{"id":137922,"date":"2026-02-13T11:19:19","date_gmt":"2026-02-13T03:19:19","guid":{"rendered":"https:\/\/vertu.com\/?post_type=aitools&p=137922"},"modified":"2026-02-13T11:25:05","modified_gmt":"2026-02-13T03:25:05","slug":"minimax-m2-5-free-in-kilo-code-state-of-the-art-model","status":"publish","type":"aitools","link":"https:\/\/legacy.vertu.com\/ar\/ai-tools\/minimax-m2-5-free-in-kilo-code-state-of-the-art-model\/","title":{"rendered":"MiniMax M2.5 Free in Kilo Code: State-of-the-Art Model"},"content":{"rendered":"

\"\"<\/h1>\n

Complete Guide to MiniMax's SOTA Breakthrough\u2014Free for One Week in Kilo's CLI, VS Code Extension, and More\u2014Rivaling Claude Opus 4.6, Beating Gemini 3 Pro, at Fraction of the Cost<\/p>\n

MiniMax M2.5<\/strong> represents a quantum leap for the Chinese AI lab, achieving 80.2% on SWE-Bench Verified<\/strong> (human-validated real-world GitHub issues) matching Claude Opus 4.6's standard performance<\/strong>, outperforming Gemini 3 Pro on SWE-Bench Pro<\/strong> (55.4% vs 43.3%) and Multi-SWE-Bench<\/strong> (51.3% vs 50.3%), while delivering 100 tokens per second throughput<\/strong> (3\u00d7 faster than Opus), all with only 10B activated parameters<\/strong> (smallest Tier-1 model). The Free Access<\/strong>: Available completely free for one week<\/strong> in Kilo Code (CLI, VS Code extension, IDE integrations) with no credits required<\/strong>, making SOTA performance accessible without “frontier tax.” The Architecture<\/strong>: “Total overhaul of M2.1 architecture” engineered specifically for Agent-Verse<\/strong> and agentic workflows, optimized for “thinking efficiency” through planning, achieving $0.3\/M input<\/strong> and $0.06\/M blended cost<\/strong> with cache (best price for SOTA model). The Competitive Position<\/strong>: MiniMax moves “into big leagues as truly SOTA lab,” blurring “OSS vs Proprietary distinction” with 51.3% Multi-SWE-Bench<\/strong>, 76.3% BrowseComp<\/strong>, rivaling best frontier models while maintaining cost efficiency. The Popularity<\/strong>: M2.1 already “most popular open-weight model on Kilo to date,” with M2.5 poised to “rule every category” on Kilo's leaderboard. The Self-Hosting Advantage<\/strong>: 10B parameter efficiency enables self-hosting without “massive clusters,” offering “unparalleled advantage for developers.” Access Points<\/strong>: Kilo Code via kilo.ai\/landing\/minimax-m25, CLI installation, VS Code marketplace extension, all IDE integrations, joining 1.5M+ developers using Kilo platform.<\/p>\n

Part I: The Breakthrough Performance<\/h2>\n

SWE-Bench Verified: 80.2% Matching Opus 4.6<\/h3>\n

The Benchmark<\/strong>: Human-validated subset of real-world GitHub issues testing production-level bug solving<\/p>\n

MiniMax M2.5<\/strong>: 80.2% accuracy<\/p>\n

Claude Opus 4.6<\/strong>: “Just below 80%” on standard trials<\/p>\n

The Significance<\/strong>: “M2.5 sits comfortably at 80.2% out-of-the-box”<\/p>\n

Anthropic's Prompt Modification<\/strong>: Opus 4.6 reaches 81.42% with specific prompt adjustment<\/p>\n

Real-World Testing<\/strong>: “Fits with what we're seeing with Opus in the wild”<\/p>\n

Competitive Assessment<\/strong>: “Formidable powerhouse rivaling best in industry”<\/p>\n

SWE-Bench Pro: Dominating Gemini 3 Pro<\/h3>\n

MiniMax M2.5<\/strong>: 55.4%<\/p>\n

Gemini 3 Pro<\/strong>: 43.3%<\/p>\n

Performance Gap<\/strong>: +12.1 percentage points<\/p>\n

What It Tests<\/strong>: “Increased difficulty and realism of advanced software engineering tasks”<\/p>\n

