InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

    Indexed OpenRouter model list, nvidia Updated 33 days ago

    nvidia/nemotron-3.5-super-vl:free
  2. Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...

    No longer listed OpenRouter model list, xingchen-agi Updated 32 days ago

    xingchen-agi/xing4.0-29b-a4b:free
  3. DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...

    Indexed OpenRouter model list, deepseek Updated 31 days ago

    deepseek/deepseek-v4.1-flash-1017
  4. Wavn

    MCP servers

    The deciding place: argue the call, decide, keep the reasons, get the work back as finished files.

    Stale Official MCP Registry, ai.wavn Updated 3 months ago 1 note

  5. Advisory MCP tools: policy score, reasoning checklist, compression. To enforce, use delentia-guard.

    Stale Official MCP Registry, io.github.delentia-labs Updated 25 days ago 1 note

    delentia-mcp@2.1.2
  6. ejentum-mcp

    MCP servers

    Reasoning, code, anti-deception, memory harness MCP tools. Stdio or HTTPS api.ejentum.com/mcp

    Stale Official MCP Registry, io.github.ejentum Updated 5 months ago 3 notes

    ejentum-mcp@0.2.2
  7. Staylist World

    MCP servers

    Free hotel comparison for AI assistants: 77k hotels on the same criteria, with reasons. No key.

    Stale Official MCP Registry, world.staylist Updated 46 days ago 1 note

  8. representments.com

    MCP servers

    Explains each card chargeback reason code and the proof that wins it, and prices custom responses.

    Stale Official MCP Registry, com.representments Updated 17 days ago 1 note

  9. Sagashi

    MCP servers

    Checks Sydney homes for sale against a buyer's budget, school zone, commute and area, with reasons.

    Stale Official MCP Registry, au.sagashi Updated 6 days ago 1 note

  10. MarketFrame

    MCP servers

    Daily news tone for every FTSE 100 company, with stories and reasons. Free, read-only. Not advice.

    Stale Official MCP Registry, app.marketframe Updated 5 days ago 1 note

  11. Odile Gate Oversight

    MCP servers

    Watch Odile Gate: runs, held actions, audit log with signed export, metrics and refusal reasons.

    Indexed Official MCP Registry, com.odilelabs Updated 3 days ago 1 note

  12. Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...

    Indexed OpenRouter model list, anthropic Updated 41 days ago

    anthropic/claude-haiku-5.5:batch
  13. GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...

    Indexed OpenRouter model list, openai Updated 49 days ago

    openai/gpt-6.1-sol
  14. GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...

    Indexed OpenRouter model list, openai Updated 56 days ago

    openai/gpt-6-luna
  15. GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...

    Indexed OpenRouter model list, openai Updated 56 days ago

    openai/gpt-6-sol
  16. Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

    Indexed OpenRouter model list, google Updated 3 months ago

    google/gemini-3.6-flash
  17. Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

    Indexed OpenRouter model list, google Updated 3 months ago

    google/gemini-3.5-flash-lite:batch
  18. 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...

    Indexed OpenRouter model list, stepfun Updated 5 months ago

    stepfun/step-3.7-flash
  19. Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

    Indexed OpenRouter model list, qwen Updated 6 months ago

    qwen/qwen3.6-35b-a3b
  20. MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...

    Indexed OpenRouter model list, xiaomi Updated 6 months ago

    xiaomi/mimo-v2.5
  21. Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

    Indexed OpenRouter model list, moonshotai Updated 7 months ago

    moonshotai/kimi-k2.6
  22. 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...

    Indexed OpenRouter model list, google Updated 7 months ago

    google/gemma-4-26b-a4b-it:free
  23. Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...

    Indexed OpenRouter model list, anthropic Updated 9 months ago

    anthropic/claude-sonnet-4.6:batch
  24. The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

    Indexed OpenRouter model list, qwen Updated 9 months ago

    qwen/qwen3.5-plus-02-15

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.