# Dokumentasi - [Dokumentasi XPlor3](/id): Cara memakai studio XPlor3, dari generate pertama sampai menghubungkan aplikasimu lewat MCP dan REST API. - **Panduan** - Memulai - [Membuat akun](/id/mulai): Daftar di studio, verifikasi email, lalu kenali bagian-bagian studio yang akan paling sering kamu pakai. - [Generate pertama](/id/mulai/generate-pertama): Dari memilih model sampai hasilnya tersimpan, lengkap dengan cara membaca biaya sebelum kredit dipotong. - [Kredit dan pembayaran](/id/mulai/kredit): Satu saldo untuk semua model, cara kredit dipotong dan kembali, dan cara membelinya lewat QRIS. - Studio - [Konsol generate](/id/studio/konsol): Tempat setiap model dijalankan, dan fitur-fitur kecil di dalamnya yang menghemat waktu dan kredit. - [Multi Generate](/id/studio/multi-generate): Satu prompt di sampai lima model sekaligus, supaya kamu bisa membandingkan hasil dan biayanya berdampingan. - [Brand Kit](/id/studio/brand-kit): Simpan identitas merek sekali, lalu masukkan ke prompt dan konsol dengan satu tombol. - [Riwayat, Pustaka, dan Proyek](/id/studio/riwayat-proyek): Di mana hasil dan berkasmu tersimpan, cara merapikannya, dan berapa lama semuanya disimpan. - [Berbagi dan hak atas hasil](/id/studio/berbagi): Tautan berbagi untuk satu hasil, galeri komunitas, dan siapa pemilik gambar dan video yang kamu buat. - Model - [Katalog model](/id/model): Semua model gambar, video, dan suara di XPlor3, dikelompokkan per jenis, lengkap dengan slug untuk API. - [Memilih model](/id/model/memilih-model): Cara menentukan model yang tepat dari jenis pekerjaan, masukan yang kamu punya, dan anggaran. - [Menulis prompt](/id/model/menulis-prompt): Susunan prompt yang mudah dipahami model gambar dan video, dengan contoh yang bisa langsung dicoba. - Workflow - [Mengenal Workflow](/id/workflow): Rangkai beberapa model di satu kanvas, sehingga hasil satu langkah langsung jadi masukan langkah berikutnya. - [Jenis node](/id/workflow/node): Tujuh jenis node di kanvas Workflow, dan kapan masing-masing dipakai. - [Banyak foto sekaligus](/id/workflow/batch): Jalankan workflow yang sama untuk sampai 50 foto dalam satu batch, misalnya satu katalog produk. - [Template dan berbagi workflow](/id/workflow/template): Mulai dari template workflow di Beranda atau workflow bawaan di akunmu, lalu simpan dan pindahkan sebagai berkas JSON. - Toko - [Toko](/id/toko): Panduan PDF dan paket aset dari tim XPlor3, dibayar dengan kredit dan bisa diunduh ulang kapan saja. - **Developer** - [Ringkasan untuk developer](/id/developer): Dua cara memakai XPlor3 dari luar studio, MCP untuk agen AI dan REST API untuk aplikasimu, dengan satu kunci API. - [Kredensial](/id/developer/kredensial): Membuat, menyimpan, dan mencabut kunci API yang dipakai untuk MCP dan REST API. - [Server MCP](/id/developer/mcp): Hubungkan Claude Desktop, Cursor, atau agen lokal ke XPlor3, lalu minta agen membuat gambar dan video dari percakapan. - REST API - [Mengenal REST API](/id/developer/rest-api): Base URL, autentikasi, format request dan respons, serta cara menguji kunci pertamamu. - [Alur generate](/id/developer/rest-api/generate): Lima langkah dari memilih model sampai mengunduh berkas hasil, dengan contoh curl, JavaScript, dan Python. - [Webhook](/id/developer/rest-api/webhook): XPlor3 memberi tahu server kamu saat job selesai, gagal, atau dibatalkan, jadi kamu tidak perlu membaca status berulang kali. - [Referensi endpoint](/id/developer/rest-api/referensi): Endpoint REST yang tersedia untuk kunci API, dengan field request dan respons masing-masing. - [Batas dan error](/id/developer/rest-api/error): Format error, kode yang paling sering ditemui, batas request per menit, dan cara menanganinya. - Referensi model - [Referensi model](/id/developer/model): modelSlug, field input, nilai yang diterima, dan aturan setiap model XPlor3, untuk REST API dan MCP. - **Gambar** - [GPT Image 2.5](/id/developer/model/gpt-image-2-5): Model visual OpenAI dengan dua gaya render, latar transparan opsional, dan resolusi hingga 4K. - [Nano Banana](/id/developer/model/nano-banana): Model visual Google untuk pembuatan gambar cepat dan penyuntingan berbasis gambar acuan. - [Nano Banana 2](/id/developer/model/nano-banana-2): Model visual Google