Proof<\/strong>: “Can handle” most rigorous engineering challenges<\/p>\n

Multi-SWE-Bench: Complex Multi-Step Superiority<\/h3>\n

MiniMax M2.5<\/strong>: 51.3%<\/p>\n

Gemini 3 Pro<\/strong>: 50.3%<\/p>\n

What It Measures<\/strong>: “Complex, multi-step software suites”<\/p>\n

Capability Demonstrated<\/strong>: “Superior autonomous execution in long-horizon tasks”<\/p>\n

Implication<\/strong>: Better at sustained reasoning and multi-phase problem-solving<\/p>\n

BrowseComp: Agentic Search Excellence<\/h3>\n

MiniMax M2.5<\/strong>: 76.3%<\/p>\n

What It Tests<\/strong>: Information retrieval and research capabilities<\/p>\n

Agentic Strength<\/strong>: “Catching up to and often surpassing major models like GPT-5.2 and Gemini 3 Pro in coding and research”<\/p>\n

The Complete Picture<\/h3>\n

Benchmark Summary<\/strong>:<\/p>\n

    \n
  • SWE-Bench Verified<\/strong>: 80.2% (matches Opus 4.6)<\/li>\n
  • SWE-Bench Pro<\/strong>: 55.4% (beats Gemini 3 Pro by 12.1 points)<\/li>\n
  • Multi-SWE-Bench<\/strong>: 51.3% (edges Gemini 3 Pro)<\/li>\n
  • BrowseComp<\/strong>: 76.3% (strong research capability)<\/li>\n<\/ul>\n

    Overall Assessment<\/strong>: “Not just incremental update; total overhaul of M2.1 architecture”<\/p>\n

    Part II: Speed and Efficiency Revolution<\/h2>\n

    Lightning Fast Throughput: 100 TPS<\/h3>\n

    Speed<\/strong>: 100 tokens per second<\/p>\n

    Versus Opus<\/strong>: 3\u00d7 faster in early testing<\/p>\n

    What It Means<\/strong>: Dramatically faster response times<\/p>\n

    User Experience<\/strong>: Near-instant feedback for complex queries<\/p>\n

    Agentic Advantage<\/strong>: Rapid iteration in autonomous workflows<\/p>\n

    Thinking Efficiency Optimization<\/h3>\n

    Training Focus<\/strong>: “Trained to optimize actions and output through planning”<\/p>\n

    Token Efficiency<\/strong>: More efficient than previous generations<\/p>\n

    Cost Impact<\/strong>: Lower token consumption for same quality<\/p>\n

    Planning Integration<\/strong>: Built-in planning reduces wasted tokens<\/p>\n

    Result<\/strong>: Better performance with fewer resources<\/p>\n

    The 10B Parameter Advantage<\/h3>\n

    Activated Parameters<\/strong>: Only 10 billion<\/p>\n

    Significance<\/strong>: “Smallest Tier-1 model in existence”<\/p>\n

    Comparison<\/strong>: Other Tier-1 models require “massive clusters”<\/p>\n

    Self-Hosting Benefit<\/strong>: “Unparalleled advantage for developers who want to self-host”<\/p>\n

    Deployment Flexibility<\/strong>: Feasible on consumer-grade hardware<\/p>\n

    Cost Savings<\/strong>: Lower infrastructure requirements<\/p>\n

    Always-On Efficiency<\/h3>\n

    Input Pricing<\/strong>: $0.3\/M tokens<\/p>\n

    Blended Cost with Cache<\/strong>: $0.06\/M tokens<\/p>\n

    Competitive Assessment<\/strong>: “Best price of any SOTA model for always-on agents”<\/p>\n

    Use Case<\/strong>: Continuous monitoring, real-time assistance, persistent agents<\/p>\n

    Economic Impact<\/strong>: Enables 24\/7 agent deployment affordably<\/p>\n

    Part III: Free Access Through Kilo Code<\/h2>\n

    The One-Week Free Promotion<\/h3>\n

    Duration<\/strong>: One week from launch (Feb 12, 2026)<\/p>\n

    Scope<\/strong>: “Completely free for all Kilo users”<\/p>\n

    No Restrictions<\/strong>: “No credits required\u2014just pure, unadulterated SOTA power”<\/p>\n

