InnerVault

Library

86,219 resources from 11 public sources. 46 checked by hand; the rest are unreviewed.

Results

1,209 results with any of your words Clear search and filters
  1. Qwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default....

    Indexed OpenRouter model list, qwen Updated yesterday

    qwen/qwen4-max
  2. freight-pulse

    MCP servers

    Ocean & multimodal freight intelligence: rates, landed cost, transit, customs, risk, ship decisions

    Stale Official MCP Registry, io.github.Baneado98 Updated 4 months ago 1 note

  3. mcp-context-server

    MCP servers

    An MCP server that provides persistent multimodal context storage for LLM agents.

    Stale Official MCP Registry, io.github.alex-feel Updated 7 months ago 2 notes

    mcp-context-server@2.2.2
  4. Callirra

    MCP servers

    Create images, video and audio; chat with multimodal AI; manage assets and reusable workflows.

    Stale Official MCP Registry, io.github.callirra-ai Updated 24 days ago 1 note

    @callirra/mcp@0.3.1
  5. Mixpeek

    MCP servers

    Give your agent eyes. Search video, images, and audio via the Mixpeek multimodal retrieval API.

    Stale Official MCP Registry, io.github.mixpeek Updated 7 months ago 2 notes

    @mixpeek/mcp@0.1.1
  6. Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...

    Indexed OpenRouter model list, stepfun Updated 40 days ago

    stepfun/step-5-preview
  7. Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...

    Indexed OpenRouter model list, google Updated 42 days ago

    google/gemini-nano-banana-2.1
  8. Fugu 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...

    Indexed OpenRouter model list, sakana Updated 2 months ago

    sakana/fugu-max
  9. Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

    Indexed OpenRouter model list, google Updated 2 months ago

    google/gemini-3.8-flash
  10. Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

    Indexed OpenRouter model list, anthropic Updated 4 months ago

    anthropic/claude-sonnet-5
  11. Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

    Indexed OpenRouter model list, anthropic Updated 5 months ago

    anthropic/claude-fable-5:batch
  12. Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...

    Indexed OpenRouter model list, perceptron Updated 6 months ago

    perceptron/perceptron-mk1
  13. Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...

    Indexed OpenRouter model list, google Updated 7 months ago

    google/lyria-3-pro-preview
  14. Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

    Indexed OpenRouter model list, mistralai Updated 11 months ago

    mistralai/devstral-2512
  15. MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...

    No longer listed OpenRouter model list, minimax Updated 22 months ago

    minimax/minimax-01
  16. Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...

    Indexed OpenRouter model list, mistralai Updated 2 years ago

    mistralai/mixtral-8x22b-instruct
  17. Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...

    Indexed OpenRouter model list, moondream Updated 33 days ago

    moondream/moondream3.1-9b-a2b
  18. 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:batch
  19. Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can...

    Indexed OpenRouter model list, inclusionai Updated 4 days ago

    inclusionai/ling-3.2-flash:free
  20. imp

    Agents & frameworks

    Run large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faster than vLLM. Even a model almost four times larger than the card's memory runs. Works with apps made for ChatGPT or Claude. Starts with one docker command.

    Stale GitHub, kekzl 124 ★MITUpdated 13 days ago

    git clone https://github.com/kekzl/imp.git
  21. nvidia-nim-mcp

    MCP servers

    MCP server for NVIDIA NIM - 50+ LLMs, multimodal, image gen, embeddings, reranking

    Stale Official MCP Registry, io.github.david-eve-za Updated 4 months ago 2 notes

    nvidia-nim-mcp@2.1.2
  22. Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...

    Indexed OpenRouter model list, meta Updated 36 days ago

    meta/muse-wonder
  23. Fugu 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...

    Indexed OpenRouter model list, sakana Updated 2 months ago

    sakana/fugu-ultra-v2
  24. Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

    Indexed OpenRouter model list, google Updated 2 months ago

    google/gemini-3.8-flash: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.