{ "aboutHtml": "

Voyage rerank-3-lite ialah edisi siri Rerank 3 Voyage yang memfokuskan kependaman. Ia menerima pertanyaan teks dan dokumen calon, menilai setiap pasangan pertanyaan-dokumen bersama-sama, serta mengembalikan skor kerelevanan mengikut kedudukan. Ia berfungsi pada peringkat kedua carian: alat pemerolehan berasaskan pembenaman atau kata kunci mencari calon, kemudian Lite memperhalusi susunannya. Hasilnya ialah pemeringkatan untuk digunakan dalam carian atau aliran kerja penjanaan diperkaya pemerolehan maklumat.

Perubahan dalam Rerank 3 Lite Pengeluar menekankan pemerolehan dokumen panjang dan kod yang lebih kukuh berbanding rerank-2.5-lite. Kedua-dua edisi Rerank 3 mengekalkan pematuhan arahan dan kelas konteks 32K yang sama, manakala Lite direka untuk aplikasi yang sensitif terhadap kependaman. Ini menjadikannya calon praktikal untuk carian pangkalan pengetahuan interaktif, pemerolehan dokumen sokongan dan carian kod apabila pengguna memerlukan hasil berkaitan dengan segera. Pilih berdasarkan keperluan kualiti dan masa respons koleksi sebenar, tanpa menganggap edisi lebih kecil bermakna tetingkap konteks lebih kecil.

Pandu kerelevanan melalui pertanyaan Arahan bahasa semula jadi boleh disertakan bersama pertanyaan untuk menerangkan perkara yang dianggap relevan. Pastikan soalan dan keutamaan kerelevanan ringkas serta konsisten. Untuk carian sokongan perisian, gunakan “Cari prosedur untuk menetapkan semula peranti; utamakan arahan bagi versi perkakasan yang dinyatakan.” Untuk nama produk yang kabur, sertakan kategori produk supaya makna yang tidak berkaitan tidak mendominasi. Keutamaan dalam pertanyaan memandu penskoran semantik; gunakan metadata koleksi yang jelas untuk memilih produk, versi dokumen atau skop akses yang betul sebelum membina senarai calon.

Sediakan senarai pendek calon teks Dokumen input ialah rentetan. Ekstrak teks yang boleh dibaca daripada bahan sumber dan kekalkan tajuk, pengepala, pengecam serta konteks sekeliling yang berguna. Kekalkan pemetaan stabil daripada setiap kedudukan input kepada rekod asal. Untuk artikel penyelesaian masalah, sertakan gejala dan prosedur berkaitan, bukan hanya ayat yang terpisah. Untuk carian kod sumber, sertakan fungsi dan maklumat berhampiran yang diperlukan untuk membezakannya daripada fungsi bernama serupa. Buang navigasi atau teks templat berulang apabila ia mengambil ruang petikan yang berguna.

Pemeringkat semula hanya boleh menyusun semula dokumen yang diterimanya. Jika carian pertama tidak pernah memperoleh artikel berkaitan, peringkat ini tidak boleh mendapatkan kembali calon yang tiada itu. Periksa senarai pendek dan susunan akhir apabila hasil kelihatan salah. Apabila dokumen panjang meliputi banyak topik, asingkan bahagian yang koheren dan kekalkan rujukan dokumen induknya supaya bahagian berkaitan boleh dipilih tanpa kehilangan sumbernya.

Had konteks dan permintaan Panduan semasa pengeluar menyatakan maksimum pertanyaan 8,000 token dan maksimum gabungan 32,000 token bagi pertanyaan bersama setiap dokumen individu. Ia membenarkan sehingga 1,000 dokumen calon dan jumlah belanjawan permintaan 600,000 token, dikira sebagai token pertanyaan didarab bilangan dokumen, ditambah semua token dokumen. Oleh itu, pertanyaan panjang menggunakan ruang dalam setiap pasangan dan menyumbang berulang kali kepada jumlah belanjawan. Kira teks yang dihantar dengan pentoken model yang sesuai tanpa menganggap aksara, perkataan dan token boleh saling menggantikan.

Contohnya, pertanyaan 500 token dengan 100 dokumen yang masing-masing mengandungi 4,000 token bersamaan 450,000 token input mengikut formula itu. Ini menggambarkan perancangan belanjawan, bukannya saiz senarai pendek yang disyorkan atau hasil kelajuan yang diukur. Pilihan pemangkasan yang didokumenkan diaktifkan secara lalai; teks yang terlalu besar boleh dipendekkan sebelum penskoran. Sediakan bahagian penting dengan sengaja supaya pemangkasan tidak membuang petikan yang perlu dipadankan.

Baca dan gunakan hasil Hasil disusun daripada skor kerelevanan tertinggi ke bawah. Setiap hasil mengenal pasti kedudukan input asal dokumen, membolehkan aplikasi melampirkan tajuk, pengecam rekod dan sumbernya sendiri. Tetapan top_k mengawal bilangan calon berperingkat yang dikembalikan; tanpanya, semua calon dikembalikan. Antara muka REST pengeluar juga boleh mengembalikan teks dokumen. Kekalkan pengecam asal bersama hasil yang dipilih apabila memaparkan halaman carian atau meneruskan bukti ke langkah penjanaan jawapan.

Skor kerelevanan menyatakan sejauh mana calon sepadan dengan pertanyaan; ia tidak membuktikan bahawa pernyataan calon adalah benar. Bandingkan item berkedudukan tertinggi dengan soalan sebenar pengguna, termasuk pengecualian dan perbezaan versi dokumen. Jika setiap calon tidak relevan, item berkedudukan tertinggi tetap wujud. Tentukan cara aplikasi anda mengendalikan keadaan itu menggunakan pertanyaan yang mewakili koleksi.

Menaik taraf dan memilih edisi Pengeluar menerangkan rerank-3-lite sebagai naik taraf kepada rerank-2.5-lite dengan semantik API yang tidak berubah dan skor yang ditentukur kepada taburan pendahulunya yang sepadan. Kekalkan pemetaan rekod dan peringkat pemerolehan maklumat sedia ada, kemudian bandingkan susunan yang terhasil pada pertanyaan bermakna sebelum bergantung pada ambang skor yang telah ditetapkan. Gunakan Lite untuk pengalaman carian yang mementingkan masa respons; gunakan edisi rerank-3 yang memfokuskan kualiti sebagai perbandingan apabila kerelevanan calon yang sukar menjadi keutamaan lebih besar.

