{
  "aboutHtml": "<p>all-MiniLM-L12-v2 ialah pengekod Sentence Transformers untuk ayat dan perenggan pendek. Ia menghasilkan satu vektor padat 384 dimensi bagi setiap teks untuk carian semantik, pemerolehan semula maklumat, pengelompokan dan keserupaan ayat. Model menggunakan seni bina asas MiniLM-L12-H384-uncased dan ditala halus dengan pembelajaran kontrastif pada koleksi satu bilion pasangan ayat.</p><h4>Kodkan unit yang mahu diperoleh semula</h4><p>Gunakan ayat atau perenggan pendek yang menyatakan satu idea berguna. Untuk koleksi penerangan produk, kekalkan ciri dan syarat yang membezakan item: “The adapter connects a wired headset to a USB-C port” lebih bermaklumat daripada “Audio accessory.” Simpan pengecam rekod dan penerangan asal di sisi vektornya.</p><p>Pertanyaan carian kemudian boleh dibandingkan dengan penerangan yang dikodkan. Periksa calon yang dikembalikan untuk keperluan tepat seperti jenis penyambung atau keserasian peranti sebelum membentangkan pilihan akhir. Vektor mewakili makna teks; aplikasi carian di sekelilingnya mendapatkan rekod yang sepadan.</p><h4>Mean pooling dan vektor ternormal</h4><p>Contoh pengekodan yang diterbitkan mempuratakan perwakilan token menggunakan topeng perhatian supaya kedudukan padding tidak menyumbang kepada purata. Kemudian ia menggunakan penormalan L2. Langkah ini sebahagian daripada kaedah rujukan mendapatkan vektor ayat, bukannya arahan mengambil token sembarangan daripada transformer asas.</p><p>Pastikan konfigurasi model, pooling dan penormalan konsisten antara teks berindeks dan pertanyaan baharu. Perwakilan 384 komponen yang terhasil boleh dibandingkan menggunakan keserupaan kosinus. Simpan rekod konfigurasi itu bersama koleksi; pengekod 384 dimensi lain tidak menjadi serasi hanya kerana vektornya sama panjang.</p><h4>Panjang input lalai dan skop latihan</h4><p>Pembuat menetapkan pemotongan lalai melebihi 256 unit word piece. Ini had tokenizer, bukan bilangan perkataan biasa atau aksara. Untuk rekod lebih panjang, pilih bahagian pendek yang koheren dan simpan tajuk atau perincian pengenal yang diperlukan untuk mentafsir setiap satunya.</p><p>Prosedur latihan model menggunakan jujukan sehingga 128 token. Tetapan latihan itu berasingan daripada tetapan lalai 256 unit word piece yang diterbitkan untuk pengekodan. Petikan yang muat dalam tetapan lalai masih boleh berbeza dengan ketara daripada bahan ayat pendek semasa latihan, maka nilai penerangan panjang atau khusus menggunakan contoh yang mewakili tugas.</p><h4>Aliran kerja keserupaan dan pengelompokan</h4><p>Untuk set mesej sokongan, embedding boleh membekalkan input berangka kepada peringkat pengelompokan. Semak beberapa mesej daripada setiap kumpulan cadangan dan mesej berhampiran sempadannya sebelum memberikan label yang mudah dibaca manusia. Untuk semakan kandungan pendua, dapatkan rekod serupa dan bandingkan ungkapan sebenar; dua petikan mungkin membincangkan subjek sama sambil memberikan arahan berbeza.</p><p>Edisi L12-v2 tepat ini ialah profil embedding ayat bahasa Inggeris. Ia berbeza daripada all-MiniLM-L6-v2 dan checkpoint paraphrase-MiniLM. Nama keluarga yang dikongsi tidak memindahkan konfigurasi jujukan atau kaedah poolingnya. Gunakan vektor padat kompaknya bersama rekod sumber dan penilaian khusus tugas, bukannya menganggap nilai keserupaan sebagai jawapan yang disahkan atau keputusan editorial akhir.</p>",
  "aboutText": "all-MiniLM-L12-v2 ialah pengekod Sentence Transformers untuk ayat dan perenggan pendek. Ia menghasilkan satu vektor padat 384 dimensi bagi setiap teks untuk carian semantik, pemerolehan semula maklumat, pengelompokan dan keserupaan ayat. Model menggunakan seni bina asas MiniLM-L12-H384-uncased dan ditala halus dengan pembelajaran kontrastif pada koleksi satu bilion pasangan ayat.\n\n### Kodkan unit yang mahu diperoleh semula\n\nGunakan ayat atau perenggan pendek yang menyatakan satu idea berguna. Untuk koleksi penerangan produk, kekalkan ciri dan syarat yang membezakan item: “The adapter connects a wired headset to a USB-C port” lebih bermaklumat daripada “Audio accessory.” Simpan pengecam rekod dan penerangan asal di sisi vektornya.\n\nPertanyaan carian kemudian boleh dibandingkan dengan penerangan yang dikodkan. Periksa calon yang dikembalikan untuk keperluan tepat seperti jenis penyambung atau keserasian peranti sebelum membentangkan pilihan akhir. Vektor mewakili makna teks; aplikasi carian di sekelilingnya mendapatkan rekod yang sepadan.\n\n### Mean pooling dan vektor ternormal\n\nContoh pengekodan yang diterbitkan mempuratakan perwakilan token menggunakan topeng perhatian supaya kedudukan padding tidak menyumbang kepada purata. Kemudian ia menggunakan penormalan L2. Langkah ini sebahagian daripada kaedah rujukan mendapatkan vektor ayat, bukannya arahan mengambil token sembarangan daripada transformer asas.\n\nPastikan konfigurasi model, pooling dan penormalan konsisten antara teks berindeks dan pertanyaan baharu. Perwakilan 384 komponen yang terhasil boleh dibandingkan menggunakan keserupaan kosinus. Simpan rekod konfigurasi itu bersama koleksi; pengekod 384 dimensi lain tidak menjadi serasi hanya kerana vektornya sama panjang.\n\n### Panjang input lalai dan skop latihan\n\nPembuat menetapkan pemotongan lalai melebihi 256 unit word piece. Ini had tokenizer, bukan bilangan perkataan biasa atau aksara. Untuk rekod lebih panjang, pilih bahagian pendek yang koheren dan simpan tajuk atau perincian pengenal yang diperlukan untuk mentafsir setiap satunya.\n\nProsedur latihan model menggunakan jujukan sehingga 128 token. Tetapan latihan itu berasingan daripada tetapan lalai 256 unit word piece yang diterbitkan untuk pengekodan. Petikan yang muat dalam tetapan lalai masih boleh berbeza dengan ketara daripada bahan ayat pendek semasa latihan, maka nilai penerangan panjang atau khusus menggunakan contoh yang mewakili tugas.\n\n### Aliran kerja keserupaan dan pengelompokan\n\nUntuk set mesej sokongan, embedding boleh membekalkan input berangka kepada peringkat pengelompokan. Semak beberapa mesej daripada setiap kumpulan cadangan dan mesej berhampiran sempadannya sebelum memberikan label yang mudah dibaca manusia. Untuk semakan kandungan pendua, dapatkan rekod serupa dan bandingkan ungkapan sebenar; dua petikan mungkin membincangkan subjek sama sambil memberikan arahan berbeza.\n\nEdisi L12-v2 tepat ini ialah profil embedding ayat bahasa Inggeris. Ia berbeza daripada all-MiniLM-L6-v2 dan checkpoint paraphrase-MiniLM. Nama keluarga yang dikongsi tidak memindahkan konfigurasi jujukan atau kaedah poolingnya. Gunakan vektor padat kompaknya bersama rekod sumber dan penilaian khusus tugas, bukannya menganggap nilai keserupaan sebagai jawapan yang disahkan atau keputusan editorial akhir.",