generasi kedua dengan opsi tier Lite untuk efisiensi dan tier Standard hingga resolusi 4K. - [Nano Banana 2.1](/id/developer/model/nano-banana-2-1): Penerus Nano Banana 2 dari Google untuk membuat dan mengedit gambar hingga 4K, dengan harga lebih hemat di setiap resolusi. - [Nano Banana Pro](/id/developer/model/nano-banana-pro): Model visual flagship Google yang dirancang untuk penalaran prompt kompleks, detail fotorealistik, dan konsistensi karakter. - [Seedream 4](/id/developer/model/seedream-4): Model visual ByteDance dengan fleksibilitas rasio kanvas dan dukungan rendering hingga resolusi 4K. - [Seedream 4.5](/id/developer/model/seedream-4-5): Model visual ByteDance versi 4.5 dengan peningkatan detail tekstur dan preset kualitas bertingkat. - [Seedream 5](/id/developer/model/seedream-5): Model visual ByteDance generasi terbaru dengan tier Lite untuk rendering cepat, Pro untuk presisi komposisi artistik, Flash yang paling hemat, dan tier Layer yang memecah satu gambar menjadi lapisan terpisah. - [GPT Image 1.5](/id/developer/model/gpt-image-1-5): Model visual OpenAI dengan pemahaman instruksi teks terarah dan dua opsi kualitas rendering. - [GPT Image 2](/id/developer/model/gpt-image-2): Model visual OpenAI generasi kedua dengan kemampuan render tipografi dalam gambar, variasi rasio kanvas, dan resolusi hingga 4K. - [Grok Imagine Image 2](/id/developer/model/grok-imagine-image-2): Model visual xAI generasi kedua untuk pembuatan gambar dari teks dan penyuntingan multi-aset hingga lima gambar acuan. - [Grok Imagine Image](/id/developer/model/grok-imagine-image): Model visual xAI untuk pembuatan gambar cepat dari prompt teks, mendukung satu gambar acuan opsional. - [Wan 2.7 Image](/id/developer/model/wan-2-7-image): Model visual Alibaba bertier Standard dan Pro untuk resolusi hingga 4K, menerima hingga sembilan gambar acuan sekaligus. - [Qwen 3](/id/developer/model/qwen-3): Model visual Alibaba tier Standard dan Pro beresolusi hingga 2K, mendukung komposisi ulang dari 3 gambar acuan. - [Qwen 2](/id/developer/model/qwen-2): Model visual Alibaba berkecepatan tinggi untuk draf dari prompt ringkas dan pengeditan berbasis instruksi teks. - [Qwen 2.1](/id/developer/model/qwen-2-1): Model visual Alibaba beresolusi hingga 2K dengan opsi latar transparan dan blending hingga 10 gambar acuan. - [Z-Image](/id/developer/model/z-image): Model visual Alibaba berbobot ringan untuk rendering fotorealistis dari teks murni dengan efisiensi biaya tertinggi. - [Recraft Remove Background](/id/developer/model/recraft-remove-background): Alat isolasi subjek otomatis Recraft untuk memisahkan objek utama ke atas latar belakang transparan (alpha). - [Recraft Crisp Upscale](/id/developer/model/recraft-crisp-upscale): Alat pembesaran resolusi Recraft untuk merekonstruksi ketajaman detail dan tekstur tanpa mengubah isi gambar. - **Video** - [Kling 3](/id/developer/model/kling-3): Model video Kuaishou berdurasi 3 sampai 15 detik dengan audio bawaan, hingga lima adegan, bingkai awal, dan resolusi hingga 4K. - [Wan 3 Video](/id/developer/model/wan-3-video): Model video Alibaba berdurasi 2 sampai 30 detik dalam tier Standard dan Prime, dilengkapi audio bawaan serta acuan gambar, video, atau suara. - [Seedance 1](/id/developer/model/seedance-1): Model video ByteDance untuk animasi gerak 5 hingga 10 detik dari teks atau gambar acuan melalui tier Lite, Fast, dan Pro. - [Seedance 1.5 Pro](/id/developer/model/seedance-1-5-pro): Model video ByteDance generasi terbaru dengan dukungan durasi hingga 12 detik, transisi bingkai awal-akhir, dan sinkronisasi audio bawaan. - [Seedance 2](/id/developer/model/seedance-2): Model video ByteDance generasi kedua dengan tiga tier kecepatan, durasi hingga 15 detik, dan acuan multimodal berupa gambar, video, maupun audio. - [Seedance 2.5](/id/developer/model/seedance-2-5): Model video ByteDance paling mutakhir dengan durasi hingga 30 detik, prompt panjang, dan acuan multimodal hingga 30 gambar. - [Kling 3 Turbo](/id/developer/model/kling-3-turbo): Model video Kuaishou versi cepat dan hemat kredit untuk durasi 3 sampai 15 detik, resolusi hingga 1080p dari teks atau satu gambar acuan. - [Kling 3 Motion Control](/id/developer/model/kling-3-motion-control): Model video