", "aboutText": "Voyage rerank-3-lite ialah edisi siri Rerank 3 Voyage yang memfokuskan kependaman. Ia menerima pertanyaan teks dan dokumen calon, menilai setiap pasangan pertanyaan-dokumen bersama-sama, serta mengembalikan skor kerelevanan mengikut kedudukan. Ia berfungsi pada peringkat kedua carian: alat pemerolehan berasaskan pembenaman atau kata kunci mencari calon, kemudian Lite memperhalusi susunannya. Hasilnya ialah pemeringkatan untuk digunakan dalam carian atau aliran kerja penjanaan diperkaya pemerolehan maklumat.\n\nPerubahan dalam Rerank 3 Lite\nPengeluar menekankan pemerolehan dokumen panjang dan kod yang lebih kukuh berbanding rerank-2.5-lite. Kedua-dua edisi Rerank 3 mengekalkan pematuhan arahan dan kelas konteks 32K yang sama, manakala Lite direka untuk aplikasi yang sensitif terhadap kependaman. Ini menjadikannya calon praktikal untuk carian pangkalan pengetahuan interaktif, pemerolehan dokumen sokongan dan carian kod apabila pengguna memerlukan hasil berkaitan dengan segera. Pilih berdasarkan keperluan kualiti dan masa respons koleksi sebenar, tanpa menganggap edisi lebih kecil bermakna tetingkap konteks lebih kecil.\n\nPandu kerelevanan melalui pertanyaan\nArahan bahasa semula jadi boleh disertakan bersama pertanyaan untuk menerangkan perkara yang dianggap relevan. Pastikan soalan dan keutamaan kerelevanan ringkas serta konsisten. Untuk carian sokongan perisian, gunakan “Cari prosedur untuk menetapkan semula peranti; utamakan arahan bagi versi perkakasan yang dinyatakan.” Untuk nama produk yang kabur, sertakan kategori produk supaya makna yang tidak berkaitan tidak mendominasi. Keutamaan dalam pertanyaan memandu penskoran semantik; gunakan metadata koleksi yang jelas untuk memilih produk, versi dokumen atau skop akses yang betul sebelum membina senarai calon.\n\nSediakan senarai pendek calon teks\nDokumen input ialah rentetan. Ekstrak teks yang boleh dibaca daripada bahan sumber dan kekalkan tajuk, pengepala, pengecam serta konteks sekeliling yang berguna. Kekalkan pemetaan stabil daripada setiap kedudukan input kepada rekod asal. Untuk artikel penyelesaian masalah, sertakan gejala dan prosedur berkaitan, bukan hanya ayat yang terpisah. Untuk carian kod sumber, sertakan fungsi dan maklumat berhampiran yang diperlukan untuk membezakannya daripada fungsi bernama serupa. Buang navigasi atau teks templat berulang apabila ia mengambil ruang petikan yang berguna.\n\nPemeringkat semula hanya boleh menyusun semula dokumen yang diterimanya. Jika carian pertama tidak pernah memperoleh artikel berkaitan, peringkat ini tidak boleh mendapatkan kembali calon yang tiada itu. Periksa senarai pendek dan susunan akhir apabila hasil kelihatan salah. Apabila dokumen panjang meliputi banyak topik, asingkan bahagian yang koheren dan kekalkan rujukan dokumen induknya supaya bahagian berkaitan boleh dipilih tanpa kehilangan sumbernya.\n\nHad konteks dan permintaan\nPanduan semasa pengeluar menyatakan maksimum pertanyaan 8,000 token dan maksimum gabungan 32,000 token bagi pertanyaan bersama setiap dokumen individu. Ia membenarkan sehingga 1,000 dokumen calon dan jumlah belanjawan permintaan 600,000 token, dikira sebagai token pertanyaan didarab bilangan dokumen, ditambah semua token dokumen. Oleh itu, pertanyaan panjang menggunakan ruang dalam setiap pasangan dan menyumbang berulang kali kepada jumlah belanjawan. Kira teks yang dihantar dengan pentoken model yang sesuai tanpa menganggap aksara, perkataan dan token boleh saling menggantikan.\n\nContohnya, pertanyaan 500 token dengan 100 dokumen yang masing-masing mengandungi 4,000 token bersamaan 450,000 token input mengikut formula itu. Ini menggambarkan perancangan belanjawan, bukannya saiz senarai pendek yang disyorkan atau hasil kelajuan yang diukur. Pilihan pemangkasan yang didokumenkan diaktifkan secara lalai; teks yang terlalu besar boleh dipendekkan sebelum penskoran. Sediakan bahagian penting dengan sengaja supaya pemangkasan tidak membuang petikan yang perlu dipadankan.\n\nBaca dan gunakan hasil\nHasil disusun daripada skor kerelevanan tertinggi ke bawah. Setiap hasil mengenal pasti kedudukan input asal dokumen, membolehkan aplikasi melampirkan tajuk, pengecam rekod dan sumbernya sendiri. Tetapan top_k mengawal bilangan calon berperingkat yang dikembalikan; tanpanya, semua calon dikembalikan. Antara muka REST pengeluar juga boleh mengembalikan teks dokumen. Kekalkan pengecam asal bersama hasil yang dipilih apabila memaparkan halaman carian atau meneruskan bukti ke langkah penjanaan jawapan.\n\nSkor kerelevanan menyatakan sejauh mana calon sepadan dengan pertanyaan; ia tidak membuktikan bahawa pernyataan calon adalah benar. Bandingkan item berkedudukan tertinggi dengan soalan sebenar pengguna, termasuk pengecualian dan perbezaan versi dokumen. Jika setiap calon tidak relevan, item berkedudukan tertinggi tetap wujud. Tentukan cara aplikasi anda mengendalikan keadaan itu menggunakan pertanyaan yang mewakili koleksi.\n\nMenaik taraf dan memilih edisi\nPengeluar menerangkan rerank-3-lite sebagai naik taraf kepada rerank-2.5-lite dengan semantik API yang tidak berubah dan skor yang ditentukur kepada taburan pendahulunya yang sepadan. Kekalkan pemetaan rekod dan peringkat pemerolehan maklumat sedia ada, kemudian bandingkan susunan yang terhasil pada pertanyaan bermakna sebelum bergantung pada ambang skor yang telah ditetapkan. Gunakan Lite untuk pengalaman carian yang mementingkan masa respons; gunakan edisi rerank-3 yang memfokuskan kualiti sebagai perbandingan apabila kerelevanan calon yang sukar menjadi keutamaan lebih besar.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "71b7b04da3425c637eb5d08b2887088cde244437bac80ecf6a6c896d2a7c51be", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "ms", "methods": [ { "html": "
•

VoyageAI by MongoDB: rerank-3-lite

VoyageAI by MongoDB /voyageai/rerank-3-lite

Pengenalan

Voyage rerank-3-lite memberi skor dan menyusun semula dokumen teks calon untuk pertanyaan, dengan tumpuan pada carian yang responsif. Ia menyokong arahan kerelevanan dan tetingkap pertanyaan-dokumen 32,000 token, menjadikannya berguna selepas pemerolehan maklumat berasaskan vektor atau kata kunci dalam aliran kerja carian dan RAG.

Input yang diterima
Teks
Hasil
Hasil mengikut kedudukan
Tentang model

Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.

Voyage rerank-3-lite ialah edisi siri Rerank 3 Voyage yang memfokuskan kependaman. Ia menerima pertanyaan teks dan dokumen calon, menilai setiap pasangan pertanyaan-dokumen bersama-sama, serta mengembalikan skor kerelevanan mengikut kedudukan. Ia berfungsi pada peringkat kedua carian: alat pemerolehan berasaskan pembenaman atau kata kunci mencari calon, kemudian Lite memperhalusi susunannya. Hasilnya ialah pemeringkatan untuk digunakan dalam carian atau aliran kerja penjanaan diperkaya pemerolehan maklumat.

Perubahan dalam Rerank 3 Lite Pengeluar menekankan pemerolehan dokumen panjang dan kod yang lebih kukuh berbanding rerank-2.5-lite. Kedua-dua edisi Rerank 3 mengekalkan pematuhan arahan dan kelas konteks 32K yang sama, manakala Lite direka untuk aplikasi yang sensitif terhadap kependaman. Ini menjadikannya calon praktikal untuk carian pangkalan pengetahuan interaktif, pemerolehan dokumen sokongan dan carian kod apabila pengguna memerlukan hasil berkaitan dengan segera. Pilih berdasarkan keperluan kualiti dan masa respons koleksi sebenar, tanpa menganggap edisi lebih kecil bermakna tetingkap konteks lebih kecil.

