Library
88,213 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
-
Mistral: Mistral Small 3
ModelsMistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...
Source for Mistral: Mistral Small 3 (opens openrouter.ai) mistralai/mistral-small-24b-instruct-2501 -
OpenAI: o3
Modelso3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....
-
Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...
Source for Inference.net: Schematron V2 Small (opens openrouter.ai) inference-net/schematron-v2-small -
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 -
OpenAI: o3 (batch)
Modelso3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....
Source for OpenAI: o3 (batch) (opens openrouter.ai) openai/o3:batch -
Meta: Llama 4 Scout
ModelsLlama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
Source for Meta: Llama 4 Scout (opens openrouter.ai) meta-llama/llama-4-scout -
Qwen: Qwen3 Coder 480B A35B
ModelsQwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
Source for Qwen: Qwen3 Coder 480B A35B (opens openrouter.ai) qwen/qwen3-coder -
Meta: Llama 4 Maverick
ModelsLlama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
Source for Meta: Llama 4 Maverick (opens openrouter.ai) meta-llama/llama-4-maverick -
inclusionAI: Ling 3.0 Tiny
ModelsLing 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...
Source for inclusionAI: Ling 3.0 Tiny (opens openrouter.ai) inclusionai/ling-3.0-tiny -
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...
Source for Inference.net: Schematron V2 Turbo (opens openrouter.ai) inference-net/schematron-v2-turbo -
Mistral: Mistral Medium 3.5
ModelsMistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
Source for Mistral: Mistral Medium 3.5 (opens openrouter.ai) mistralai/mistral-medium-3-5 -
Google: Gemma 4 31B
ModelsGemma 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...
Source for Google: Gemma 4 31B (opens openrouter.ai) google/gemma-4-31b-it -
OpenAI: GPT-5
ModelsGPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...
Source for OpenAI: GPT-5 (opens openrouter.ai) openai/gpt-5 -
SpaceXAI: Grok 4.3
ModelsGrok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Source for SpaceXAI: Grok 4.3 (opens openrouter.ai) x-ai/grok-4.3 -
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
Source for Mistral: Mistral Medium 3.5 (batch) (opens openrouter.ai) mistralai/mistral-medium-3-5:batch -
Google: Gemma 4 31B (free)
ModelsGemma 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...
Source for Google: Gemma 4 31B (free) (opens openrouter.ai) google/gemma-4-31b-it:free -
OpenAI: GPT-5 Pro
ModelsGPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...
Source for OpenAI: GPT-5 Pro (opens openrouter.ai) openai/gpt-5-pro -
OpenAI: GPT-5 (batch)
ModelsGPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...
Source for OpenAI: GPT-5 (batch) (opens openrouter.ai) openai/gpt-5:batch -
OpenAI: GPT-4.1
ModelsGPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...
Source for OpenAI: GPT-4.1 (opens openrouter.ai) openai/gpt-4.1 -
Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...
Source for Mistral: Mistral Small 3.1 24B (opens openrouter.ai) mistralai/mistral-small-3.1-24b-instruct -
SpaceXAI: Grok 4.3 (batch)
ModelsGrok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Source for SpaceXAI: Grok 4.3 (batch) (opens openrouter.ai) x-ai/grok-4.3:batch -
OpenAI: GPT-5 Pro (batch)
ModelsGPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...
Source for OpenAI: GPT-5 Pro (batch) (opens openrouter.ai) openai/gpt-5-pro:batch -
OpenAI: GPT-4.1 (batch)
ModelsGPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...
Source for OpenAI: GPT-4.1 (batch) (opens openrouter.ai) openai/gpt-4.1:batch -
Google: Gemma 4 26B A4B
ModelsGemma 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...
Source for Google: Gemma 4 26B A4B (opens openrouter.ai) google/gemma-4-26b-a4b-it
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.