Library
88,213 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
-
image text to text model by xtools-at · transformers
Source for Qwensploit-V2-27B-CyberSecurity-Qwen3.8 (opens huggingface.co) xtools-at/Qwensploit-V2-27B-CyberSecurity-Qwen3.8 -
Sakana: Sakana Namazu
ModelsSakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...
Source for Sakana: Sakana Namazu (opens openrouter.ai) sakana/sakana-namazu -
Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).
Source for Sao10K: Llama 3.1 Euryale 70B v2.2 (opens openrouter.ai) sao10k/l3.1-euryale-70b -
Sakana: Fugu Ultra
ModelsFugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
Source for Sakana: Fugu Ultra (opens openrouter.ai) sakana/fugu-ultra -
Sakana: Fugu Max
ModelsFugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
Source for Sakana: Fugu Max (opens openrouter.ai) sakana/fugu-max -
Sakana: Fugu Ultra v2
ModelsFugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...
Source for Sakana: Fugu Ultra v2 (opens openrouter.ai) sakana/fugu-ultra-v2 -
Sao10K: Llama 3 8B Lunaris
ModelsLunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....
Source for Sao10K: Llama 3 8B Lunaris (opens openrouter.ai) sao10k/l3-lunaris-8b -
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...
Source for OpenAI: gpt-oss-safeguard-20b (opens openrouter.ai) openai/gpt-oss-safeguard-20b -
Mistral: Saba
ModelsMistral 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...
Source for Mistral: Saba (opens openrouter.ai) mistralai/mistral-saba -
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...
Source for inclusionAI: Ling 3.0 Flash Sante (opens openrouter.ai) inclusionai/ling-3.0-flash-sante -
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
Source for NVIDIA: Nemotron 3.5 Content Safety (opens openrouter.ai) nvidia/nemotron-3.5-content-safety -
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
Source for NVIDIA: Nemotron 3.5 Content Safety (free) (opens openrouter.ai) nvidia/nemotron-3.5-content-safety:free -
OpenAI: GPT-5 Mini
ModelsGPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....
Source for OpenAI: GPT-5 Mini (opens openrouter.ai) openai/gpt-5-mini -
OpenAI: GPT-5 Mini (batch)
ModelsGPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....
Source for OpenAI: GPT-5 Mini (batch) (opens openrouter.ai) openai/gpt-5-mini:batch -
Mancer: Weaver (alpha)
ModelsAn attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.
Source for Mancer: Weaver (alpha) (opens openrouter.ai) mancer/weaver -
Google: Gemma 2 27B
ModelsGemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...
Source for Google: Gemma 2 27B (opens openrouter.ai) google/gemma-2-27b-it -
Meta: Llama Guard 4 12B
ModelsLlama 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...
Source for Meta: Llama Guard 4 12B (opens openrouter.ai) meta-llama/llama-guard-4-12b -
Auto Code
ModelsAuto Code is OpenRouter’s router built specifically for coding agents and harnesses. It uses the same routing engine as the [Auto Router](https://openrouter.ai/openrouter/auto), with every request treated as part of an...
Source for Auto Code (opens openrouter.ai) openrouter/auto-code -
OpenAI: GPT-6 Luna Pro
ModelsGPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
Source for OpenAI: GPT-6 Luna Pro (opens openrouter.ai) openai/gpt-6-luna-pro -
OpenAI: GPT-6 Sol Pro
ModelsGPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
Source for OpenAI: GPT-6 Sol Pro (opens openrouter.ai) openai/gpt-6-sol-pro -
OpenAI: GPT-6 Astra Pro
ModelsGPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
Source for OpenAI: GPT-6 Astra Pro (opens openrouter.ai) openai/gpt-6-astra-pro -
GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
Source for OpenAI: GPT-6 Luna Pro (batch) (opens openrouter.ai) openai/gpt-6-luna-pro:batch -
GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
Source for OpenAI: GPT-6 Sol Pro (batch) (opens openrouter.ai) openai/gpt-6-sol-pro:batch -
GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
Source for OpenAI: GPT-6 Astra Pro (batch) (opens openrouter.ai) openai/gpt-6-astra-pro:batch
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.