Free LLMs17
Updated Oct 26, 2026, 8:33 AM UTC
The list couldn't be refreshed just now, so this is the last saved version.
17 models
- Cohere: North Mini Code (free)TextChatChat256K
cohere · OpenRouter — North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts…
- Dots Studio: Dots3-Note Preview (free)VisionChatChat512K · Vision
dots-studio · OpenRouter — Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B…
- Google: Gemma 4 26B A4B (free)VisionChatChat262K · Vision
google · OpenRouter — Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total…
- Google: Gemma 4 31B (free)VisionChatChat262K · Vision
google · OpenRouter — Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text…
- LiquidAI: LFM2.5-2.6B (free)TextChatChat66K
liquid · OpenRouter — LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and…
- NVIDIA: Nemotron 3 Nano Omni (free)VisionAudioChatChat256K · Vision · Audio
nvidia · OpenRouter — NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context…
- NVIDIA: Nemotron 3 Super (free)TextChatChat262K
nvidia · OpenRouter — NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute…
- NVIDIA: Nemotron 3 Ultra (free)TextChatChat1M
nvidia · OpenRouter — NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters…
- NVIDIA: Nemotron 3.5 Content Safety (free)VisionChatChat128K · Vision
nvidia · OpenRouter — NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from…
- NVIDIA: Nemotron 3.5 Lightning (free)TextChatChat1M
nvidia · OpenRouter — NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B…
- NVIDIA: Nemotron 3.5 Super VL (free)VisionChatChat1M · Vision
nvidia · OpenRouter — NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters…
- Poolside: Laguna S 2.1 (free)TextChatChat262K
poolside · OpenRouter — Laguna S 2.1 is the latest coding agent model from Poolside. Laguna S 2.1 is a 118B total parameter model with 8B…
- Poolside: Laguna XS 2.1 (free)TextChatChat262K
poolside · OpenRouter — Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside and a step forward from their…
- Recursive: Flint (free)TextChatChat262K
recursive · OpenRouter — Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total,…
- Thinking Machines: Inkling (free)VisionAudioChatChat1M · Vision · Audio
thinkingmachines · OpenRouter — Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters…
- Thinking Machines: Inkling Small (free)VisionAudioChatChat1M · Vision · Audio
thinkingmachines · OpenRouter — Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active…
- XingChen: Xing4.0 29B A4B (free)TextChatChat262K
xingchen-agi · OpenRouter — Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the…
Listed by OpenRouter as zero-priced. A listing doesn't guarantee the model is answering right now. Capabilities describe the upstream model; chat and API here are text-only.