Kuaishou untuk transfer gerak: memindahkan aksi dari video acuan ke karakter pada gambar diam. - [Kling 2.6](/id/developer/model/kling-2-6): Model video Kuaishou berdurasi 5 atau 10 detik dari teks maupun gambar acuan, dengan opsi trek audio mandiri. - [Grok Imagine Video 1.5](/id/developer/model/grok-imagine-video-1-5): Model video xAI berdurasi 1 sampai 15 detik dari teks maupun hingga tujuh gambar acuan dalam satu render. - [Grok Imagine Video](/id/developer/model/grok-imagine-video): Model video xAI berdurasi 6 sampai 30 detik dari teks atau hingga tujuh gambar acuan, dengan resolusi hingga 1080p. - [Wan 2.7 Video](/id/developer/model/wan-2-7-video): Model video Alibaba dengan empat alur kerja: teks-ke-video, animasi bingkai, penyuntingan video yang ada, dan komposisi dari bahan acuan. - [Wan 2.6 Video](/id/developer/model/wan-2-6-video): Model video Alibaba berdurasi 5 sampai 15 detik dari teks, satu gambar, atau subjek di video acuan, dengan tier Standard bersuara dan tier Flash yang lebih hemat. - [Happy Horse 1](/id/developer/model/happy-horse-1): Model video Alibaba dengan empat moda: teks ke video, animasi bingkai awal, multi-referensi, dan pengeditan klip. - [Happy Horse 1.1](/id/developer/model/happy-horse-1-1): Model video Alibaba generasi 1.1 dengan tarif per detik lebih hemat, sembilan rasio aspek, dan rendering berarah. - [MiniMax H3](/id/developer/model/minimax-h3): Model video MiniMax beresolusi hingga 2K (durasi 4 sampai 15 detik) dari teks, bingkai awal-akhir, atau referensi multi-modal. - [Veo 3.1](/id/developer/model/veo-3-1): Model video sinematik Google beresolusi hingga 4K dengan audio bawaan, dalam tiga tier: Lite paling hemat, Fast seimbang, Quality paling tajam. - [Vidu Q4](/id/developer/model/vidu-q4): Model video Vidu dari ShengShu berdurasi 3 sampai 16 detik hingga 4K, dari satu gambar awal atau sampai 15 gambar acuan, dengan dialog dan efek suara bawaan. - **Suara** - [Gemini 3.8 Flash TTS](/id/developer/model/gemini-tts): Model suara Google yang membacakan teks dengan satu dari 70 suara, atau dialog dua pembicara, lengkap dengan arahan nada, emosi, dan tempo. - **Lainnya** - [Bantuan](/id/bantuan): Cara menghubungi tim XPlor3 dan jawaban untuk pertanyaan yang paling sering muncul. # Documentation - [XPlor3 Documentation](/en): How to use the XPlor3 studio, from your first generation to connecting your own app over MCP and the REST API. - **Guides** - Getting started - [Create an account](/en/mulai): Sign up in the studio, verify your email, then get to know the parts of the studio you will use most. - [Your first generation](/en/mulai/generate-pertama): From picking a model to a saved result, including how to read the cost before any credits are taken. - [Credits and payment](/en/mulai/kredit): One balance for every model, how credits are taken and returned, and how to buy them with QRIS. - Studio - [The generate console](/en/studio/konsol): Where every model runs, and the small features in it that save time and credits. - [Multi Generate](/en/studio/multi-generate): One prompt on up to five models at once, so you can compare the results and their costs side by side. - [Brand Kit](/en/studio/brand-kit): Save a brand's identity once, then add it to the prompt and the console with one button. - [History, Library and Projects](/en/studio/riwayat-proyek): Where your results and files are kept, how to organise them, and how long everything is stored. - [Sharing and ownership](/en/studio/berbagi): Share links for a single result, the community gallery, and who owns the images and video you make. - Models - [Model catalogue](/en/model): Every image, video and speech model on XPlor3, grouped by kind, with the slug to use in the API. - [Choosing a model](/en/model/memilih-model): How to settle on the right model from the job, the inputs you have, and the budget. - [Writing prompts](/en/model/menulis-prompt): A prompt structure image and video models understand easily, with examples you can try straight away. - Workflow - [Getting to know Workflow](/en/workflow): Chain several models on one canvas, so what one step makes goes straight into the next. - [Node types](/en/workflow/node): The seven kinds of node on the Workflow canvas, and when