Pandu kerelevanan melalui pertanyaan Arahan bahasa semula jadi boleh disertakan bersama pertanyaan untuk menerangkan perkara yang dianggap relevan. Pastikan soalan dan keutamaan kerelevanan ringkas serta konsisten. Untuk carian sokongan perisian, gunakan “Cari prosedur untuk menetapkan semula peranti; utamakan arahan bagi versi perkakasan yang dinyatakan.” Untuk nama produk yang kabur, sertakan kategori produk supaya makna yang tidak berkaitan tidak mendominasi. Keutamaan dalam pertanyaan memandu penskoran semantik; gunakan metadata koleksi yang jelas untuk memilih produk, versi dokumen atau skop akses yang betul sebelum membina senarai calon.

Sediakan senarai pendek calon teks Dokumen input ialah rentetan. Ekstrak teks yang boleh dibaca daripada bahan sumber dan kekalkan tajuk, pengepala, pengecam serta konteks sekeliling yang berguna. Kekalkan pemetaan stabil daripada setiap kedudukan input kepada rekod asal. Untuk artikel penyelesaian masalah, sertakan gejala dan prosedur berkaitan, bukan hanya ayat yang terpisah. Untuk carian kod sumber, sertakan fungsi dan maklumat berhampiran yang diperlukan untuk membezakannya daripada fungsi bernama serupa. Buang navigasi atau teks templat berulang apabila ia mengambil ruang petikan yang berguna.

Pemeringkat semula hanya boleh menyusun semula dokumen yang diterimanya. Jika carian pertama tidak pernah memperoleh artikel berkaitan, peringkat ini tidak boleh mendapatkan kembali calon yang tiada itu. Periksa senarai pendek dan susunan akhir apabila hasil kelihatan salah. Apabila dokumen panjang meliputi banyak topik, asingkan bahagian yang koheren dan kekalkan rujukan dokumen induknya supaya bahagian berkaitan boleh dipilih tanpa kehilangan sumbernya.

Had konteks dan permintaan Panduan semasa pengeluar menyatakan maksimum pertanyaan 8,000 token dan maksimum gabungan 32,000 token bagi pertanyaan bersama setiap dokumen individu. Ia membenarkan sehingga 1,000 dokumen calon dan jumlah belanjawan permintaan 600,000 token, dikira sebagai token pertanyaan didarab bilangan dokumen, ditambah semua token dokumen. Oleh itu, pertanyaan panjang menggunakan ruang dalam setiap pasangan dan menyumbang berulang kali kepada jumlah belanjawan. Kira teks yang dihantar dengan pentoken model yang sesuai tanpa menganggap aksara, perkataan dan token boleh saling menggantikan.

Contohnya, pertanyaan 500 token dengan 100 dokumen yang masing-masing mengandungi 4,000 token bersamaan 450,000 token input mengikut formula itu. Ini menggambarkan perancangan belanjawan, bukannya saiz senarai pendek yang disyorkan atau hasil kelajuan yang diukur. Pilihan pemangkasan yang didokumenkan diaktifkan secara lalai; teks yang terlalu besar boleh dipendekkan sebelum penskoran. Sediakan bahagian penting dengan sengaja supaya pemangkasan tidak membuang petikan yang perlu dipadankan.

Baca dan gunakan hasil Hasil disusun daripada skor kerelevanan tertinggi ke bawah. Setiap hasil mengenal pasti kedudukan input asal dokumen, membolehkan aplikasi melampirkan tajuk, pengecam rekod dan sumbernya sendiri. Tetapan top_k mengawal bilangan calon berperingkat yang dikembalikan; tanpanya, semua calon dikembalikan. Antara muka REST pengeluar juga boleh mengembalikan teks dokumen. Kekalkan pengecam asal bersama hasil yang dipilih apabila memaparkan halaman carian atau meneruskan bukti ke langkah penjanaan jawapan.

Skor kerelevanan menyatakan sejauh mana calon sepadan dengan pertanyaan; ia tidak membuktikan bahawa pernyataan calon adalah benar. Bandingkan item berkedudukan tertinggi dengan soalan sebenar pengguna, termasuk pengecualian dan perbezaan versi dokumen. Jika setiap calon tidak relevan, item berkedudukan tertinggi tetap wujud. Tentukan cara aplikasi anda mengendalikan keadaan itu menggunakan pertanyaan yang mewakili koleksi.

Menaik taraf dan memilih edisi Pengeluar menerangkan rerank-3-lite sebagai naik taraf kepada rerank-2.5-lite dengan semantik API yang tidak berubah dan skor yang ditentukur kepada taburan pendahulunya yang sepadan. Kekalkan pemetaan rekod dan peringkat pemerolehan maklumat sedia ada, kemudian bandingkan susunan yang terhasil pada pertanyaan bermakna sebelum bergantung pada ambang skor yang telah ditetapkan. Gunakan Lite untuk pengalaman carian yang mementingkan masa respons; gunakan edisi rerank-3 yang memfokuskan kualiti sebagai perbandingan apabila kerelevanan calon yang sukar menjadi keutamaan lebih besar.

Tersedia di Ailoot · input & kaedah

Ailoot Ultra · Pemeringkatan semula POST /v1/rerank
Input
text
Output
rerank
Format output
json
MedanJenisKeperluanNilai & hadLalai
MedandocumentsJenisarrayKeperluanDiperlukanNilai & hadLalai—
MedanmodelJenisstringKeperluanDiperlukanNilai & had
voyageai/rerank-3-lite
Lalai—
MedanproviderJenisschemaKeperluanPilihanNilai & hadLalai—
MedanqueryJenisstringKeperluanDiperlukanNilai & hadLalai—
Medansession_idJenisstringKeperluanPilihanNilai & hadLalai—
Medantop_nJenisintegerKeperluanPilihanNilai & had
Minimum: 1
Lalai—
MedantraceJenisschemaKeperluanPilihanNilai & hadLalai—
MedanuserJenisstringKeperluanPilihanNilai & hadLalai—
Medandocuments[].textJenisstringKeperluanPilihanNilai & hadLalai—
Medandocuments[].imageJenisstringKeperluanPilihanNilai & hadLalai—
Gabungan bahan input

text_rerank · Diperlukan: query, documents array with minItems1

Parameter kaedah dan kitar hayat
ParameterKontrak
Parametercontent_typeKontrakapplication/json
ParameterrequiredKontrakmodel, query, documents
Parametermaterial_typesKontraktext
Parameteroptional_controlsKontrakprovider, session_id, top_n, trace, user
Parametermultimodal_input_bindingKontraknull

Kitar hayat: synchronous

Hantar ID model yang tepat dan simpan respons natif yang lengkap.

Pelan harga

Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.