  "editorialOverlay": {
    "copy_fields": null,
    "copy_sha256": null,
    "copy_source": null,
    "html_sha256": "6b49539bcdfe8b1e152c89d2392e562db33ca52bdc89f9a780c4b5221bc01367",
    "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06",
    "raw_model_unchanged": true,
    "schema": "ailoot-native-model-editorial-v1"
  },
  "locale": "ms",
  "methods": [
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">•</span><h2 id=\"sheet-title\">Sentence Transformers: all-MiniLM-L12-v2</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Tutup\">×</button></div><div class=\"idline\"><span>Sentence Transformers /</span><code>sentence-transformers/all-minilm-l12-v2</code><button type=\"button\" id=\"copy-id\">Salin ID</button></div><nav class=\"card-jump-nav\" aria-label=\"Bahagian kad model\"><button type=\"button\" data-card-jump=\"overview\">Pengenalan</button><button type=\"button\" data-card-jump=\"methods\">Input &amp; kaedah</button><button type=\"button\" data-card-jump=\"pricing\">Pelan harga</button><button type=\"button\" data-card-jump=\"examples\">Contoh</button><button type=\"button\" data-card-jump=\"results\">Hasil</button><button type=\"button\" data-card-jump=\"aliases\">Alias</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"Kaedah API\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Ultra|embeddings|/v1/embeddings|sentence-transformers%2Fall-minilm-l12-v2\">Pembenaman</button></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">Pengenalan</h3><p class=\"mdesc-full\">Sentence Transformers all-MiniLM-L12-v2 mengekod ayat dan perenggan pendek kepada vektor 384 dimensi untuk carian, keserupaan dan pengelompokan. Kaedah rujukannya menggunakan mean pooling dan penormalan, dengan pemotongan lalai pada 256 unit word piece.</p><dl class=\"card-io\" data-card-io><div><dt>Input yang diterima</dt><dd>Teks · token_ids</dd></div><div><dt>Hasil</dt><dd>embedding</dd></div></dl><details class=\"card-about\"><summary>Tentang model</summary><p class=\"note-s\" data-model-method-boundary>Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.</p><div class=\"mabout\" id=\"m-about\"><p>all-MiniLM-L12-v2 ialah pengekod Sentence Transformers untuk ayat dan perenggan pendek. Ia menghasilkan satu vektor padat 384 dimensi bagi setiap teks untuk carian semantik, pemerolehan semula maklumat, pengelompokan dan keserupaan ayat. Model menggunakan seni bina asas MiniLM-L12-H384-uncased dan ditala halus dengan pembelajaran kontrastif pada koleksi satu bilion pasangan ayat.</p><h4>Kodkan unit yang mahu diperoleh semula</h4><p>Gunakan ayat atau perenggan pendek yang menyatakan satu idea berguna. Untuk koleksi penerangan produk, kekalkan ciri dan syarat yang membezakan item: “The adapter connects a wired headset to a USB-C port” lebih bermaklumat daripada “Audio accessory.” Simpan pengecam rekod dan penerangan asal di sisi vektornya.</p><p>Pertanyaan carian kemudian boleh dibandingkan dengan penerangan yang dikodkan. Periksa calon yang dikembalikan untuk keperluan tepat seperti jenis penyambung atau keserasian peranti sebelum membentangkan pilihan akhir. Vektor mewakili makna teks; aplikasi carian di sekelilingnya mendapatkan rekod yang sepadan.</p><h4>Mean pooling dan vektor ternormal</h4><p>Contoh pengekodan yang diterbitkan mempuratakan perwakilan token menggunakan topeng perhatian supaya kedudukan padding tidak menyumbang kepada purata. Kemudian ia menggunakan penormalan L2. Langkah ini sebahagian daripada kaedah rujukan mendapatkan vektor ayat, bukannya arahan mengambil token sembarangan daripada transformer asas.</p><p>Pastikan konfigurasi model, pooling dan penormalan konsisten antara teks berindeks dan pertanyaan baharu. Perwakilan 384 komponen yang terhasil boleh dibandingkan menggunakan keserupaan kosinus. Simpan rekod konfigurasi itu bersama koleksi; pengekod 384 dimensi lain tidak menjadi serasi hanya kerana vektornya sama panjang.</p><h4>Panjang input lalai dan skop latihan</h4><p>Pembuat menetapkan pemotongan lalai melebihi 256 unit word piece. Ini had tokenizer, bukan bilangan perkataan biasa atau aksara. Untuk rekod lebih panjang, pilih bahagian pendek yang koheren dan simpan tajuk atau perincian pengenal yang diperlukan untuk mentafsir setiap satunya.</p><p>Prosedur latihan model menggunakan jujukan sehingga 128 token. Tetapan latihan itu berasingan daripada tetapan lalai 256 unit word piece yang diterbitkan untuk pengekodan. Petikan yang muat dalam tetapan lalai masih boleh berbeza dengan ketara daripada bahan ayat pendek semasa latihan, maka nilai penerangan panjang atau khusus menggunakan contoh yang mewakili tugas.</p><h4>Aliran kerja keserupaan dan pengelompokan</h4><p>Untuk set mesej sokongan, embedding boleh membekalkan input berangka kepada peringkat pengelompokan. Semak beberapa mesej daripada setiap kumpulan cadangan dan mesej berhampiran sempadannya sebelum memberikan label yang mudah dibaca manusia. Untuk semakan kandungan pendua, dapatkan rekod serupa dan bandingkan ungkapan sebenar; dua petikan mungkin membincangkan subjek sama sambil memberikan arahan berbeza.