    Access Method<\/strong>: Select MiniMax M2.5 from model dropdown<\/p>\n

    Philosophy<\/strong>: “Give every developer world's most powerful tools without ‘frontier tax'”<\/p>\n

    Scale<\/strong>: “Biggest leap yet” for Kilo Code<\/p>\n

    Platform Integration<\/h3>\n

    Kilo CLI<\/strong>: Command-line interface access<\/p>\n

    VS Code Extension<\/strong>: Marketplace.visualstudio.com\/items?itemName=kilocode.Kilo-Code<\/p>\n

    IDE Support<\/strong>: All major IDEs integrated<\/p>\n

    Cloud Access<\/strong>: Kilo Cloud platform<\/p>\n

    Slack Integration<\/strong>: Kilo for Slack (previously made M2.1 free)<\/p>\n

    User Base<\/strong>: Join 1.5M+ developers<\/p>\n

    Installation Process<\/h3>\n

    Step 1<\/strong>: Visit kilo.ai\/landing\/minimax-m25<\/p>\n

    Step 2<\/strong>: Click “Install Kilo Code”<\/p>\n

    Step 3<\/strong>: Choose installation method (CLI, VS Code, etc.)<\/p>\n

    Step 4<\/strong>: Select MiniMax M2.5 from dropdown<\/p>\n

    Step 5<\/strong>: Start building immediately<\/p>\n

    Simplicity<\/strong>: No complex setup, instant access<\/p>\n

    Part IV: The MiniMax Model Family<\/h2>\n

    MiniMax M2.5 (New Release)<\/h3>\n

    Status<\/strong>: Free in Kilo (one week promotion)<\/p>\n

    Performance<\/strong>: SOTA on multiple benchmarks<\/p>\n

    Capabilities<\/strong>:<\/p>\n

      \n
    • Exceptional reasoning<\/li>\n
    • Superior coding<\/li>\n
    • Fast inference (100 TPS)<\/li>\n
    • Open weights coming<\/li>\n<\/ul>\n

      Best For<\/strong>: Production coding, complex problem-solving, agentic workflows<\/p>\n

      MiniMax M2.1 (High Performer)<\/h3>\n

      Pricing<\/strong>: $0.27\/M input tokens<\/p>\n

      Status<\/strong>: “Most popular open-weight model on Kilo to date”<\/p>\n

      Performance<\/strong>: “Competitive performance on practical coding benchmarks”<\/p>\n

      Reliability<\/strong>: “Reliable for production use cases”<\/p>\n

      Cost Position<\/strong>: “Fraction of frontier model costs”<\/p>\n

      Best For<\/strong>: Cost-effective production deployment<\/p>\n

      MiniMax M1-80k (Long Context)<\/h3>\n

      Pricing<\/strong>: $0.80\/M input tokens<\/p>\n

      Context Window<\/strong>: 80,000 tokens<\/p>\n

      Reasoning<\/strong>: “Advanced chain-of-thought reasoning”<\/p>\n

      Specialty<\/strong>: “Excellent for complex multi-step tasks”<\/p>\n

      Capabilities<\/strong>:<\/p>\n

        \n
      • Deep reasoning<\/li>\n
      • Complex task handling<\/li>\n
      • Extended context understanding<\/li>\n<\/ul>\n

        Best For<\/strong>: Multi-step analysis, large codebases, comprehensive reasoning<\/p>\n

        Part V: MiniMax Company Context<\/h2>\n

        The Organization<\/h3>\n

        Founded<\/strong>: 2022<\/p>\n

        Location<\/strong>: China (leading Chinese AI company)<\/p>\n

        Backing<\/strong>: Major investors including Alibaba, Tencent, HongShan<\/p>\n

        User Base<\/strong>: Over 200 million users globally<\/p>\n

        Specialization<\/strong>: Large language models and multi-modal AI technology<\/p>\n

        Open-Weight Philosophy<\/h3>\n

        Commitment<\/strong>: “Making advanced AI accessible to developers worldwide”<\/p>\n

        Previous Releases<\/strong>: M2 series, M1 models<\/p>\n

        Recognition<\/strong>: “Competitive performance on coding and reasoning benchmarks”<\/p>\n