Mod pantas
Tidak dinyatakan Apabila mod pantas dipilih
Mod flex
Tidak dinyatakan Apabila mod flex dipilih
Usaha penaakulan maksimum
Tidak dinyatakan Apabila usaha penaakulan maksimum menggunakan pelarasan default

Kadar Ailoot

Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

KonfigurasiJadual kadarUnit pengebilanCaj
KonfigurasiKadar asas tokenJadual kadarKadar asasUnit pengebilan—Caj
Input · Token input — / 1K token
Output · Token output — / 1K token
Input · Bacaan cache — / 1K token
Input · Penulisan cache — / 1K token
Input · Penulisan cache, 1 jam — / 1K token
KonfigurasiUltraJadual kadar—Unit pengebilan/ 1K tokenCaj
Input $0.00004 / 1K token

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. Cara rizab dan penyelesaian caj berfungsi →

Contoh permintaan

Ailoot Ultra · Pemeringkatan semula

{\n  "documents": [\n    "Paris is the capital of France.",\n    "Berlin is the capital of Germany."\n  ],\n  "model": "voyageai/rerank-3-lite",\n  "query": "What is the capital of France?",\n  "top_n": 3\n}

Terima dan simpan hasil

Ailoot Ultra · Pemeringkatan semula

json

Simpan semua hasil yang selesai

Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.

Setiap indeks hasil sebenar, relevance_score terhingga dan objek dokumen asal dikekalkan. Indeks mengikat tatasusunan dokumen asal. Keseluruhan JSON asal disimpan dan hanya dikembalikan selepas penyelesaian caj.

Jika respons asal perlu disemak

Simpan operasi asal dan balasan penuh/separa; jangan ulang POST.

Medan respons
MedanJenis
MedanmodelJenisstring
MedanidJenisstring
MedanproviderJenisstring
Medanresults[].indexJenisinteger
Medanresults[].relevance_scoreJenisnumber
Medanresults[].document.textJenisstring
Medanresults[].document.imageJenisstring
Medanusage.search_unitsJenisinteger
Medanusage.total_tokensJenisinteger
Medanusage.costJenisnumber
Ralat dan langkah seterusnya
ResponsSyaratLangkah seterusnya
Respons400 · invalid_request_errorSyaratMedan wajib, bentuk perwakilan atau nilai tidak sahLangkah seterusnyaBetulkan medan permintaan yang dinyatakan.

