[{"data":1,"prerenderedAt":526},["ShallowReactive",2],{"doc-\u002Fen\u002Fdocs\u002Fmodels-billing\u002Fmodels":3,"doc-surround-\u002Fen\u002Fdocs\u002Fmodels-billing\u002Fmodels":427,"doc-nav-en":434},{"id":4,"title":5,"body":6,"description":417,"extension":418,"meta":419,"navigation":420,"order":421,"path":422,"section":423,"seo":424,"stem":425,"__hash__":426},"docs_en\u002Fen\u002Fdocs\u002F03.models-billing\u002F12.models.md","Supported Models",{"type":7,"value":8,"toc":409},"minimark",[9,13,30,40,45,260,279,283,286,344,351,355,371,380,384],[10,11,5],"h1",{"id":12},"supported-models",[14,15,16,17,21,22,25,26,29],"p",{},"LingXizhi IDE natively supports ",[18,19,20],"strong",{},"15+ mainstream models"," including Kimi K3, GLM-5.2, DeepSeek-V4, Qwen3.6, Doubao and MiniMax, via ",[18,23,24],{},"official direct"," and ",[18,27,28],{},"Volcano Engine"," channels. The model list is pulled from the cloud by the kernel in real time — newly released models are available without upgrading the IDE.",[31,32,34],"callout",{"type":33},"tip",[14,35,36,39],{},[18,37,38],{},"The IDE is the source of truth for available models",": open \"Settings → Models\"; the dropdown lists every model available to your account. The table below lists representative models enabled by default and their key parameters.",[41,42,44],"h2",{"id":43},"model-list","Model List",[46,47,48,73],"table",{},[49,50,51],"thead",{},[52,53,54,58,61,64,67,70],"tr",{},[55,56,57],"th",{},"Model",[55,59,60],{},"Vendor",[55,62,63],{},"Tier",[55,65,66],{},"Context",[55,68,69],{},"Vision",[55,71,72],{},"Highlights",[74,75,76,108,128,148,167,186,204,222,241],"tbody",{},[52,77,78,85,88,91,94,97],{},[79,80,81],"td",{},[82,83,84],"code",{},"kimi-k3",[79,86,87],{},"Kimi (Moonshot AI)",[79,89,90],{},"Flagship",[79,92,93],{},"1M",[79,95,96],{},"✓",[79,98,99,100,103,104,107],{},"2.8T parameters, ",[18,101,102],{},"always-on thinking",", adjustable thinking depth via ",[82,105,106],{},"reasoning_effort"," (low \u002F high \u002F max), automatic prefix caching",[52,109,110,115,117,120,123,125],{},[79,111,112],{},[82,113,114],{},"kimi-k2.7-code",[79,116,87],{},[79,118,119],{},"Standard",[79,121,122],{},"256K",[79,124,96],{},[79,126,127],{},"Coding-focused model, thinking always on, image \u002F video input, built for Agent tasks",[52,129,130,135,138,140,142,145],{},[79,131,132],{},[82,133,134],{},"glm-5.2",[79,136,137],{},"Zhipu GLM",[79,139,90],{},[79,141,93],{},[79,143,144],{},"—",[79,146,147],{},"IndexShare index-reuse architecture, five thinking levels (Low \u002F Medium \u002F High \u002F Extra \u002F Max), native MCP tool calling",[52,149,150,155,158,160,162,164],{},[79,151,152],{},[82,153,154],{},"deepseek-v4-pro",[79,156,157],{},"DeepSeek",[79,159,90],{},[79,161,93],{},[79,163,144],{},[79,165,166],{},"1.6T-parameter MoE, thinking mode by default, open-source SOTA for Agentic Coding",[52,168,169,174,177,179,181,183],{},[79,170,171],{},[82,172,173],{},"qwen3.8-max-preview",[79,175,176],{},"Qwen",[79,178,90],{},[79,180,93],{},[79,182,144],{},[79,184,185],{},"Thinking-only mode (cannot be disabled), strongest reasoning, structured output",[52,187,188,193,195,197,199,201],{},[79,189,190],{},[82,191,192],{},"qwen3.7-max",[79,194,176],{},[79,196,90],{},[79,198,93],{},[79,200,144],{},[79,202,203],{},"Hybrid thinking mode (on by default), built-in tools",[52,205,206,211,213,215,217,219],{},[79,207,208],{},[82,209,210],{},"qwen3.7-plus",[79,212,176],{},[79,214,119],{},[79,216,93],{},[79,218,96],{},[79,220,221],{},"Hybrid thinking mode, high cost-performance, structured output",[52,223,224,229,232,234,236,238],{},[79,225,226],{},[82,227,228],{},"minimax-m3",[79,230,231],{},"MiniMax",[79,233,90],{},[79,235,93],{},[79,237,96],{},[79,239,240],{},"MSA sparse attention, native