to use each. - [Many photos at once](/en/workflow/batch): Run the same workflow for up to 50 photos in one batch, for example a whole product catalogue. - [Templates and sharing workflows](/en/workflow/template): Start from a workflow template on Home or the built-in workflows in your account, then save and move them as JSON files. - Store - [Store](/en/toko): PDF guides and asset packs from the XPlor3 team, paid for with credits and downloadable again at any time. - **Developer** - [Developer overview](/en/developer): Two ways to use XPlor3 from outside the studio, MCP for AI agents and the REST API for your app, with one API key. - [Credentials](/en/developer/kredensial): Creating, storing and revoking the API keys used for MCP and the REST API. - [MCP server](/en/developer/mcp): Connect Claude Desktop, Cursor or a local agent to XPlor3, then ask the agent for images and video from the conversation. - REST API - [About the REST API](/en/developer/rest-api): Base URL, authentication, request and response format, and how to test your first key. - [Generation flow](/en/developer/rest-api/generate): Five steps from choosing a model to downloading the result files, with curl, JavaScript and Python examples. - [Webhooks](/en/developer/rest-api/webhook): XPlor3 tells your server when a job succeeds, fails or is cancelled, so you don't have to keep asking. - [Endpoint reference](/en/developer/rest-api/referensi): The REST endpoints available to an API key, with each one's request and response fields. - [Limits and errors](/en/developer/rest-api/error): The error format, the codes you will meet most, per-minute request limits, and how to handle them. - Model reference - [Model reference](/en/developer/model): The modelSlug, input fields, accepted values and rules of every XPlor3 model, for the REST API and MCP. - **Image** - [GPT Image 2.5](/en/developer/model/gpt-image-2-5): OpenAI visual model with two rendering styles, an optional transparent background, and up to 4K output. - [Nano Banana](/en/developer/model/nano-banana): Google visual model for fast image generation and reference-based editing. - [Nano Banana 2](/en/developer/model/nano-banana-2): Second-generation Google visual model with a Lite tier for fast generations and a Standard tier up to 4K resolution. - [Nano Banana 2.1](/en/developer/model/nano-banana-2-1): Google's successor to Nano Banana 2 for making and editing images up to 4K, cheaper at every resolution. - [Nano Banana Pro](/en/developer/model/nano-banana-pro): Google visual model for complex prompts, photographic detail, and character consistency across generations. - [Seedream 4](/en/developer/model/seedream-4): ByteDance visual model with versatile aspect ratios and rendering support up to 4K resolution. - [Seedream 4.5](/en/developer/model/seedream-4-5): ByteDance 4.5 visual model with refined texture detail and multi-tiered quality presets. - [Seedream 5](/en/developer/model/seedream-5): ByteDance visual model with a fast Lite tier, a Pro tier for precise composition, a low-cost Flash tier, and Layer tiers that split an image into separate layers. - [GPT Image 1.5](/en/developer/model/gpt-image-1-5): OpenAI visual model with guided text prompt adherence and dual rendering quality settings. - [GPT Image 2](/en/developer/model/gpt-image-2): Second-generation OpenAI visual model with in-image typography, wide aspect ratios, and up to 4K output. - [Grok Imagine Image 2](/en/developer/model/grok-imagine-image-2): Second-generation xAI visual model for text prompts and multi-asset editing with up to five reference images. - [Grok Imagine Image](/en/developer/model/grok-imagine-image): Lightweight xAI visual model for rapid text-to-image rendering with optional single image reference. - [Wan 2.7 Image](/en/developer/model/wan-2-7-image): Alibaba visual model with Standard and Pro tiers for output up to 4K, accepting up to nine reference images per prompt. - [Qwen 3](/en/developer/model/qwen-3): Alibaba image model across Standard and Pro tiers up to 2K, supporting composition workflows from up to 3 reference images. - [Qwen 2](/en/developer/model/qwen-2): Fast Alibaba image model for drafting from compact prompts and instruction-based single-image