Alias

Alias model

Ailoot Ultra voyageai/rerank-3-lite

Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

ID pemanggil berkaitan

voyageai/rerank-3-lite

", "method_identity": { "effective_request_model_id": "voyageai/rerank-3-lite", "fmt": "rerank", "http": "POST", "path": "/v1/rerank", "request_model_id": "voyageai/rerank-3-lite", "route_label": "Ultra" }, "method_key": "Ultra|rerank|/v1/rerank|voyageai%2Frerank-3-lite", "ordinal": 0, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Every actual result index, finite relevance_score and original document object is retained. Indices bind the original document array. Entire original JSON is stored and returned only after settlement.", "errors": [ { "code": null, "condition": "Medan wajib, bentuk perwakilan atau nilai tidak sah", "http_status": 400, "recovery": "Betulkan medan permintaan yang dinyatakan.", "type": "invalid_request_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "cancel": null, "idempotency_header": null, "job_retrieve": null, "mode": "synchronous", "streaming": false, "unknown": "Simpan operasi asal dan balasan penuh/separa; jangan ulang POST." }, "material_combinations": [ { "accepted": [ "string documents", "objects with text; image only for separately exact-supported multimodal model" ], "mode": "text_rerank", "required": [ "query", "documents array with minItems1" ] } ], "operation_modes": [ "rerank" ], "outputs": { "all_results": "Setiap indeks hasil sebenar, relevance_score terhingga dan objek dokumen asal dikekalkan. Indeks mengikat tatasusunan dokumen asal. Keseluruhan JSON asal disimpan dan hanya dikembalikan selepas penyelesaian caj.", "family": "rerank", "fields": [ { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "id", "type": "string" }, { "description": null, "name": "provider", "type": "string" }, { "description": null, "name": "results[].index", "type": "integer" }, { "description": null, "name": "results[].relevance_score", "type": "number" }, { "description": null, "name": "results[].document.text", "type": "string" }, { "description": null, "name": "results[].document.image", "type": "string" }, { "description": null, "name": "usage.search_units", "type": "integer" }, { "description": null, "name": "usage.total_tokens", "type": "integer" }, { "description": null, "name": "usage.cost", "type": "number" } ], "format": "json", "schema": { "description": "Rerank response containing ranked results", "example": { "id": "gen-rerank-1234567890-abc", "model": "cohere/rerank-v3.5", "results": [ { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 } ], "usage": { "search_units": 1, "total_tokens": 150 } }, "properties": { "id": { "description": "Unique identifier for the rerank response (ORID format)", "example": "gen-rerank-1234567890-abc", "type": "string" }, "model": { "description": "The model used for reranking", "example": "cohere/rerank-v3.5", "type": "string" }, "provider": { "description": "The provider that served the rerank request", "example": "Cohere", "type": "string" }, "results": { "description": "List of rerank results sorted by relevance", "example": [ { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 } ], "items": { "description": "A single rerank result", "example": { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 }, "properties": { "document": { "description": "The document object echoing the original input (text and/or image)", "properties": { "image": { "description": "The image (URL or data URI) from the original document", "example": "https://example.com/image.png", "type": "string" }, "text": { "description": "The document text", "example": "Paris is the capital of France.", "type": "string" } }, "type": "object" }, "index": { "description": "Index of the document in the original input list", "example": 0, "type": "integer" }, "relevance_score": { "description": "Relevance score of the document to the query", "example": 0.98, "format": "double", "type": "number" } }, "required": [ "index", "relevance_score", "document" ], "type": "object" }, "type": "array" }, "usage": { "description": "Usage statistics", "example": { "search_units": 1, "total_tokens": 150 }, "properties": { "cost": { "description": "Cost of the request in credits", "example": 0.001, "format": "double", "type": "number" }, "search_units": { "description": "Number of search units consumed (Cohere billing)", "example": 1, "type": "integer" }, "total_tokens": { "description": "Total number of tokens used", "example": 150, "type": "integer" } }, "type": "object" } }, "required": [ "model", "results" ], "type": "object" } }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "description": "The list of documents to rerank. Documents may be plain strings, or structured objects with `text` and/or `image` for multimodal models.", "enum": null, "enum_known": false, "minItems": 1, "name": "documents", "required": true, "type": "array" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "voyageai/rerank-3-lite" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "provider", "required": false, "type": "schema" }, { "availability": "source_interface", "default": null, "default_known": false, "description": "The search query to rerank documents against", "enum": null, "enum_known": false, "name": "query", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "description": "A unique identifier for grouping related requests (e.g., a conversation or agent workflow). Used for observability grouping in Broadcast and private logging; never sent to the provider. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters.", "enum": null, "enum_known": false, "maxLength": 256, "name": "session_id", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "description": "Number of most relevant documents to return", "enum": null, "enum_known": false, "minimum": 1, "name": "top_n", "required": false, "type": "integer" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "trace", "required": false, "type": "schema" }, { "availability": "source_interface", "default": null, "default_known": false, "description": "A unique identifier representing your end-user. Forwarded to Broadcast and private logging as the end-user id; never sent to the provider.", "enum": null, "enum_known": false, "maxLength": 256, "name": "user", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "documents[].text", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "description": "Official family image carrier is remote http/https URL or data:image URI; only for exact multimodal-model bindings.", "enum": null, "enum_known": false, "name": "documents[].image", "required": false, "type": "string" } ], "unsupported": [ "stream=true" ] }, "hints": [ "Hantar ID model yang tepat dan simpan respons natif yang lengkap." ], "input": { "content_type": "application/json", "material_types": [ "text" ], "multimodal_input_binding": null, "optional_controls": [ "provider", "session_id", "top_n", "trace", "user" ], "required": [ "model", "query", "documents" ] }, "lifecycle": { "cancel": null, "idempotency_header": null, "job_retrieve": null, "mode": "synchronous", "streaming": false, "unknown": "Preserve original operation and full/partial reply; do not replay POST." }, "manufacturer_capability": { "context_length": 32000, "manufacturer_input": [ "text" ], "manufacturer_output": [ "rerank" ] }, "method": { "http": "POST", "path": "/v1/rerank" }, "method_aliases": [], "operation_modes": [ "rerank" ], "output": { "all_results": "Every actual result index, finite relevance_score and original document object is retained. Indices bind the original document array. Entire original JSON is stored and returned only after settlement.", "family": "rerank", "fields": [ { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "id", "type": "string" }, { "description": null, "name": "provider", "type": "string" }, { "description": null, "name": "results[].index", "type": "integer" }, { "description": null, "name": "results[].relevance_score", "type": "number" }, { "description": null, "name": "results[].document.text", "type": "string" }, { "description": null, "name": "results[].document.image", "type": "string" }, { "description": null, "name": "usage.search_units", "type": "integer" }, { "description": null, "name": "usage.total_tokens", "type": "integer" }, { "description": null, "name": "usage.cost", "type": "number" } ], "format": "json", "schema": { "description": "Rerank response containing ranked results", "example": { "id": "gen-rerank-1234567890-abc", "model": "cohere/rerank-v3.5", "results": [ { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 } ], "usage": { "search_units": 1, "total_tokens": 150 } }, "properties": { "id": { "description": "Unique identifier for the rerank response (ORID format)", "example": "gen-rerank-1234567890-abc", "type": "string" }, "model": { "description": "The model used for reranking", "example": "cohere/rerank-v3.5", "type": "string" }, "provider": { "description": "The provider that served the rerank request", "example": "Cohere", "type": "string" }, "results": { "description": "List of rerank results sorted by relevance", "example": [ { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 } ], "items": { "description": "A single rerank result", "example": { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 }, "properties": { "document": { "description": "The document object echoing the original input (text and/or image)", "properties": { "image": { "description": "The image (URL or data URI) from the original document", "example": "https://example.com/image.png", "type": "string" }, "text": { "description": "The document text", "example": "Paris is the capital of France.", "type": "string" } }, "type": "object" }, "index": { "description": "Index of the document in the original input list", "example": 0, "type": "integer" }, "relevance_score": { "description": "Relevance score of the document to the query", "example": 0.98, "format": "double", "type": "number" } }, "required": [ "index", "relevance_score", "document" ], "type": "object" }, "type": "array" }, "usage": { "description": "Usage statistics", "example": { "search_units": 1, "total_tokens": 150 }, "properties": { "cost": { "description": "Cost