</p><p>Edisi L12-v2 tepat ini ialah profil embedding ayat bahasa Inggeris. Ia berbeza daripada all-MiniLM-L6-v2 dan checkpoint paraphrase-MiniLM. Nama keluarga yang dikongsi tidak memindahkan konfigurasi jujukan atau kaedah poolingnya. Gunakan vektor padat kompaknya bersama rekod sumber dan penilaian khusus tugas, bukannya menganggap nilai keserupaan sebagai jawapan yang disahkan atau keputusan editorial akhir.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Tersedia di Ailoot · input &amp; kaedah</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · Pembenaman</b> <code>POST /v1/embeddings</code></summary><dl class=\"method-capabilities\"><div><dt>Input</dt><dd><code>text</code>, <code>token_ids</code></dd></div><div><dt>Output</dt><dd><code>embedding</code></dd></div><div><dt>Format output</dt><dd>json</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>Medan</th><th>Jenis</th><th>Keperluan</th><th>Nilai &amp; had</th><th>Lalai</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span><code>string</code></td><td data-cell-label=\"Keperluan\"><span class=\"card-cell-label\">Keperluan</span>Diperlukan</td><td data-cell-label=\"Nilai &amp; had\"><span class=\"card-cell-label\">Nilai &amp; had</span><div>sentence-transformers/all-minilm-l12-v2</div></td><td data-cell-label=\"Lalai\" data-default=\"unspecified\"><span class=\"card-cell-label\">Lalai</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">input</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span><code>string|string[]|integer[]|integer[][]</code></td><td data-cell-label=\"Keperluan\"><span class=\"card-cell-label\">Keperluan</span>Diperlukan</td><td data-cell-label=\"Nilai &amp; had\"><span class=\"card-cell-label\">Nilai &amp; had</span><div>Item minimum: 1</div><div>Syarat: Kelompok homogen yang tidak kosong. ID token ialah integer bukan negatif.</div><div>Bajet input: Maksimum: 512 · Unit teks: bait UTF8 · Unit token: elemen tatasusunan token</div></td><td data-cell-label=\"Lalai\" data-default=\"unspecified\"><span class=\"card-cell-label\">Lalai</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">encoding_format</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span><code>string</code></td><td data-cell-label=\"Keperluan\"><span class=\"card-cell-label\">Keperluan</span>Pilihan</td><td data-cell-label=\"Nilai &amp; had\"><span class=\"card-cell-label\">Nilai &amp; had</span><div>float</div></td><td data-cell-label=\"Lalai\" data-default=\"known\"><span class=\"card-cell-label\">Lalai</span>float</td></tr><tr data-parameter-availability=\"unsupported\"><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">dimensions</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span><code>integer</code></td><td data-cell-label=\"Keperluan\"><span class=\"card-cell-label\">Keperluan</span>Tidak disokong</td><td data-cell-label=\"Nilai &amp; had\"><span class=\"card-cell-label\">Nilai &amp; had</span><div>Minimum: 1</div></td><td data-cell-label=\"Lalai\" data-default=\"unspecified\"><span class=\"card-cell-label\">Lalai</span>—</td></tr><tr data-parameter-availability=\"pass_through_metadata\"><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">user</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span><code>json_value</code></td><td data-cell-label=\"Keperluan\"><span class=\"card-cell-label\">Keperluan</span>Pilihan</td><td data-cell-label=\"Nilai &amp; had\"><span class=\"card-cell-label\">Nilai &amp; had</span><div>Syarat: Sumber membenarkan medan metadata JSON ini; semantik tepat di pihak huluan bergantung pada model.</div></td><td data-cell-label=\"Lalai\" data-default=\"unspecified\"><span class=\"card-cell-label\">Lalai</span>—</td></tr><tr data-parameter-availability=\"pass_through_metadata\"><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">session_id</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span><code>json_value</code></td><td data-cell-label=\"Keperluan\"><span class=\"card-cell-label\">Keperluan</span>Pilihan</td><td data-cell-label=\"Nilai &amp; had\"><span class=\"card-cell-label\">Nilai &amp; had</span><div>Syarat: Sumber membenarkan medan metadata JSON ini; semantik tepat di pihak huluan bergantung pada model.</div></td><td data-cell-label=\"Lalai\" data-default=\"unspecified\"><span class=\"card-cell-label\">Lalai</span>—</td></tr><tr data-parameter-availability=\"pass_through_metadata\"><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">trace</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span><code>json_value</code></td><td data-cell-label=\"Keperluan\"><span class=\"card-cell-label\">Keperluan</span>Pilihan</td><td data-cell-label=\"Nilai &amp; had\"><span class=\"card-cell-label\">Nilai &amp; had</span><div>Syarat: Sumber membenarkan medan metadata JSON ini; semantik tepat di pihak huluan bergantung pada model.</div></td><td data-cell-label=\"Lalai\" data-default=\"unspecified\"><span class=\"card-cell-label\">Lalai</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">provider</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span><code>object</code></td><td data-cell-label=\"Keperluan\"><span class=\"card-cell-label\">Keperluan</span>Pilihan</td><td data-cell-label=\"Nilai &amp; had\"><span class=\"card-cell-label\">Nilai &amp; had</span><div>Syarat: provider.options ditolak</div></td><td data-cell-label=\"Lalai\" data-default=\"unspecified\"><span class=\"card-cell-label\">Lalai</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>Gabungan bahan input</summary><p class=\"note-s\"><b>text_to_embedding</b></p></details><details class=\"note-s\" data-method-contract><summary>Parameter kaedah dan kitar hayat</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>Parameter</th><th>Kontrak</th></tr></thead><tbody><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>content_type</code></th><td data-cell-label=\"Kontrak\"><span class=\"card-cell-label\">Kontrak</span>application/json</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>required</code></th><td data-cell-label=\"Kontrak\"><span class=\"card-cell-label\">Kontrak</span>model, input</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>input_shapes</code></th><td