InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. A faster version of Whisper built on CTranslate2.

    Hand-checked InnerVault (hand-checked), SYSTRAN MIT

    pip install faster-whisper
  2. llama.cpp

    Models

    The C/C++ engine many local-model tools are built on. It runs models efficiently on ordinary hardware.

    Hand-checked InnerVault (hand-checked), ggml-org MIT

  3. Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

    Indexed OpenRouter model list, mistralai Updated 18 months ago

    mistralai/mistral-medium-3
  4. MythoMax 13B

    Models

    One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge

    Indexed OpenRouter model list, gryphe Updated 3 years ago

    gryphe/mythomax-l2-13b
  5. Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

    Indexed OpenRouter model list, qwen Updated 21 months ago

    qwen/qwen-plus
  6. Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

    Indexed OpenRouter model list, x-ai Updated 4 months ago

    x-ai/grok-4.5
  7. Pareto 26.9

    Models

    Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

    Indexed OpenRouter model list, unbiased Updated 34 days ago

    unbiased/pareto-26.9
  8. Pareto 26.10

    Models

    Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

    Indexed OpenRouter model list, unbiased Updated 32 days ago

    unbiased/pareto-26.10
  9. Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

    Indexed OpenRouter model list, cohere Updated 20 months ago

    cohere/command-a
  10. [Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

    Indexed OpenRouter model list, microsoft Updated 22 months ago

    microsoft/phi-4
  11. Mistral: Saba

    Models

    Mistral 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...

    Indexed OpenRouter model list, mistralai Updated 21 months ago

    mistralai/mistral-saba
  12. The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...

    Indexed OpenRouter model list, relace Updated 11 months ago

    relace/relace-search
  13. Tencent: Hy4

    Models

    The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...

    Indexed OpenRouter model list, tencent Updated 12 days ago

    tencent/hy4
  14. Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. This is a preview of the...

    Indexed OpenRouter model list, unbiased Updated 46 days ago

    unbiased/pareto-26.10-preview
  15. The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

    Indexed OpenRouter model list, mistralai Updated 11 months ago

    mistralai/ministral-14b-2512
  16. DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

    Indexed OpenRouter model list, deepseek Updated 11 months ago

    deepseek/deepseek-v3.2
  17. Mistral 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...

    Indexed OpenRouter model list, mistralai Updated 21 months ago

    mistralai/mistral-small-24b-instruct-2501
  18. Fugu 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...

    Indexed OpenRouter model list, sakana Updated 4 months ago

    sakana/fugu-ultra
  19. Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...

    Indexed OpenRouter model list, meta-llama Updated 2 years ago

    meta-llama/llama-3.1-8b-instruct
  20. Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).

    Indexed OpenRouter model list, x-ai Updated 3 months ago

    x-ai/grok-4.6
  21. Reka Edge

    Models

    Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...

    Indexed OpenRouter model list, rekaai Updated 8 months ago

    rekaai/reka-edge
  22. The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...

    Indexed OpenRouter model list, openai Updated 17 months ago

    openai/o3-pro
  23. May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

    Indexed OpenRouter model list, deepseek Updated 17 months ago

    deepseek/deepseek-r1-0528
  24. DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

    Indexed OpenRouter model list, deepseek Updated 20 months ago

    deepseek/deepseek-chat-v3-0324

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.