[{"data":1,"prerenderedAt":273},["ShallowReactive",2],{"navigation":3,"\u002Fproviders\u002Fcatalog":113,"\u002Fproviders\u002Fcatalog-surround":268},[4,23,44,87],{"title":5,"path":6,"stem":7,"children":8,"icon":22},"Getting Started","\u002Fgetting-started","1.getting-started\u002F1.index",[9,12,17],{"title":10,"path":6,"stem":7,"icon":11},"Introduction","i-lucide-house",{"title":13,"path":14,"stem":15,"icon":16},"Install VisionSqueezer (npm, cargo, pip)","\u002Fgetting-started\u002Finstallation","1.getting-started\u002F2.installation","i-lucide-download",{"title":18,"path":19,"stem":20,"icon":21},"MCP Setup","\u002Fgetting-started\u002Fmcp-setup","1.getting-started\u002F3.mcp-setup","i-lucide-plug","i-lucide-rocket",{"title":24,"icon":25,"path":26,"stem":27,"children":28,"page":43},"CLI","i-lucide-terminal","\u002Fcli","2.cli",[29,33,38],{"title":30,"path":31,"stem":32,"icon":25},"CLI Usage — Optimize Images for Vision LLMs","\u002Fcli\u002Fusage","2.cli\u002F1.usage",{"title":34,"path":35,"stem":36,"icon":37},"CLI Options Reference","\u002Fcli\u002Foptions","2.cli\u002F2.options","i-lucide-sliders-horizontal",{"title":39,"path":40,"stem":41,"icon":42},"Batch Mode and JSON Output","\u002Fcli\u002Fbatch-json","2.cli\u002F3.batch-json","i-lucide-package",false,{"title":45,"icon":46,"path":47,"stem":48,"children":49,"page":43},"Providers","i-lucide-cpu","\u002Fproviders","3.providers",[50,55,60,65,70,74,78,83],{"title":51,"path":52,"stem":53,"icon":54},"Claude (Patch-Based)","\u002Fproviders\u002Fclaude","3.providers\u002F1.claude","i-lucide-square",{"title":56,"path":57,"stem":58,"icon":59},"OpenAI GPT-6 \u002F GPT-5.6","\u002Fproviders\u002Fgpt","3.providers\u002F2.gpt","i-lucide-grid-2x2",{"title":61,"path":62,"stem":63,"icon":64},"Gemini (Large Tiles)","\u002Fproviders\u002Fgemini","3.providers\u002F3.gemini","i-lucide-grid-3x3",{"title":66,"path":67,"stem":68,"icon":69},"Llama Vision (Tiles)","\u002Fproviders\u002Fllama","3.providers\u002F4.llama","i-simple-icons-meta",{"title":71,"path":72,"stem":73,"icon":64},"Qwen-VL (Patch Grid)","\u002Fproviders\u002Fqwen","3.providers\u002F5.qwen",{"title":75,"path":76,"stem":77,"icon":59},"DeepSeek Flash + DeepSeek-VL2","\u002Fproviders\u002Fdeepseek","3.providers\u002F6.deepseek",{"title":79,"path":80,"stem":81,"icon":82},"Kimi Vision","\u002Fproviders\u002Fkimi","3.providers\u002F7.kimi","i-lucide-sparkles",{"title":84,"path":85,"stem":86},"Popular multimodal model catalog","\u002Fproviders\u002Fcatalog","3.providers\u002F8.catalog",{"title":88,"icon":89,"path":90,"stem":91,"children":92,"page":43},"Guides","i-lucide-book-open","\u002Fguides","4.guides",[93,98,103,108],{"title":94,"path":95,"stem":96,"icon":97},"Python Bindings","\u002Fguides\u002Fpython-bindings","4.guides\u002F1.python-bindings","i-lucide-file-code",{"title":99,"path":100,"stem":101,"icon":102},"Sandbox (Think in Code)","\u002Fguides\u002Fsandbox","4.guides\u002F2.sandbox","i-lucide-flask-conical",{"title":104,"path":105,"stem":106,"icon":107},"Crawler Integration","\u002Fguides\u002Fcrawler-integration","4.guides\u002F3.crawler-integration","i-lucide-globe",{"title":109,"path":110,"stem":111,"icon":112},"Token Budget for Vision LLM