data-cell-label=\"Kontrak\"><span class=\"card-cell-label\">Kontrak</span>string, string[], nonnegative_integer_token_array, nonnegative_integer_token_array[]</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>encoding_format</code></th><td data-cell-label=\"Kontrak\"><span class=\"card-cell-label\">Kontrak</span>float</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>dimensions_override</code></th><td data-cell-label=\"Kontrak\"><span class=\"card-cell-label\">Kontrak</span>false</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>max_input_budget_units</code></th><td data-cell-label=\"Kontrak\"><span class=\"card-cell-label\">Kontrak</span>512</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>multimodal_objects</code></th><td data-cell-label=\"Kontrak\"><span class=\"card-cell-label\">Kontrak</span>false</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>material_types</code></th><td data-cell-label=\"Kontrak\"><span class=\"card-cell-label\">Kontrak</span>text, token_ids</td></tr></tbody></table></div><p>Kitar hayat: <code>synchronous_json</code></p><p class=\"note-s\">Simpan setiap indeks dan dimensi vektor.</p><p class=\"note-s\">Nama model multimodal tidak bermakna objek imej dibenarkan pada laluan khusus ini.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">Pelan harga</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.</p><dl data-price-conditions><dt>Mod pantas</dt><dd>Tidak dinyatakan <span class=\"note-s\">Apabila mod pantas dipilih</span></dd><dt>Mod flex</dt><dd>Tidak dinyatakan <span class=\"note-s\">Apabila mod flex dipilih</span></dd><dt>Usaha penaakulan maksimum</dt><dd>Tidak dinyatakan <span class=\"note-s\">Apabila usaha penaakulan maksimum menggunakan pelarasan default</span></dd></dl></div><div data-declared-tariff-pricing><h4>Kadar Ailoot</h4><h4>Harga mengikut konfigurasi</h4><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>Konfigurasi</th><th>Jadual kadar</th><th>Caj</th></tr></thead><tbody><tr><th data-cell-label=\"Konfigurasi\" scope=\"row\"><span class=\"card-cell-label\">Konfigurasi</span>Kadar asas token</th><td data-cell-label=\"Jadual kadar\"><span class=\"card-cell-label\">Jadual kadar</span>Kadar asas</td><td data-cell-label=\"Caj\"><span class=\"card-cell-label\">Caj</span><div><span>Input · Token input</span> <b>$0.00001</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Output · Token output</span> <b>$0</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Input · Bacaan cache</span> <b>—</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Input · Penulisan cache</span> <b>—</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Input · Penulisan cache, 1 jam</span> <b>—</b> <span class=\"price-unit\">/ 1K token</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. <a href=\"/docs/ms/billing/reserve/\">Cara rizab dan penyelesaian caj berfungsi →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">Contoh permintaan</h3><h4>Ailoot Ultra · Pembenaman</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Pilihan kod\"><button class=\"cg-tab\" id=\"model-code-2596-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2596-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl</button><button class=\"cg-tab\" id=\"model-code-2596-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2596-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Salin kod\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-2596-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-2596-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;sentence-transformers/all-minilm-l12-v2&quot;, &quot;input&quot;: [&quot;First document&quot;, &quot;Second document&quot;]}&#39;)\n\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nr=json.loads(Path(&quot;result.json&quot;).read_text())\nfor x in r.get(&quot;data&quot;,[]): print(json.dumps({&quot;index&quot;:x.get(&quot;index&quot;),&quot;embedding&quot;:x.get(&quot;embedding&quot;)}))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-2596-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-2596-tab-1\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nresult=client.embeddings.create(model=&#39;sentence-transformers/all-minilm-l12-v2&#39;,input=[&quot;First document&quot;,&quot;Second document&quot;])\nprint(result)\nfor item in result.data:print(item.index,item.embedding)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">Terima dan simpan hasil</h3><h4>Ailoot Ultra · Pembenaman</h4><p class=\"note-s\">json</p><div class=\"card-result-process\" data-all-results><h5>Simpan semua hasil yang selesai</h5><p class=\"note-s\">Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.</p><p class=\"note-s\">Simpan setiap vektor bersama indeksnya. Bilangan vektor mesti sama dengan bilangan input; dimensi mesti konsisten.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>Jika respons asal perlu disemak</h5><p class=\"note-s\">Tiada titik akhir tugas pembenaman diperkenalkan.</p></div><details class=\"card-about\" data-output-fields><summary>Medan respons</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>Medan</th><th>Jenis</th></tr></thead><tbody><tr><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">object</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span>string</td></tr><tr><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span>string</td></tr><tr><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">data[].index</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span>integer</td></tr><tr><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">data[].embedding</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span>finite float[]</td></tr><tr><th data-cell-label=\"Medan\" scope=\"row\"><span class=\"card-cell-label\">Medan</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"Jenis\" data-field-type><span class=\"card-cell-label\">Jenis</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>Ralat