of the request in credits", "example": 0.001, "format": "double", "type": "number" }, "search_units": { "description": "Number of search units consumed (Cohere billing)", "example": 1, "type": "integer" }, "total_tokens": { "description": "Total number of tokens used", "example": 150, "type": "integer" } }, "type": "object" } }, "required": [ "model", "results" ], "type": "object" } }, "schema": { "request": { "description": "Rerank request input", "example": { "documents": [ "Paris is the capital of France.", "Berlin is the capital of Germany." ], "model": "cohere/rerank-v3.5", "query": "What is the capital of France?", "top_n": 3 }, "properties": { "documents": { "description": "The list of documents to rerank. Documents may be plain strings, or structured objects with `text` and/or `image` for multimodal models.", "example": [ "Paris is the capital of France.", "Berlin is the capital of Germany." ], "items": { "anyOf": [ { "type": "string" }, { "description": "A structured document with optional text and/or image content. At least one of `text` or `image` must be provided.", "properties": { "image": { "description": "An image associated with the document, as a remote URL (http/https) or a base64-encoded data URI (data:image/...).", "example": "https://upload.wikimedia.org/wikipedia/commons/thumb/8/8b/Phytogenic.png", "type": "string" }, "text": { "description": "The document text", "example": "AI enables robots to perceive, plan, and act autonomously.", "type": "string" } }, "type": "object" } ], "description": "A document to rerank. Either a plain string, or a structured object with optional `text` and/or `image`." }, "minItems": 1, "type": "array" }, "model": { "enum": [ "voyageai/rerank-3-lite" ], "type": "string" }, "provider": { "allOf": [ { "$ref": "#/components/schemas/ProviderPreferences" }, { "description": "Provider routing preferences for the request." } ] }, "query": { "description": "The search query to rerank documents against", "example": "What is the capital of France?", "type": "string" }, "session_id": { "description": "A unique identifier for grouping related requests (e.g., a conversation or agent workflow). Used for observability grouping in Broadcast and private logging; never sent to the provider. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters.", "example": "session-1234", "maxLength": 256, "type": "string" }, "top_n": { "description": "Number of most relevant documents to return", "example": 3, "minimum": 1, "type": "integer" }, "trace": { "$ref": "#/components/schemas/TraceConfig" }, "user": { "description": "A unique identifier representing your end-user. Forwarded to Broadcast and private logging as the end-user id; never sent to the provider.", "example": "user-1234", "maxLength": 256, "type": "string" } }, "required": [ "model", "query", "documents" ], "type": "object" }, "response": { "description": "Rerank response containing ranked results", "example": { "id": "gen-rerank-1234567890-abc", "model": "cohere/rerank-v3.5", "results": [ { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 } ], "usage": { "search_units": 1, "total_tokens": 150 } }, "properties": { "id": { "description": "Unique identifier for the rerank response (ORID format)", "example": "gen-rerank-1234567890-abc", "type": "string" }, "model": { "description": "The model used for reranking", "example": "cohere/rerank-v3.5", "type": "string" }, "provider": { "description": "The provider that served the rerank request", "example": "Cohere", "type": "string" }, "results": { "description": "List of rerank results sorted by relevance", "example": [ { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 } ], "items": { "description": "A single rerank result", "example": { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 }, "properties": { "document": { "description": "The document object echoing the original input (text and/or image)", "properties": { "image": { "description": "The image (URL or data URI) from the original document", "example": "https://example.com/image.png", "type": "string" }, "text": { "description": "The document text", "example": "Paris is the capital of France.", "type": "string" } }, "type": "object" }, "index": { "description": "Index of the document in the original input list", "example": 0, "type": "integer" }, "relevance_score": { "description": "Relevance score of the document to the query", "example": 0.98, "format": "double", "type": "number" } }, "required": [ "index", "relevance_score", "document" ], "type": "object" }, "type": "array" }, "usage": { "description": "Usage statistics", "example": { "search_units": 1, "total_tokens": 150 }, "properties": { "cost": { "description": "Cost of the request in credits", "example": 0.001, "format": "double", "type": "number" }, "search_units": { "description": "Number of search units consumed (Cohere billing)", "example": 1, "type": "integer" }, "total_tokens": { "description": "Total number of tokens used", "example": 150, "type": "integer" } }, "type": "object" } }, "required": [ "model", "results" ], "type": "object" } } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "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": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "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" } ] }, { "dimensions": { "native_endpoint": "rerank", "quoted_unit": "/ 1K tokens" }, "label": "Ultra", "units": [ { "amount": "0.00004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.00000004", "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" } ] } ], "examples": [ { "code": "{\n \"documents\": [\n \"Paris is the capital of France.\",\n \"Berlin is the capital of Germany.\"\n ],\n \"model\": \"voyageai/rerank-3-lite\",\n \"query\": \"What is the capital of France?\",\n \"top_n\": 3\n}", "label": "Retained official request structure; documentary example", "language": "json" }, { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_REQUEST_FILE:?Set your actual JSON request file}\"\nexport AILOOT_REQUEST_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads(Path(os.environ['AILOOT_REQUEST_FILE']).read_text(encoding='utf-8'))\nif not isinstance(p,dict): raise SystemExit('Request must be a JSON object')\np['model']='voyageai/rerank-3-lite'\nPath('request.json').write_text(json.dumps(p,ensure_ascii=False),encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/rerank \\\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\nprint(json.dumps(json.loads(Path('result.json').read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n", "label": "Use your actual request material and retain the complete result", "language": "bash", "material_policy": "Use real owner-supplied state/questions or query/documents. No invented file ID, document, image URL, job ID or returned result." } ], "family": "rerank", "fast_multiplier": null, "flex_multiplier": null, "fmt": "rerank", "http": "POST", "in": null, "input": [ "text" ], "label": "Pemeringkatan semula", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "native_endpoint": "rerank", "out": null, "output": [ "rerank" ], "path": "/v1/rerank", "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": "per_request", "image_input_price": null, "image_output_price": null, "per_request_price": null, "unit_prices": { "input_token": 4e-08 } }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "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": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "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" } ] }, { "dimensions": { "native_endpoint": "rerank", "quoted_unit": "/ 1K tokens" }, "label": "Ultra", "units": [ { "amount": "0.00004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.00000004", "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" } ] } ], "request_model_id": "voyageai/rerank-3-lite", "route_label": "Ultra", "status_reads": [], "tiers": [], "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "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": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "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" }, { "amount": "0.00004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.00000004", "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" } ] } } ], "model_id": "voyageai/rerank-3-lite", "nativeProvenance": { "input_facts_canonical_sha256": "21de89282331f3cb7bdd62b0760b3d7ff099c48ada4f93b26b02049dc5d6f563", "input_html_sha256": "b65c2f350bd3d3331b44b7d319790a0f1d1b53457918992f4ab4c63beb9d985a", "private_audit_sha256": "b39550f49484304095dd290fd7edba2b66cb5601fc16a2173309619fb58c41c6", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/ms/voyageai-rerank-3-lite/", "description": "Voyage rerank-3-lite memberi skor dan menyusun semula dokumen teks calon untuk pertanyaan, dengan tumpuan pada carian yang responsif. Ia menyokong arahan kerelevanan dan tetingkap pertanyaan-dokumen 32,000 token, menjadikannya berguna selepas pemerolehan maklumat berasaskan vektor atau kata kunci dalam aliran kerja carian dan RAG.", "locale": "ms", "md_url": "https://ailoot.ai/models/ms/voyageai-rerank-3-lite/index.md", "title": "VoyageAI by MongoDB: rerank-3-lite — Ailoot", "url": "https://ailoot.ai/models/ms/voyageai-rerank-3-lite/" }, "rawModel": { "about": "Voyage rerank-3-lite ialah edisi siri Rerank 3 Voyage yang memfokuskan kependaman. Ia menerima pertanyaan teks dan dokumen calon, menilai setiap pasangan pertanyaan-dokumen bersama-sama, serta mengembalikan skor kerelevanan mengikut kedudukan. Ia berfungsi pada peringkat kedua carian: alat pemerolehan berasaskan pembenaman atau kata kunci mencari calon, kemudian Lite memperhalusi susunannya. Hasilnya ialah pemeringkatan untuk digunakan dalam carian atau aliran kerja penjanaan diperkaya pemerolehan maklumat.\n\nPerubahan dalam Rerank 3 Lite\nPengeluar menekankan pemerolehan dokumen panjang dan kod yang lebih kukuh berbanding rerank-2.5-lite. Kedua-dua edisi Rerank 3 mengekalkan pematuhan arahan dan kelas konteks 32K yang sama, manakala Lite direka untuk aplikasi yang sensitif terhadap kependaman. Ini menjadikannya calon praktikal untuk carian pangkalan pengetahuan interaktif, pemerolehan dokumen sokongan dan carian kod apabila pengguna memerlukan hasil berkaitan dengan segera. Pilih berdasarkan keperluan kualiti dan masa respons koleksi sebenar, tanpa menganggap edisi lebih kecil bermakna tetingkap konteks lebih kecil.