caseModelModel nameEligibilitySourcesContextModalitiesDescription
General purpose fallbackupstage/solar-pro4:freeUpstage: Solar Pro 4Verified $0nous524 288text->textSolar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...
General purpose fallbackdots-studio/dots-3-note-preview:freeDots Studio: Dots3-Note Preview (free)Verified $0openrouter512 000text+image->textDots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...
General purpose fallbacknvidia/nemotron-3-super-120b-a12b:freeNVIDIA: Nemotron 3 Super (free)Verified $0openrouter262 144text->textNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...