dan langkah seterusnya</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>Respons</th><th>Syarat</th><th>Langkah seterusnya</th></tr></thead><tbody><tr><th data-cell-label=\"Respons\" scope=\"row\"><span class=\"card-cell-label\">Respons</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"Syarat\"><span class=\"card-cell-label\">Syarat</span>Medan wajib, perwakilan bahan atau nilai parameter tidak sah</td><td data-cell-label=\"Langkah seterusnya\"><span class=\"card-cell-label\">Langkah seterusnya</span>Betulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">Alias</h3><h4>Alias model</h4><p class=\"note-s\"><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=sentence-transformers%2Fall-minilm-l12-v2&amp;route=Ultra&amp;caller=sentence-transformers%2Fall-minilm-l12-v2&amp;fmt=embeddings\"><code>sentence-transformers/all-minilm-l12-v2</code></a></span></p><h4>Alias laluan kaedah</h4><p class=\"note-s\">Gunakan laluan kaedah yang dipaparkan di atas.</p><h4>ID pemanggil berkaitan</h4><p class=\"note-s\"><a href=\"#m=sentence-transformers%2Fall-minilm-l12-v2&amp;route=Ultra&amp;caller=sentence-transformers%2Fall-minilm-l12-v2&amp;fmt=embeddings\"><code>sentence-transformers/all-minilm-l12-v2</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "sentence-transformers/all-minilm-l12-v2",
        "fmt": "embeddings",
        "http": "POST",
        "path": "/v1/embeddings",
        "request_model_id": "sentence-transformers/all-minilm-l12-v2",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|embeddings|/v1/embeddings|sentence-transformers%2Fall-minilm-l12-v2",
      "ordinal": 0,
      "rawMethod": {
        "available": null,
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.",
            "errors": [
              {
                "code": null,
                "condition": "Medan wajib, perwakilan bahan atau nilai parameter tidak sah",
                "http_status": 400,
                "recovery": "Betulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/embeddings"
              },
              "job_read": null,
              "mode": "synchronous_json",
              "unknown": "Tiada titik akhir tugas pembenaman diperkenalkan."
            },
            "material_combinations": [
              {
                "alternatives": [
                  "string",
                  "string[]",
                  "nonnegative_integer_token_array",
                  "nonnegative_integer_token_array[]"
                ],
                "mode": "text_to_embedding"
              }
            ],
            "operation_modes": [
              "single_embedding",
              "batched_embeddings"
            ],
            "outputs": {
              "all_results": "Simpan setiap vektor bersama indeksnya. Bilangan vektor mesti sama dengan bilangan input; dimensi mesti konsisten.",
              "default_dimensions": null,
              "family": "embedding",
              "fields": [
                {
                  "description": null,
                  "name": "object",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "data[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "data[].embedding",
                  "type": "finite float[]"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "sentence-transformers/all-minilm-l12-v2"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "budget": {
                  "maximum": 512,
                  "text_unit": "bait UTF8",
                  "token_unit": "elemen tatasusunan token"
                },
                "conditions": "Kelompok homogen yang tidak kosong. ID token ialah integer bukan negatif.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "input",
                "required": true,
                "type": "string|string[]|integer[]|integer[][]"
              },
              {
                "availability": "source_interface",
                "default": "float",
                "default_known": true,
                "enum": [
                  "float"
                ],
                "enum_known": true,
                "name": "encoding_format",
                "required": false,
                "type": "string"
              },
              {
                "availability": "unsupported",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "dimensions",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "pass_through_metadata",
                "conditions": "Sumber membenarkan medan metadata JSON ini; semantik tepat di pihak huluan bergantung pada model.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "user",
                "required": false,
                "type": "json_value"
              },
              {
                "availability": "pass_through_metadata",
                "conditions": "Sumber membenarkan medan metadata JSON ini; semantik tepat di pihak huluan bergantung pada model.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "session_id",
                "required": false,
                "type": "json_value"
              },
              {
                "availability": "pass_through_metadata",
                "conditions": "Sumber membenarkan medan metadata JSON ini; semantik tepat di pihak huluan bergantung pada model.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "trace",
                "required": false,
                "type": "json_value"
              },
              {
                "availability": "source_interface",
                "conditions": "provider.options ditolak",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "provider",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "mixed input kinds",
              "empty input",
              "image/audio/file objects",
              "encoding_format=base64",
              "dimensions override"
            ]
          },
          "hints": [
            "Simpan setiap indeks dan dimensi vektor.",
            "Nama model multimodal tidak bermakna objek imej dibenarkan pada laluan khusus ini."
