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
Deep reasoning / research
10 models| Use case | Model | Model name | Eligibility | Sources | Context | Modalities | Description |
|---|---|---|---|---|---|---|---|
| Deep reasoning / research | stealth/space-bunny-alpha | Space Bunny Alpha | Verified $0 | openrouter · nous | 1 000 000 | text+image+video->text | Space 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 / research | muse-spark-1.3-contributor-free | muse-spark-1.3-contributor-free | Zen micro | opencode-zen | 1 048 576 | text | Muse 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 / research | nemotron-3-ultra-free | nemotron-3-ultra-free | Zen free | opencode-zen | 131 072 | text | Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy |
| Deep reasoning / research | google/gemma-4-31b-it:free | Google: Gemma 4 31B (free) | Verified $0 | openrouter | 262 144 | text+image+video->text | Gemma 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 / research | liquid/lfm-2.5-2.6b:free | LiquidAI: LFM2.5-2.6B (free) | Verified $0 | openrouter | 65 536 | text->text | LFM2.5-2.6B 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 / research | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | NVIDIA: Nemotron 3 Nano Omni (free) | Verified $0 | openrouter | 256 000 | text+image+audio+video->text | NVIDIA 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 / research | nvidia/nemotron-3-ultra-550b-a55b:free | NVIDIA: Nemotron 3 Ultra (free) | Verified $0 | openrouter | 1 000 000 | text->text | NVIDIA 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 / research | thinkingmachines/inkling:free | Thinking Machines: Inkling (free) | Verified $0 | openrouter | 1 048 576 | text+image+audio->text | Inkling 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 / research | thinkingmachines/inkling-small:free | Thinking Machines: Inkling Small (free) | Verified $0 | openrouter | 1 048 576 | text+image+audio->text | Inkling 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 / research | z-ai/glm-5.2:free | Z.ai: GLM 5.2 (free) | Verified $0 | openrouter | 32 768 | text->text | GLM 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| Use case | Model | Model name | Eligibility | Sources | Context | Modalities | Description |
|---|---|---|---|---|---|---|---|
| Agentic coding | meituan/longcat-2.0:free | Meituan: LongCat 2.0 | Verified $0 | nous | 1 048 756 | text->text | LongCat 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 coding | poolside/laguna-s-2.1:free | Poolside: Laguna S 2.1 (free) | Verified $0 | openrouter · nous | 262 144 | text->text | Laguna 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 coding | poolside/laguna-xs-2.1:free | Poolside: Laguna XS 2.1 (free) | Verified $0 | openrouter · nous | 262 144 | text->text | Laguna 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 coding | stepfun/step-3.7-flash:free | StepFun: Step 3.7 Flash | Verified $0 | nous | 262 144 | text+image+video->text | Step 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 coding | mimo-v2.5-free | mimo-v2.5-free | Zen free | opencode-zen | 1 048 576 | text | Open MiMo model for multimodal coding agents and long-context automation |
| Agentic coding | cohere/north-mini-code:free | Cohere: North Mini Code (free) | Verified $0 | openrouter | 256 000 | text->text | North 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 coding | qwen/qwen3.8-27b:free | Qwen: Qwen3.8 27B (free) | Verified $0 | openrouter | 262 144 | text+image+video->text | Qwen3.8 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| Use case | Model | Model name | Eligibility | Sources | Context | Modalities | Description |
|---|---|---|---|---|---|---|---|
| Vision / multimodal | google/gemma-4-26b-a4b-it:free | Google: Gemma 4 26B A4B (free) | Verified $0 | openrouter | 262 144 | text+image+video->text | Gemma 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| Use case | Model | Model name | Eligibility | Sources | Context | Modalities | Description |
|---|---|---|---|---|---|---|---|
| Fast / lightweight | inclusionai/ling-3.0-flash-fin:free | inclusionAI: Ling 3.0 Flash Fin (free) | Verified $0 | openrouter · nous | 262 144 | text->text | Ling 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 / lightweight | inclusionai/ling-3.0-flash-sante:free | inclusionAI: Ling 3.0 Flash Sante (free) | Verified $0 | openrouter · nous | 262 144 | text->text | Ling 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 / lightweight | nemotron-3.5-lightning-free | nemotron-3.5-lightning-free | Zen free | opencode-zen | 262 144 | text | Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads |
| Fast / lightweight | nvidia/nemotron-3.5-lightning:free | NVIDIA: Nemotron 3.5 Lightning (free) | Verified $0 | openrouter | 1 000 000 | text->text | NVIDIA 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| Use case | Model | Model name | Eligibility | Sources | Context | Modalities | Description |
|---|---|---|---|---|---|---|---|
| General purpose fallback | upstage/solar-pro4:free | Upstage: Solar Pro 4 | Verified $0 | nous | 524 288 | text->text | Solar 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 fallback | dots-studio/dots-3-note-preview:free | Dots Studio: Dots3-Note Preview (free) | Verified $0 | openrouter | 512 000 | text+image->text | Dots3-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 fallback | nvidia/nemotron-3-super-120b-a12b:free | NVIDIA: Nemotron 3 Super (free) | Verified $0 | openrouter | 262 144 | text->text | NVIDIA 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... |
No models match the current filters. Try a broader search or another use case.