Images","\u002Fguides\u002Ftoken-budget","4.guides\u002F4.token-budget","i-lucide-gauge",{"id":114,"title":84,"body":115,"description":261,"extension":262,"links":263,"meta":264,"navigation":265,"path":85,"seo":266,"stem":86,"__hash__":267},"docs\u002F3.providers\u002F8.catalog.md",{"type":116,"value":117,"toc":254},"minimark",[118,122,127,158,162,165,216,239],[119,120,121],"p",{},"VisionSqueezer accepts aliases for the most-used current multimodal families. There is no universal “top 20” ranking, so this catalog follows current OpenRouter vision usage and Hugging Face image-text-to-text trends.",[123,124,126],"h2",{"id":125},"exact-profiles","Exact profiles",[119,128,129,133,134,133,137,133,140,133,143,133,146,149,150,153,154,157],{},[130,131,132],"code",{},"gpt6",", ",[130,135,136],{},"claude",[130,138,139],{},"gemini",[130,141,142],{},"llama",[130,144,145],{},"qwen",[130,147,148],{},"deepseek",", and ",[130,151,152],{},"deepseek-local"," use provider or open-weight formulas documented in the individual provider pages. ",[130,155,156],{},"kimi"," supports native vision, but its estimate is advisory because Moonshot does not publish a stable image billing grid.",[123,159,161],{"id":160},"popular-aliases-with-advisory-estimates","Popular aliases with advisory estimates",[119,163,164],{},"The following aliases are accepted and use one deterministic 28px\u002F2048px generic profile:",[119,166,167,133,170,133,173,133,176,133,179,133,182,133,185,133,188,133,191,133,194,133,197,133,200,133,203,133,206,133,209,149,212,215],{},[130,168,169],{},"glm",[130,171,172],{},"pixtral",[130,174,175],{},"mistral",[130,177,178],{},"gemma",[130,180,181],{},"internvl",[130,183,184],{},"minicpm",[130,186,187],{},"molmo",[130,189,190],{},"aya",[130,192,193],{},"phi4",[130,195,196],{},"granite",[130,198,199],{},"llava",[130,201,202],{},"falcon",[130,204,205],{},"minimax",[130,207,208],{},"step",[130,210,211],{},"ling",[130,213,214],{},"voyage",".",[119,217,218,219,133,222,133,225,133,228,133,231,234,235,238],{},"Use the full family alias when desired, for example ",[130,220,221],{},"glm-5.3-flash",[130,223,224],{},"pixtral-large",[130,226,227],{},"gemma-4",[130,229,230],{},"internvl3",[130,232,233],{},"llava-onevision",", or ",[130,236,237],{},"minimax-vl",". These estimates are not provider billing claims; resizing and compression remain exact.",[119,240,241,242,133,249,215],{},"Sources: ",[243,244,248],"a",{"href":245,"rel":246},"https:\u002F\u002Fopenrouter.ai\u002Fcollections\u002Fvision-models",[247],"nofollow","OpenRouter vision collection",[243,250,253],{"href":251,"rel":252},"https:\u002F\u002Fhuggingface.co\u002Fmodels?inference_provider=all&p=0&pipeline_tag=image-text-to-text&sort=trending",[247],"Hugging Face trending image-text-to-text models",{"title":255,"searchDepth":256,"depth":257,"links":258},"",1,2,[259,260],{"id":125,"depth":257,"text":126},{"id":160,"depth":257,"text":161},"Every model alias accepted by --model, from Claude and GPT-6 to Pixtral, Gemma, InternVL, Phi-4, and other popular vision models.","md",null,{},true,{"title":84,"description":261},"tJpvYrxVEdIBTUO-ZtzAKPigb5zY1iFzGnev2uffpS4",[269,271],{"title":79,"path":80,"stem":81,"description":270,"icon":82,"children":-1},"Kimi K2.5, K2.6, and K3 image support with an advisory native-resolution estimate.",{"title":94,"path":95,"stem":96,"description":272,"icon":97,"children":-1},"Install the VisionSqueezer Python bindings with pip install vision-squeezer and optimize images for vision LLMs using native pyo3 wheels.",1790809357099]