          ],
          "input": {
            "content_type": "application/json",
            "dimensions_override": false,
            "encoding_format": [
              "float"
            ],
            "input_shapes": [
              "string",
              "string[]",
              "nonnegative_integer_token_array",
              "nonnegative_integer_token_array[]"
            ],
            "material_types": [
              "text",
              "token_ids"
            ],
            "max_input_budget_units": 512,
            "multimodal_objects": false,
            "required": [
              "model",
              "input"
            ]
          },
          "lifecycle": {
            "mode": "synchronous_json",
            "unknown": "no embedding job endpoint inferred"
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/embeddings"
          },
          "method_aliases": [],
          "operation_modes": [
            "text_to_embedding"
          ],
          "output": {
            "default_dimensions": null,
            "family": "embedding",
            "format": "json",
            "http_success": 200,
            "vectors": "one dense float vector per input; indices/model/usage validated"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Kadar asas token",
            "units": [
              {
                "amount": "0.00001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.00000001",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"sentence-transformers/all-minilm-l12-v2\", \"input\": [\"First document\", \"Second document\"]}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n",
            "label": "curl · retained exact creation",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.embeddings.create(model='sentence-transformers/all-minilm-l12-v2',input=[\"First document\",\"Second document\"])\nprint(result)\nfor item in result.data:print(item.index,item.embedding)\n",
            "label": "Python SDK · all vectors",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "embeddings",
        "hints": [
          "Keep every vector index and dimension.",
          "Multimodal model name does not admit image objects on this exact path."
        ],
        "http": "POST",
        "in": 0.01,
        "input": [
          "text",
          "token_ids"
        ],
        "label": "Эмбеддинги",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": 0,
        "output": [
          "embedding"
        ],
        "path": "/v1/embeddings",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.00001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.00000001",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "request_model_id": "sentence-transformers/all-minilm-l12-v2",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "units": [
          {
            "amount": "0.00001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.00000001",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    }
  ],
  "model_id": "sentence-transformers/all-minilm-l12-v2",
  "nativeProvenance": {
    "input_facts_canonical_sha256": "d99d092c30b32ca65f5e228b57e9625b682281e9f3984c3bc5c9cdcd585509e6",
    "input_html_sha256": "268d265081925946538c09c01b3cc489c68006227d7f2b09e65c4d0c424a5822",
    "private_audit_sha256": "dcd90e2065471702e0f99499db9dd295de19235a30bfdb69917e3e695d04f59b",
    "role": "historical-normalized-input-audit-hashes",
    "schema": "ailoot-native-model-provenance-v2"
  },
  "page": {
    "canonical": "https://ailoot.ai/models/ms/sentence-transformers-all-minilm-l12-v2/",
    "description": "Sentence Transformers all-MiniLM-L12-v2 mengekod ayat dan perenggan pendek kepada vektor 384 dimensi untuk carian, keserupaan dan pengelompokan. Kaedah rujukannya menggunakan mean pooling dan penormalan, dengan pemotongan lalai pada 256 unit word piece.",
    "locale": "ms",
    "md_url": "https://ailoot.ai/models/ms/sentence-transformers-all-minilm-l12-v2/index.md",
    "title": "Sentence Transformers: all-MiniLM-L12-v2 — Ailoot",
    "url": "https://ailoot.ai/models/ms/sentence-transformers-all-minilm-l12-v2/"
  },
  "rawModel": {
    "about": "all-MiniLM-L12-v2 ialah pengekod Sentence Transformers untuk ayat dan perenggan pendek. Ia menghasilkan satu vektor padat 384 dimensi bagi setiap teks untuk carian semantik, pemerolehan semula maklumat, pengelompokan dan keserupaan ayat. Model menggunakan seni bina asas MiniLM-L12-H384-uncased dan ditala halus dengan pembelajaran kontrastif pada koleksi satu bilion pasangan ayat.\n\n### Kodkan unit yang mahu diperoleh semula\n\nGunakan ayat atau perenggan pendek yang menyatakan satu idea berguna. Untuk koleksi penerangan produk, kekalkan ciri dan syarat yang membezakan item: “The adapter connects a wired headset to a USB-C port” lebih bermaklumat daripada “Audio accessory.” Simpan pengecam rekod dan penerangan asal di sisi vektornya.\n\nPertanyaan carian kemudian boleh dibandingkan dengan penerangan yang dikodkan. Periksa calon yang dikembalikan untuk keperluan tepat seperti jenis penyambung atau keserasian peranti sebelum membentangkan pilihan akhir. Vektor mewakili makna teks; aplikasi carian di sekelilingnya mendapatkan rekod yang sepadan.\n\n### Mean pooling dan vektor ternormal\n\nContoh pengekodan yang diterbitkan mempuratakan perwakilan token menggunakan topeng perhatian supaya kedudukan padding tidak menyumbang kepada purata. Kemudian ia menggunakan penormalan L2. Langkah ini sebahagian daripada kaedah rujukan mendapatkan vektor ayat, bukannya arahan mengambil token sembarangan daripada transformer asas.\n\nPastikan konfigurasi model, pooling dan penormalan konsisten antara teks berindeks dan pertanyaan baharu. Perwakilan 384 komponen yang terhasil boleh dibandingkan menggunakan keserupaan kosinus. Simpan rekod konfigurasi itu bersama koleksi; pengekod 384 dimensi lain tidak menjadi serasi hanya kerana vektornya sama panjang.\n\n### Panjang input lalai dan skop latihan\n\nPembuat menetapkan pemotongan lalai melebihi 256 unit word piece. Ini had tokenizer, bukan bilangan perkataan biasa atau aksara. Untuk rekod lebih panjang, pilih bahagian pendek yang koheren dan simpan tajuk atau perincian pengenal yang diperlukan untuk mentafsir setiap satunya.