multimodal (image \u002F video), max output 512K",[52,242,243,248,250,252,255,257],{},[79,244,245],{},[82,246,247],{},"minimax-m2.7",[79,249,231],{},[79,251,119],{},[79,253,254],{},"200K",[79,256,144],{},[79,258,259],{},"229B-parameter MoE (10B active), thinking mode enforced",[31,261,262],{"type":33},[14,263,264,267,268,270,271,274,275,278],{},[18,265,266],{},"Thinking modes vary by model",": Kimi K3 keeps thinking always on, with ",[82,269,106],{}," controlling the depth; GLM-5.2's deep thinking requires ",[82,272,273],{},"thinking"," enabled with ",[82,276,277],{},"clear_thinking: false",". The kernel adapts these parameters automatically per model — no manual work needed after switching models.",[41,280,282],{"id":281},"access-channels","Access Channels",[14,284,285],{},"The same model can be served by multiple channels; the IDE picks an available one based on configuration:",[46,287,288,301],{},[49,289,290],{},[52,291,292,295,298],{},[55,293,294],{},"Channel",[55,296,297],{},"Type",[55,299,300],{},"Description",[74,302,303,316,327],{},[52,304,305,308,313],{},[79,306,307],{},"Official direct",[79,309,310],{},[82,311,312],{},"api",[79,314,315],{},"Official APIs of Zhipu GLM, DeepSeek, Alibaba Qwen, Moonshot AI Kimi and MiniMax",[52,317,318,320,324],{},[79,319,28],{},[79,321,322],{},[82,323,312],{},[79,325,326],{},"ByteDance Volcano Engine aggregation channel; all mainstream models above can be accessed through it",[52,328,329,332,341],{},[79,330,331],{},"Coding Plan \u002F Agent",[79,333,334,337,338],{},[82,335,336],{},"plan"," \u002F ",[82,339,340],{},"agent",[79,342,343],{},"Plan-based channels such as Zhipu Plan and Volcano Engine Plan; require the corresponding vendor's subscription",[14,345,346,347,350],{},"Aggregation channels such as SiliconFlow are also integrated. Channel and model availability is managed centrally on the server side — ",[18,348,349],{},"the model picker in the IDE is the source of truth for actual combinations",".",[41,352,354],{"id":353},"switching-models","Switching Models",[356,357,358,362,368],"ol",{},[359,360,361],"li",{},"Open \"Settings → Models\".",[359,363,364,365,350],{},"Pick a model in the \"Default model\" dropdown — the choice ",[18,366,367],{},"applies to AI chat, inline edit and RUSH tasks at the same time",[359,369,370],{},"If the dropdown is empty, the network or the kernel is usually not ready yet — wait a moment or restart the IDE.",[31,372,374],{"type":373},"warn",[14,375,376,379],{},[18,377,378],{},"Bigger context is not always better",": very long context increases the latency of each request and (with BYOK) the vendor cost. Use standard-tier models for everyday chat, and switch to flagship models for RUSH deep tasks.",[41,381,383],{"id":382},"next-steps","Next Steps",[385,386,387,395,402],"ul",{},[359,388,389,390,350],{},"Learn about built-in plan quotas and the daily reset rule: ",[391,392,394],"a",{"href":393},"\u002Fen\u002Fdocs\u002Fmodels-billing\u002Fplans-quota","Plans & Quota",[359,396,397,398,350],{},"Already have a vendor key? Bind it to get billed by the vendor with zero platform markup: ",[391,399,401],{"href":400},"\u002Fen\u002Fdocs\u002Fmodels-billing\u002Fbyok","BYOK",[359,403,404,405,350],{},"Use thinking mode and multimodal capabilities in chat: ",[391,406,408],{"href":407},"\u002Fen\u002Fdocs\u002Fguides\u002Fai-chat","AI Chat Guide",{"title":410,"searchDepth":411,"depth":411,"links":412},"",2,[413,414,415,416],{"id":43,"depth":411,"text":44},{"id":281,"depth":411,"text":282},{"id":353,"depth":411,"text":354},{"id":382,"depth":411,"text":383},"LingXizhi IDE natively supports 15+ mainstream models including Kimi K3, GLM-5.2 and DeepSeek-V4, via official direct and Volcano Engine channels","md",{},true,12,"\u002Fen\u002Fdocs\u002Fmodels-billing\u002Fmodels","Models & Billing",{"title":5,"description":417},"en\u002Fdocs\u002F03.models-billing\u002F12.models","YuDgIWzS8sWjFoWHZoGga6eTwsp-Gvtch04YYP45zy4",[428,432],{"title":429,"path":430,"stem":431,"children":-1},"Integrated Terminal","\u002Fen\u002Fdocs\u002Fguides\u002Fterminal","en\u002Fdocs\u002F02.guides\u002F11.terminal",{"title":394,"path":393,"stem":433,"children":-1},"en\u002Fdocs\u002F03.models-billing\u002F13.plans-quota",[435],{"title":436,"path":437,"stem":438,"children":439,"page":466},"En","\u002Fen","en",[440],{"title":441,"path":442,"stem":443,"children":444,"page":466},"Docs","\u002Fen\u002Fdocs","en\u002Fdocs",[445,467,496,505],{"title":446,"path":447,"stem":448,"children":449,"page":466},"Getting Started","\u002Fen\u002Fdocs\u002Fgetting-started","en\u002Fdocs\u002F01.getting-started",[450,454,458,462],{"title":451,"path":452,"stem":453},"Installation & Download","\u002Fen\u002Fdocs\u002Fgetting-started\u002Finstallation","en\u002Fdocs\u002F01.getting-started\u002F01.installation",{"title":455,"path":456,"stem":457},"Register & Sign In","\u002Fen\u002Fdocs\u002Fgetting-started\u002Fregister-login","en\u002Fdocs\u002F01.getting-started\u002F02.register-login",{"title":459,"path":460,"stem":461},"First-Time Setup","\u002Fen\u002Fdocs\u002Fgetting-started\u002Ffirst-setup","en\u002Fdocs\u002F01.getting-started\u002F03.first-setup",{"title":463,"path":464,"stem":465},"Migrate from VS Code","\u002Fen\u002Fdocs\u002Fgetting-started\u002Fmigrate-from-vscode","en\u002Fdocs\u002F01.getting-started\u002F04.migrate-from-vscode",false,{"title":468,"path":469,"stem":470,"children":471,"page":466},"Feature Guides","\u002Fen\u002Fdocs\u002Fguides","en\u002Fdocs\u002F02.guides",[472,475,479,483,487,491,495],{"title":473,"path":407,"stem":474},"AI Chat & Inline Edit","en\u002Fdocs\u002F02.guides\u002F05.ai-chat",{"title":476,"path":477,"stem":478},"RUSH Deep Task","\u002Fen\u002Fdocs\u002Fguides\u002Frush","en\u002Fdocs\u002F02.guides\u002F06.rush",{"title":480,"path":481,"stem":482},"FIM Code Completion","\u002Fen\u002Fdocs\u002Fguides\u002Ffim-completion","en\u002Fdocs\u002F02.guides\u002F07.fim-completion",{"title":484,"path":485,"stem":486},"Semantic Code Graph","\u002Fen\u002Fdocs\u002Fguides\u002Fcode-graph","en\u002Fdocs\u002F02.guides\u002F08.code-graph",{"title":488,"path":489,"stem":490},"MCP Tools & Marketplace","\u002Fen\u002Fdocs\u002Fguides\u002Fmcp","en\u002Fdocs\u002F02.guides\u002F09.mcp",{"title":492,"path":493,"stem":494},"Debugging & DAP","\u002Fen\u002Fdocs\u002Fguides\u002Fdebugging","en\u002Fdocs\u002F02.guides\u002F10.debugging",{"title":429,"path":430,"stem":431},{"title":423,"path":497,"stem":498,"children":499,"page":466},"\u002Fen\u002Fdocs\u002Fmodels-billing","en\u002Fdocs\u002F03.models-billing",[500,501,502],{"title":5,"path":422,"stem":425},{"title":394,"path":393,"stem":433},{"title":503,"path":400,"stem":504},"BYOK (Bring Your Own Key)","en\u002Fdocs\u002F03.models-billing\u002F14.byok",{"title":506,"path":507,"stem":508,"children":509,"page":466},"Reference & FAQ","\u002Fen\u002Fdocs\u002Freference","en\u002Fdocs\u002F04.reference",[510,514,518,522],{"title":511,"path":512,"stem":513},"Keyboard Shortcuts","\u002Fen\u002Fdocs\u002Freference\u002Fshortcuts","en\u002Fdocs\u002F04.reference\u002F15.shortcuts",{"title":515,"path":516,"stem":517},"Configuration","\u002Fen\u002Fdocs\u002Freference\u002Fconfiguration","en\u002Fdocs\u002F04.reference\u002F16.configuration",{"title":519,"path":520,"stem":521},"Kernel API","\u002Fen\u002Fdocs\u002Freference\u002Fkernel-api","en\u002Fdocs\u002F04.reference\u002F17.kernel-api",{"title":523,"path":524,"stem":525},"FAQ","\u002Fen\u002Fdocs\u002Freference\u002Ffaq","en\u002Fdocs\u002F04.reference\u002F18.faq",1786077825728]