        Future Plans<\/strong>: “MiniMax typically releases open weights for their models”<\/p>\n

        M2.5 Timeline<\/strong>: “Expect M2.5 weights on HuggingFace soon”<\/p>\n

        Community Benefit<\/strong>: Open weights enable research, fine-tuning, self-hosting<\/p>\n

        Part VI: Agentic Engineering Capabilities<\/h2>\n

        Designed for the Agent-Verse<\/h3>\n

        Core Design<\/strong>: “Engineered from ground up for Agent-Verse”<\/p>\n

        Primary Role<\/strong>: “Primary workhorse for future workspace”<\/p>\n

        Kilo's Excitement<\/strong>: “Particularly excited about agentic capabilities for planning and executing large-scale dev projects”<\/p>\n

        Optimization<\/strong>: “Specifically designed for agentic workflows”<\/p>\n

        Planning and Execution<\/h3>\n

        Planning Capability<\/strong>: Built-in task decomposition and strategy<\/p>\n

        Execution Quality<\/strong>: “Superior autonomous execution in long-horizon tasks”<\/p>\n

        Multi-Step Mastery<\/strong>: Handles complex sequential workflows<\/p>\n

        Error Recovery<\/strong>: Robust handling of obstacles in multi-phase tasks<\/p>\n

        Adaptability<\/strong>: Adjusts approach based on intermediate results<\/p>\n

        Kilo Code Modes for Every Workflow Step<\/h3>\n

        Ask Mode<\/strong>: “Knowledgeable technical assistant focused on answering questions without changing codebase”<\/p>\n

        Architect Mode<\/strong>: System design and architecture planning<\/p>\n

        Code Mode<\/strong>: Active code generation and modification<\/p>\n

        Debug Mode<\/strong>: Issue identification and resolution<\/p>\n

        Orchestrator Mode<\/strong>: Multi-agent coordination and workflow management<\/p>\n

        Custom Mode<\/strong>: User-defined specialized behaviors<\/p>\n

        M2.5 Performance<\/strong>: Expected to “rule every category” on Kilo leaderboard<\/p>\n

        Part VII: Competitive Landscape<\/h2>\n

        The “OSS vs Proprietary” Blur<\/h3>\n

        Previous Distinction<\/strong>: Clear gap between open-source and proprietary performance<\/p>\n

        M2.5 Impact<\/strong>: “OSS vs Proprietary distinction is blurring”<\/p>\n

        SOTA Lab Status<\/strong>: MiniMax now “truly SOTA lab with truly SOTA model”<\/p>\n

        Market Position<\/strong>: Competing directly with GPT-5.2, Claude Opus 4.6, Gemini 3 Pro<\/p>\n

        Kilo Code vs. Other Tools<\/h3>\n

        GitHub Copilot<\/strong>: Different pricing model, limited model selection<\/p>\n

        Cursor<\/strong>: Proprietary editor lock-in<\/p>\n

        Windsurf<\/strong>: Alternative agentic coding tool<\/p>\n

        Cline<\/strong>: Autonomous coding agent<\/p>\n

        Amp Code (Sourcegraph\/Cody)<\/strong>: Shutting down VS Code extension<\/p>\n

        Kilo Advantage<\/strong>: Model flexibility, platform agnostic, competitive pricing<\/p>\n

        The Leaderboard Dominance<\/h3>\n

        Current Status<\/strong>: “M2.1 has been top model on Kilo's leaderboard for every mode except Architect and Orchestrator”<\/p>\n

        M2.5 Potential<\/strong>: “Will M2.5 push MiniMax over edge to rule every category?”<\/p>\n

        User Validation<\/strong>: Popularity driven by actual developer preference<\/p>\n

        Performance Proof<\/strong>: Real-world results on Kilo platform<\/p>\n

        Part VIII: Practical Applications<\/h2>\n

        Production Bug Solving<\/h3>\n

        Use Case<\/strong>: Real-world GitHub issue resolution<\/p>\n

        Evidence<\/strong>: 80.2% SWE-Bench Verified<\/p>\n

        Workflow<\/strong>:<\/p>\n

          \n
        1. Analyze bug report<\/li>\n
        2. Navigate codebase<\/li>\n
        3. Identify root cause<\/li>\n
        4. Implement fix<\/li>\n
        5. Validate solution<\/li>\n<\/ol>\n