\n\nProsedur latihan model menggunakan jujukan sehingga 128 token. Tetapan latihan itu berasingan daripada tetapan lalai 256 unit word piece yang diterbitkan untuk pengekodan. Petikan yang muat dalam tetapan lalai masih boleh berbeza dengan ketara daripada bahan ayat pendek semasa latihan, maka nilai penerangan panjang atau khusus menggunakan contoh yang mewakili tugas.\n\n### Aliran kerja keserupaan dan pengelompokan\n\nUntuk set mesej sokongan, embedding boleh membekalkan input berangka kepada peringkat pengelompokan. Semak beberapa mesej daripada setiap kumpulan cadangan dan mesej berhampiran sempadannya sebelum memberikan label yang mudah dibaca manusia. Untuk semakan kandungan pendua, dapatkan rekod serupa dan bandingkan ungkapan sebenar; dua petikan mungkin membincangkan subjek sama sambil memberikan arahan berbeza.\n\nEdisi L12-v2 tepat ini ialah profil embedding ayat bahasa Inggeris. Ia berbeza daripada all-MiniLM-L6-v2 dan checkpoint paraphrase-MiniLM. Nama keluarga yang dikongsi tidak memindahkan konfigurasi jujukan atau kaedah poolingnya. Gunakan vektor padat kompaknya bersama rekod sumber dan penilaian khusus tugas, bukannya menganggap nilai keserupaan sebagai jawapan yang disahkan atau keputusan editorial akhir.",
    "alias_of": null,
    "aliases": [],
    "author": "Sentence Transformers",
    "available": null,
    "canonical_model": "sentence-transformers/all-minilm-l12-v2",
    "capabilities": {
      "context_length": 512,
      "manufacturer_input": [
        "text"
      ],
      "manufacturer_output": [
        "embeddings"
      ]
    },
    "card_routes": [
      {
        "label": "Ultra",
        "rates": [
          {
            "amount": "0.00001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.00000001",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          }
        ],
        "summary": "Maklumat lengkap tentang harga konfigurasi terdapat dalam butiran."
      }
    ],
    "ctx": null,
    "entity_type": "model",
    "formats": [
      "embeddings"
    ],
    "id": "sentence-transformers/all-minilm-l12-v2",
    "input": [
      "text",
      "token_ids"
    ],
    "kind": "embedding",
    "max_out": null,
    "methods": [
      {
        "available": null,
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.",
            "errors": [
              {
                "code": null,
                "condition": "Medan wajib, perwakilan bahan atau nilai parameter tidak sah",
                "http_status": 400,
                "recovery": "Betulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/embeddings"
              },
              "job_read": null,
              "mode": "synchronous_json",
              "unknown": "Tiada titik akhir tugas pembenaman diperkenalkan."
            },
            "material_combinations": [
              {
                "alternatives": [
                  "string",
                  "string[]",
                  "nonnegative_integer_token_array",
                  "nonnegative_integer_token_array[]"
                ],
                "mode": "text_to_embedding"
              }
            ],
            "operation_modes": [
              "single_embedding",
              "batched_embeddings"
            ],
            "outputs": {
              "all_results": "Simpan setiap vektor bersama indeksnya. Bilangan vektor mesti sama dengan bilangan input; dimensi mesti konsisten.",
              "default_dimensions": null,
              "family": "embedding",
              "fields": [
                {
                  "description": null,
                  "name": "object",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "data[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "data[].embedding",
                  "type": "finite float[]"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "sentence-transformers/all-minilm-l12-v2"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "budget": {
                  "maximum": 512,
                  "text_unit": "bait UTF8",
                  "token_unit": "elemen tatasusunan token"
                },
                "conditions": "Kelompok homogen yang tidak kosong. ID token ialah integer bukan negatif.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "input",
                "required": true,
                "type": "string|string[]|integer[]|integer[][]"
              },
              {
                "availability": "source_interface",
                "default": "float",
                "default_known": true,
                "enum": [
                  "float"
                ],
                "enum_known": true,
                "name": "encoding_format",
                "required": false,
                "type": "string"
              },
              {
                "availability": "unsupported",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "dimensions",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "pass_through_metadata",
                "conditions": "Sumber membenarkan medan metadata JSON ini; semantik tepat di pihak huluan bergantung pada model.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "user",
                "required": false,
                "type": "json_value"
              },
              {
                "availability": "pass_through_metadata",
                "conditions": "Sumber membenarkan medan metadata JSON ini; semantik tepat di pihak huluan bergantung pada model.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "session_id",
                "required": false,
                "type": "json_value"
              },
              {
                "availability": "pass_through_metadata",
                "conditions": "Sumber membenarkan medan metadata JSON ini; semantik tepat di pihak huluan bergantung pada model.",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "trace",
                "required": false,
                "type": "json_value"
              },
              {
                "availability": "source_interface",
                "conditions": "provider.options ditolak",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "provider",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "mixed input kinds",
              "empty input",
              "image/audio/file objects",
              "encoding_format=base64",
              "dimensions override"
            ]
          },
          "hints": [
            "Simpan setiap indeks dan dimensi vektor.",
            "Nama model multimodal tidak bermakna objek imej dibenarkan pada laluan khusus ini."