editing. - [Qwen 2.1](/en/developer/model/qwen-2-1): Alibaba image model up to 2K resolution featuring optional alpha transparency and blending across up to 10 reference images. - [Z-Image](/en/developer/model/z-image): Lightweight Alibaba image model producing photorealistic output from text prompts at maximum cost efficiency. - [Recraft Remove Background](/en/developer/model/recraft-remove-background): Automated Recraft cutout tool that isolates main subjects onto a clean transparent alpha layer. - [Recraft Crisp Upscale](/en/developer/model/recraft-crisp-upscale): Recraft upscaler that enhances image resolution, reconstructing crisp edge detail and fine texture fidelity. - **Video** - [Kling 3](/en/developer/model/kling-3): Kuaishou video model for 3 to 15-second clips with native audio, up to five scenes, a starting frame, and output up to 4K. - [Wan 3 Video](/en/developer/model/wan-3-video): Alibaba video model for 2 to 30-second clips across Standard and Prime tiers, featuring built-in audio and multi-modal media references. - [Seedance 1](/en/developer/model/seedance-1): ByteDance video model producing 5 to 10-second motion animations from text or image prompts across Lite, Fast, and Pro tiers. - [Seedance 1.5 Pro](/en/developer/model/seedance-1-5-pro): ByteDance video model supporting clips up to 12 seconds with start-and-end frame transitions and audio. - [Seedance 2](/en/developer/model/seedance-2): Second-generation ByteDance video model with three speed tiers, clips up to 15 seconds, and references from images, video, or audio. - [Seedance 2.5](/en/developer/model/seedance-2-5): ByteDance video model supporting clips up to 30 seconds, long prompts, and image references from up to 30 files. - [Kling 3 Turbo](/en/developer/model/kling-3-turbo): High-speed, cost-efficient Kuaishou video model for 3 to 15-second clips up to 1080p from text or a single reference image. - [Kling 3 Motion Control](/en/developer/model/kling-3-motion-control): Kuaishou motion transfer model that maps movement from a reference video onto a character in a still image. - [Kling 2.6](/en/developer/model/kling-2-6): Kuaishou video model for 5 or 10-second clips from text or image prompts, with optional native audio. - [Grok Imagine Video 1.5](/en/developer/model/grok-imagine-video-1-5): xAI video model for 1 to 15-second clips from text prompts or up to seven reference images per run. - [Grok Imagine Video](/en/developer/model/grok-imagine-video): xAI video model for 6 to 30-second clips from text or up to seven reference images, with output up to 1080p. - [Wan 2.7 Video](/en/developer/model/wan-2-7-video): Alibaba video model supporting four workflows: text-to-video, frame animation, existing video editing, and reference composition. - [Wan 2.6 Video](/en/developer/model/wan-2-6-video): Alibaba video model for 5 to 15-second clips from text, a single image, or the subject of reference videos, with a Standard tier that always has sound and a cheaper Flash tier. - [Happy Horse 1](/en/developer/model/happy-horse-1): Alibaba video model supporting four workflows: text-to-video, first frame animation, multi-reference, and video editing. - [Happy Horse 1.1](/en/developer/model/happy-horse-1-1): Alibaba 1.1 video model featuring reduced per-second rates, nine aspect ratios, and directed motion workflows. - [MiniMax H3](/en/developer/model/minimax-h3): MiniMax video model rendering up to 2K resolution (4 to 15 seconds) from text, keyframes, or multi-modal references. - [Veo 3.1](/en/developer/model/veo-3-1): Cinematic Google video model up to 4K with built-in audio, in three tiers: Lite for the lowest price, Fast for balance, Quality for the sharpest result. - [Vidu Q4](/en/developer/model/vidu-q4): ShengShu's Vidu video model for 3 to 16-second clips up to 4K, from one first frame or up to 15 reference images, with built-in dialogue and sound effects. - **Speech** - [Gemini 3.8 Flash TTS](/en/developer/model/gemini-tts): Google's speech model that turns text into spoken audio, with 70 voices for a single narrator or a two-speaker dialogue, on Flash and Flash Lite tiers. - **More** - [Help](/en/bantuan): How to reach the XPlor3 team, and answers to the questions that come up most.