          Speed<\/strong>: 100 TPS enables rapid iteration<\/p>\n

          Large-Scale Development Projects<\/h3>\n

          Planning<\/strong>: Task decomposition and sequencing<\/p>\n

          Execution<\/strong>: Multi-file code generation<\/p>\n

          Integration<\/strong>: Component coordination<\/p>\n

          Testing<\/strong>: Validation and debugging<\/p>\n

          Documentation<\/strong>: Comprehensive commenting<\/p>\n

          Complex Multi-Step Tasks<\/h3>\n

          Research<\/strong>: Information gathering via BrowseComp capability<\/p>\n

          Analysis<\/strong>: Deep reasoning through chain-of-thought<\/p>\n

          Synthesis<\/strong>: Combining multiple sources<\/p>\n

          Implementation<\/strong>: Translation to working code<\/p>\n

          Optimization<\/strong>: Iterative refinement<\/p>\n

          Always-On Agent Deployment<\/h3>\n

          Cost-Effective<\/strong>: $0.06\/M blended cost with cache<\/p>\n

          Use Cases<\/strong>:<\/p>\n

            \n
          • Code review automation<\/li>\n
          • Continuous testing<\/li>\n
          • Real-time documentation<\/li>\n
          • Issue triage<\/li>\n
          • Pull request assistance<\/li>\n<\/ul>\n

            Economic Viability<\/strong>: “Best price any SOTA model for always-on agents”<\/p>\n

            Part IX: Why This Matters<\/h2>\n

            Democratizing SOTA Performance<\/h3>\n

            Philosophy<\/strong>: “Give every developer world's most powerful tools without ‘frontier tax'”<\/p>\n

            Free Access<\/strong>: No cost barrier for one week<\/p>\n

            Post-Promotion<\/strong>: Still most affordable SOTA option<\/p>\n

            Impact<\/strong>: Levels playing field for individual developers, startups, students<\/p>\n

            The Self-Hosting Future<\/h3>\n

            10B Parameter Efficiency<\/strong>: Makes self-hosting practical<\/p>\n

            Infrastructure Savings<\/strong>: No massive cluster requirements<\/p>\n

            Data Sovereignty<\/strong>: Keep models on own infrastructure<\/p>\n

            Customization<\/strong>: Fine-tune for specific domains<\/p>\n

            Independence<\/strong>: Not dependent on API availability<\/p>\n

            Moving the Industry Forward<\/h3>\n

            Quote<\/strong>: “Best way to move industry forward is to put best models in hands of every developer”<\/p>\n

            Competition Effect<\/strong>: Pressure on proprietary labs to improve<\/p>\n

            Innovation Acceleration<\/strong>: More developers with SOTA tools create faster progress<\/p>\n

            Knowledge Sharing<\/strong>: Open weights enable community research<\/p>\n

            Conclusion: The New SOTA Standard<\/h2>\n

            What M2.5 Achieves<\/h3>\n

            Performance<\/strong>: 80.2% SWE-Bench Verified matching Opus 4.6<\/p>\n

            Speed<\/strong>: 100 TPS, 3\u00d7 faster than Opus<\/p>\n

            Efficiency<\/strong>: 10B parameters, smallest Tier-1 model<\/p>\n

            Cost<\/strong>: $0.06\/M blended, best SOTA pricing<\/p>\n

            Versatility<\/strong>: Excellence across coding, reasoning, research<\/p>\n

            Accessibility<\/strong>: Free in Kilo for one week, open weights coming<\/p>\n

            Why It's Revolutionary<\/h3>\n

            Blurs OSS\/Proprietary Gap<\/strong>: Open-weight model matching closed-source performance<\/p>\n

            Enables Self-Hosting<\/strong>: First Tier-1 model practical for individual deployment<\/p>\n

            Affordable Always-On Agents<\/strong>: Economic viability of continuous AI assistance<\/p>\n