          ],
          "input": {
            "content_type": "application/json",
            "dimensions_override": false,
            "encoding_format": [
              "float"
            ],
            "input_shapes": [
              "string",
              "string[]",
              "nonnegative_integer_token_array",
              "nonnegative_integer_token_array[]"
            ],
            "material_types": [
              "text",
              "token_ids"
            ],
            "max_input_budget_units": 512,
            "multimodal_objects": false,
            "required": [
              "model",
              "input"
            ]
          },
          "lifecycle": {
            "mode": "synchronous_json",
            "unknown": "no embedding job endpoint inferred"
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/embeddings"
          },
          "method_aliases": [],
          "operation_modes": [
            "text_to_embedding"
          ],
          "output": {
            "default_dimensions": null,
            "family": "embedding",
            "format": "json",
            "http_success": 200,
            "vectors": "one dense float vector per input; indices/model/usage validated"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Kadar asas token",
            "units": [
              {
                "amount": "0.00001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.00000001",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"sentence-transformers/all-minilm-l12-v2\", \"input\": [\"First document\", \"Second document\"]}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n",
            "label": "curl · retained exact creation",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.embeddings.create(model='sentence-transformers/all-minilm-l12-v2',input=[\"First document\",\"Second document\"])\nprint(result)\nfor item in result.data:print(item.index,item.embedding)\n",
            "label": "Python SDK · all vectors",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "embeddings",
        "hints": [
          "Keep every vector index and dimension.",
          "Multimodal model name does not admit image objects on this exact path."
        ],
        "http": "POST",
        "in": 0.01,
        "input": [
          "text",
          "token_ids"
        ],
        "label": "Эмбеддинги",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": 0,
        "output": [
          "embedding"
        ],
        "path": "/v1/embeddings",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.00001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.00000001",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "request_model_id": "sentence-transformers/all-minilm-l12-v2",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [],
        "units": [
          {
            "amount": "0.00001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.00000001",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    ],
    "model_aliases": [
      {
        "canonical_model_id": "sentence-transformers/all-minilm-l12-v2",
        "request_model_id": "sentence-transformers/all-minilm-l12-v2",
        "route_label": "Ultra"
      }
    ],
    "name": "Sentence Transformers: all-MiniLM-L12-v2",
    "price": {
      "in": 0.01,
      "in_label": null,
      "out": 0,
      "out_label": null,
      "scope_label": "Token rates",
      "sort_in": 0.01,
      "sort_out": 0,
      "varies": false
    },
    "public_id": "sentence-transformers/all-minilm-l12-v2",
    "short": "Sentence Transformers all-MiniLM-L12-v2 mengekod ayat dan perenggan pendek kepada vektor 384 dimensi untuk carian, keserupaan dan pengelompokan. Kaedah rujukannya menggunakan mean pooling dan penormalan, dengan pemotongan lalai pada 256 unit word piece."
  },
  "renderer_schema": {
    "method_order": "Original DTO methods order; every exact route/format/path/caller survives.",
    "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers."
  },
  "representation": "exact-public-dto-and-native-renderer-html",
  "representationNotes": {
    "current_reference": {
      "about_json_pointer": "/aboutHtml",
      "methods": [
        {
          "contract_json_pointer": "/methods/0/rawMethod/contract",
          "html_json_pointer": "/methods/0/html",
          "method_ordinal": 0
        }
      ],
      "role": "current-semantic-reference"
    },
    "raw_input": {
      "examples_role": "historical-input-not-current-ready-examples",
      "json_pointers": [
        "/rawModel",
        "/methods/0/rawMethod"
      ],
      "role": "historical-owner-input"
    },
    "schema": "ailoot-native-model-representations-v1"
  },
  "schema": "ailoot-static-model-facts-v1",
  "schema_version": 1,
  "shortText": "Sentence Transformers all-MiniLM-L12-v2 mengekod ayat dan perenggan pendek kepada vektor 384 dimensi untuk carian, keserupaan dan pengelompokan. Kaedah rujukannya menggunakan mean pooling dan penormalan, dengan pemotongan lalai pada 256 unit word piece.",
  "source": {
    "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1",
    "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036",
    "raw_model_json_sha256": "ea0cb2c404d8b53d2e386309d6901b08de0c551c6b34c2c0ec53e88d90e14455",
    "renderer_sha256": "1dab5ba62521e9568c8b7c82005622cabbf330a075df7cce1f83274a04009460"
  },
  "sourceRevision": "3a490fac31bc72df25f829fed9eb4f34172ae6d74cc9f047de1ee339a5690ccb"
}