            Democratized SOTA<\/strong>: No frontier tax for world-class performance<\/p>\n

            How to Get Started<\/h3>\n

            Immediate Action<\/strong>: Visit kilo.ai\/landing\/minimax-m25<\/p>\n

            Install<\/strong>: Choose CLI, VS Code extension, or IDE integration<\/p>\n

            Select<\/strong>: Pick MiniMax M2.5 from dropdown<\/p>\n

            Build<\/strong>: Start coding with SOTA assistance immediately<\/p>\n

            Free Window<\/strong>: One week, no credits required<\/p>\n

            Post-Promotion<\/strong>: Still most affordable SOTA option available<\/p>\n

            \n

            Try M2.5 Free<\/strong>:<\/p>\n

              \n
            • Landing Page<\/strong>: kilo.ai\/landing\/minimax-m25<\/li>\n
            • CLI<\/strong>: Install via Kilo Code CLI<\/li>\n
            • VS Code<\/strong>: marketplace.visualstudio.com (search “Kilo Code”)<\/li>\n
            • Docs<\/strong>: kilo.ai\/docs<\/li>\n
            • Blog<\/strong>: blog.kilo.ai<\/li>\n<\/ul>\n

              Join<\/strong>: 1.5M+ developers using Kilo Code<\/p>\n

              \n

              The Bottom Line<\/strong>: MiniMax M2.5 achieves breakthrough SOTA performance\u201480.2% SWE-Bench Verified (matching Claude Opus 4.6), 55.4% SWE-Bench Pro (beating Gemini 3 Pro by 12.1 points), 51.3% Multi-SWE-Bench, 76.3% BrowseComp\u2014at 100 tokens\/second speed (3\u00d7 faster than Opus) with only 10B activated parameters (smallest Tier-1 model enabling self-hosting) and $0.06\/M blended cost (best SOTA pricing). Available completely free for one week in Kilo Code (CLI, VS Code, all IDEs) with no credits required, blurring “OSS vs Proprietary distinction” as MiniMax moves “into big leagues as truly SOTA lab.” Engineered for Agent-Verse with planning optimization, expected to “rule every category” on Kilo leaderboard, joining M2.1 as “most popular open-weight model” while providing “world's most powerful tools without frontier tax.” Open weights coming to HuggingFace soon. Access at kilo.ai\/landing\/minimax-m25\u2014join 1.5M+ developers experiencing production-grade AI assistance democratized.<\/p>\n

              The future of coding assistance just got faster, cheaper, and accessible to everyone. One week free. No frontier tax. Pure SOTA power.<\/strong><\/p>","protected":false},"excerpt":{"rendered":"

              Complete Guide to MiniMax’s SOTA Breakthrough\u2014Free for One Week in Kilo’s CLI, VS Code Extension, and More\u2014Rivaling Claude Opus 4.6, […]<\/p>","protected":false},"author":11214,"featured_media":137961,"menu_order":0,"template":"","format":"standard","meta":{"_acf_changed":false,"content-type":"","site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"set","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[468],"tags":[],"class_list":["post-137922","aitools","type-aitools","status-publish","format-standard","has-post-thumbnail","hentry","category-best-post"],"acf":[],"_links":{"self":[{"href":"https:\/\/legacy.vertu.com\/ar\/wp-json\/wp\/v2\/aitools\/137922","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/legacy.vertu.com\/ar\/wp-json\/wp\/v2\/aitools"}],"about":[{"href":"https:\/\/legacy.vertu.com\/ar\/wp-json\/wp\/v2\/types\/aitools"}],"author":[{"embeddable":true,"href":"https:\/\/legacy.vertu.com\/ar\/wp-json\/wp\/v2\/users\/11214"}],"version-history":[{"count":3,"href":"https:\/\/legacy.vertu.com\/ar\/wp-json\/wp\/v2\/aitools\/137922\/revisions"}],"predecessor-version":[{"id":137977,"href":"https:\/\/legacy.vertu.com\/ar\/wp-json\/wp\/v2\/aitools\/137922\/revisions\/137977"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/legacy.vertu.com\/ar\/wp-json\/wp\/v2\/media\/137961"}],"wp:attachment":[{"href":"https:\/\/legacy.vertu.com\/ar\/wp-json\/wp\/v2\/media?parent=137922"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/legacy.vertu.com\/ar\/wp-json\/wp\/v2\/categories?post=137922"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/legacy.vertu.com\/ar\/wp-json\/wp\/v2\/tags?post=137922"}],"curies":[{"name":"\u0648\u0648\u0631\u062f\u0628\u0631\u064a\u0633","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}