\n\nPandu kerelevanan melalui pertanyaan\nArahan bahasa semula jadi boleh disertakan bersama pertanyaan untuk menerangkan perkara yang dianggap relevan. Pastikan soalan dan keutamaan kerelevanan ringkas serta konsisten. Untuk carian sokongan perisian, gunakan “Cari prosedur untuk menetapkan semula peranti; utamakan arahan bagi versi perkakasan yang dinyatakan.” Untuk nama produk yang kabur, sertakan kategori produk supaya makna yang tidak berkaitan tidak mendominasi. Keutamaan dalam pertanyaan memandu penskoran semantik; gunakan metadata koleksi yang jelas untuk memilih produk, versi dokumen atau skop akses yang betul sebelum membina senarai calon.\n\nSediakan senarai pendek calon teks\nDokumen input ialah rentetan. Ekstrak teks yang boleh dibaca daripada bahan sumber dan kekalkan tajuk, pengepala, pengecam serta konteks sekeliling yang berguna. Kekalkan pemetaan stabil daripada setiap kedudukan input kepada rekod asal. Untuk artikel penyelesaian masalah, sertakan gejala dan prosedur berkaitan, bukan hanya ayat yang terpisah. Untuk carian kod sumber, sertakan fungsi dan maklumat berhampiran yang diperlukan untuk membezakannya daripada fungsi bernama serupa. Buang navigasi atau teks templat berulang apabila ia mengambil ruang petikan yang berguna.\n\nPemeringkat semula hanya boleh menyusun semula dokumen yang diterimanya. Jika carian pertama tidak pernah memperoleh artikel berkaitan, peringkat ini tidak boleh mendapatkan kembali calon yang tiada itu. Periksa senarai pendek dan susunan akhir apabila hasil kelihatan salah. Apabila dokumen panjang meliputi banyak topik, asingkan bahagian yang koheren dan kekalkan rujukan dokumen induknya supaya bahagian berkaitan boleh dipilih tanpa kehilangan sumbernya.\n\nHad konteks dan permintaan\nPanduan semasa pengeluar menyatakan maksimum pertanyaan 8,000 token dan maksimum gabungan 32,000 token bagi pertanyaan bersama setiap dokumen individu. Ia membenarkan sehingga 1,000 dokumen calon dan jumlah belanjawan permintaan 600,000 token, dikira sebagai token pertanyaan didarab bilangan dokumen, ditambah semua token dokumen. Oleh itu, pertanyaan panjang menggunakan ruang dalam setiap pasangan dan menyumbang berulang kali kepada jumlah belanjawan. Kira teks yang dihantar dengan pentoken model yang sesuai tanpa menganggap aksara, perkataan dan token boleh saling menggantikan.\n\nContohnya, pertanyaan 500 token dengan 100 dokumen yang masing-masing mengandungi 4,000 token bersamaan 450,000 token input mengikut formula itu. Ini menggambarkan perancangan belanjawan, bukannya saiz senarai pendek yang disyorkan atau hasil kelajuan yang diukur. Pilihan pemangkasan yang didokumenkan diaktifkan secara lalai; teks yang terlalu besar boleh dipendekkan sebelum penskoran. Sediakan bahagian penting dengan sengaja supaya pemangkasan tidak membuang petikan yang perlu dipadankan.\n\nBaca dan gunakan hasil\nHasil disusun daripada skor kerelevanan tertinggi ke bawah. Setiap hasil mengenal pasti kedudukan input asal dokumen, membolehkan aplikasi melampirkan tajuk, pengecam rekod dan sumbernya sendiri. Tetapan top_k mengawal bilangan calon berperingkat yang dikembalikan; tanpanya, semua calon dikembalikan. Antara muka REST pengeluar juga boleh mengembalikan teks dokumen. Kekalkan pengecam asal bersama hasil yang dipilih apabila memaparkan halaman carian atau meneruskan bukti ke langkah penjanaan jawapan.\n\nSkor kerelevanan menyatakan sejauh mana calon sepadan dengan pertanyaan; ia tidak membuktikan bahawa pernyataan calon adalah benar. Bandingkan item berkedudukan tertinggi dengan soalan sebenar pengguna, termasuk pengecualian dan perbezaan versi dokumen. Jika setiap calon tidak relevan, item berkedudukan tertinggi tetap wujud. Tentukan cara aplikasi anda mengendalikan keadaan itu menggunakan pertanyaan yang mewakili koleksi.\n\nMenaik taraf dan memilih edisi\nPengeluar menerangkan rerank-3-lite sebagai naik taraf kepada rerank-2.5-lite dengan semantik API yang tidak berubah dan skor yang ditentukur kepada taburan pendahulunya yang sepadan. Kekalkan pemetaan rekod dan peringkat pemerolehan maklumat sedia ada, kemudian bandingkan susunan yang terhasil pada pertanyaan bermakna sebelum bergantung pada ambang skor yang telah ditetapkan. Gunakan Lite untuk pengalaman carian yang mementingkan masa respons; gunakan edisi rerank-3 yang memfokuskan kualiti sebagai perbandingan apabila kerelevanan calon yang sukar menjadi keutamaan lebih besar.", "alias_of": null, "aliases": [], "author": "VoyageAI by MongoDB", "available": null, "canonical_model": "voyageai/rerank-3-lite", "capabilities": { "context_length": 32000, "manufacturer_input": [ "text" ], "manufacturer_output": [ "rerank" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.00004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.00000004", "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" } ], "summary": "Maklumat lengkap tentang harga konfigurasi terdapat dalam butiran." } ], "ctx": null, "entity_type": "model", "formats": [ "rerank" ], "id": "voyageai/rerank-3-lite", "input": [ "text" ], "kind": "rerank", "max_out": null, "methods": [ { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Every actual result index, finite relevance_score and original document object is retained. Indices bind the original document array. Entire original JSON is stored and returned only after settlement.", "errors": [ { "code": null, "condition": "Medan wajib, bentuk perwakilan atau nilai tidak sah", "http_status": 400, "recovery": "Betulkan medan permintaan yang dinyatakan.", "type": "invalid_request_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "cancel": null, "idempotency_header": null, "job_retrieve": null, "mode": "synchronous", "streaming": false, "unknown": "Simpan operasi asal dan balasan penuh/separa; jangan ulang POST." }, "material_combinations": [ { "accepted": [ "string documents", "objects with text; image only for separately exact-supported multimodal model" ], "mode": "text_rerank", "required": [ "query", "documents array with minItems1" ] } ], "operation_modes": [ "rerank" ], "outputs": { "all_results": "Setiap indeks hasil sebenar, relevance_score terhingga dan objek dokumen asal dikekalkan. Indeks mengikat tatasusunan dokumen asal. Keseluruhan JSON asal disimpan dan hanya dikembalikan selepas penyelesaian caj.", "family": "rerank", "fields": [ { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "id", "type": "string" }, { "description": null, "name": "provider", "type": "string" }, { "description": null, "name": "results[].index", "type": "integer" }, { "description": null, "name": "results[].relevance_score", "type": "number" }, { "description": null, "name": "results[].document.text", "type": "string" }, { "description": null, "name": "results[].document.image", "type": "string" }, { "description": null, "name": "usage.search_units", "type": "integer" }, { "description": null, "name": "usage.total_tokens", "type": "integer" }, { "description": null, "name": "usage.cost", "type": "number" } ], "format": "json", "schema": { "description": "Rerank response containing ranked results", "example": { "id": "gen-rerank-1234567890-abc", "model": "cohere/rerank-v3.5", "results": [ { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 } ], "usage": { "search_units": 1, "total_tokens": 150 } }, "properties": { "id": { "description": "Unique identifier for the rerank response (ORID format)", "example": "gen-rerank-1234567890-abc", "type": "string" }, "model": { "description": "The model used for reranking", "example": "cohere/rerank-v3.5", "type": "string" }, "provider": { "description": "The provider that served the rerank request", "example": "Cohere", "type": "string" }, "results": { "description": "List of rerank results sorted by relevance", "example": [ { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 } ], "items": { "description": "A single rerank result", "example": { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 }, "properties": { "document": { "description": "The document object echoing the original input (text and/or image)", "properties": { "image": { "description": "The image (URL or data URI) from the original document", "example": "https://example.com/image.png", "type": "string" }, "text": { "description": "The document text", "example": "Paris is the capital of France.", "type": "string" } }, "type": "object" }, "index": { "description": "Index of the document in the original input list", "example": 0, "type": "integer" }, "relevance_score": { "description": "Relevance score of the document to the query", "example": 0.98, "format": "double", "type": "number" } }, "required": [ "index", "relevance_score", "document" ], "type": "object" }, "type": "array" }, "usage": { "description": "Usage statistics", "example": { "search_units": 1, "total_tokens": 150 }, "properties": { "cost": { "description": "Cost of the request in credits", "example": 0.001, "format": "double", "type": "number" }, "search_units": { "description": "Number of search units consumed (Cohere billing)", "example": 1, "type": "integer" }, "total_tokens": { "description": "Total number of tokens used", "example": 150, "type": "integer" } }, "type": "object" } }, "required": [ "model", "results" ], "type": "object" } }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "description": "The list of documents to rerank. Documents may be plain strings, or structured objects with `text` and/or `image` for multimodal models.", "enum": null, "enum_known": false, "minItems": 1, "name": "documents", "required": true, "type": "array" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "voyageai/rerank-3-lite" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "provider", "required": false, "type": "schema" }, { "availability": "source_interface", "default": null, "default_known": false, "description": "The search query to rerank documents against", "enum": null, "enum_known": false, "name": "query", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "description": "A unique identifier for grouping related requests (e.g., a conversation or agent workflow). Used for observability grouping in Broadcast and private logging; never sent to the provider. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters.", "enum": null, "enum_known": false, "maxLength": 256, "name": "session_id", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "description": "Number of most relevant documents to return", "enum": null, "enum_known": false, "minimum": 1, "name": "top_n", "required": false, "type": "integer" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "trace", "required": false, "type": "schema" }, { "availability": "source_interface", "default": null, "default_known": false, "description": "A unique identifier representing your end-user. Forwarded to Broadcast and private logging as the end-user id; never sent to the provider.", "enum": null, "enum_known": false, "maxLength": 256, "name": "user", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "documents[].text", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "description": "Official family image carrier is remote http/https URL or data:image URI; only for exact multimodal-model bindings.", "enum": null, "enum_known": false, "name": "documents[].image", "required": false, "type": "string" } ], "unsupported": [ "stream=true" ] }, "hints": [ "Hantar ID model yang tepat dan simpan respons natif yang lengkap." ], "input": { "content_type": "application/json", "material_types": [ "text" ], "multimodal_input_binding": null, "optional_controls": [ "provider", "session_id", "top_n", "trace", "user" ], "required": [ "model", "query", "documents" ] }, "lifecycle": { "cancel": null, "idempotency_header": null, "job_retrieve": null, "mode": "synchronous", "streaming": false, "unknown": "Preserve original operation and full/partial reply; do not replay POST." }, "manufacturer_capability": { "context_length": 32000, "manufacturer_input": [ "text" ], "manufacturer_output": [ "rerank" ] }, "method": { "http": "POST", "path": "/v1/rerank" }, "method_aliases": [], "operation_modes": [ "rerank" ], "output": { "all_results": "Every actual result index, finite relevance_score and original document object is retained. Indices bind the original document array. Entire original JSON is stored and returned only after settlement.", "family": "rerank", "fields": [ { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "id", "type": "string" }, { "description": null, "name": "provider", "type": "string" }, { "description": null, "name": "results[].index", "type": "integer" }, { "description": null, "name": "results[].relevance_score", "type": "number" }, { "description": null, "name": "results[].document.text", "type": "string" }, { "description": null, "name": "results[].document.image", "type": "string" }, { "description": null, "name": "usage.search_units", "type": "integer" }, { "description": null, "name": "usage.total_tokens", "type": "integer" }, { "description": null, "name": "usage.cost", "type": "number" } ], "format": "json", "schema": { "description": "Rerank response containing ranked results", "example": { "id": "gen-rerank-1234567890-abc", "model": "cohere/rerank-v3.5", "results": [ { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 } ], "usage": { "search_units": 1, "total_tokens": 150 } }, "properties": { "id": { "description": "Unique identifier for the rerank response (ORID format)", "example": "gen-rerank-1234567890-abc", "type": "string" }, "model": { "description": "The model used for reranking", "example": "cohere/rerank-v3.5", "type": "string" }, "provider": { "description": "The provider that served the rerank request", "example": "Cohere", "type": "string" }, "results": { "description": "List of rerank results sorted by relevance", "example": [ { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 } ], "items": { "description": "A single rerank result", "example": { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 }, "properties": { "document": { "description": "The document object echoing the original input (text and/or image)", "properties": { "image": { "description": "The image (URL or data URI) from the original document", "example": "https://example.com/image.png", "type": "string" }, "text": { "description": "The document text", "example": "Paris is the capital of France.", "type": "string" } }, "type": "object" }, "index": { "description": "Index of the document in the original input list", "example": 0, "type": "integer" }, "relevance_score": { "description": "Relevance score of the document to the query", "example": 0.98, "format": "double", "type": "number" } }, "required": [ "index", "relevance_score", "document" ], "type": "object" }, "type": "array" }, "usage": { "description": "Usage statistics", "example": { "search_units": 1, "total_tokens": 150 }, "properties": { "cost": { "description": "Cost of the request in credits", "example": 0.001, "format": "double", "type": "number" }, "search_units": { "description": "Number of search units consumed (Cohere billing)", "example": 1, "type": "integer" }, "total_tokens": { "description": "Total number of tokens used", "example": 150, "type": "integer" } }, "type": "object" } }, "required": [ "model", "results" ], "type": "object" } }, "schema": { "request": { "description": "Rerank request input", "example": { "documents": [ "Paris is the capital of France.", "Berlin is the capital of Germany." ], "model": "cohere/rerank-v3.5", "query": "What is the capital of France?", "top_n": 3 }, "properties": { "documents": { "description": "The list of documents to rerank. Documents may be plain strings, or structured objects with `text` and/or `image` for multimodal models.", "example": [ "Paris is the capital of France.", "Berlin is the capital of Germany." ], "items": { "anyOf": [ { "type": "string" }, { "description": "A structured document with optional text and/or image content. At least one of `text` or `image` must be provided.", "properties": { "image": { "description": "An image associated with the document, as a remote URL (http/https) or a base64-encoded data URI (data:image/...).", "example": "https://upload.wikimedia.org/wikipedia/commons/thumb/8/8b/Phytogenic.png", "type": "string" }, "text": { "description": "The document text", "example": "AI enables robots to perceive, plan, and act autonomously.", "type": "string" } }, "type": "object" } ], "description": "A document to rerank. Either a plain string, or a structured object with optional `text` and/or `image`." }, "minItems": 1, "type": "array" }, "model": { "enum": [ "voyageai/rerank-3-lite" ], "type": "string" }, "provider": { "allOf": [ { "$ref": "#/components/schemas/ProviderPreferences" }, { "description": "Provider routing preferences for the request." } ] }, "query": { "description": "The search query to rerank documents against", "example": "What is the capital of France?", "type": "string" }, "session_id": { "description": "A unique identifier for grouping related requests (e.g., a conversation or agent workflow). Used for observability grouping in Broadcast and private logging; never sent to the provider. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters.", "example": "session-1234", "maxLength": 256, "type": "string" }, "top_n": { "description": "Number of most relevant documents to return", "example": 3, "minimum": 1, "type": "integer" }, "trace": { "$ref": "#/components/schemas/TraceConfig" }, "user": { "description": "A unique identifier representing your end-user. Forwarded to Broadcast and private logging as the end-user id; never sent to the provider.", "example": "user-1234", "maxLength": 256, "type": "string" } }, "required": [ "model", "query", "documents" ], "type": "object" }, "response": { "description": "Rerank response containing ranked results", "example": { "id": "gen-rerank-1234567890-abc", "model": "cohere/rerank-v3.5", "results": [ { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 } ], "usage": { "search_units": 1, "total_tokens": 150 } }, "properties": { "id": { "description": "Unique identifier for the rerank response (ORID format)", "example": "gen-rerank-1234567890-abc", "type": "string" }, "model": { "description": "The model used for reranking", "example": "cohere/rerank-v3.5", "type": "string" }, "provider": { "description": "The provider that served the rerank request", "example": "Cohere", "type": "string" }, "results": { "description": "List of rerank results sorted by relevance", "example": [ { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 } ], "items": { "description": "A single rerank result", "example": { "document": { "text": "Paris is the capital of France." }, "index": 0, "relevance_score": 0.98 }, "properties": { "document": { "description": "The document object echoing the original input (text and/or image)", "properties": { "image": { "description": "The image (URL or data URI) from the original document", "example": "https://example.com/image.png", "type": "string" }, "text": { "description": "The document text", "example": "Paris is the capital of France.", "type": "string" } }, "type": "object" }, "index": { "description": "Index of the document in the original input list", "example": 0, "type": "integer" }, "relevance_score": { "description": "Relevance score of the document to the query", "example": 0.98, "format": "double", "type": "number" } }, "required": [ "index", "relevance_score", "document" ], "type": "object" }, "type": "array" }, "usage": { "description": "Usage statistics", "example": { "search_units": 1, "total_tokens": 150 }, "properties": { "cost": { "description": "Cost of the request in credits", "example": 0.001, "format": "double", "type": "number" }, "search_units": { "description": "Number of search units consumed (Cohere billing)", "example": 1, "type": "integer" }, "total_tokens": { "description": "Total number of tokens used", "example": 150, "type": "integer" } }, "type": "object" } }, "required": [ "model", "results" ], "type": "object" } } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "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": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "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" } ] }, { "dimensions": { "native_endpoint": "rerank", "quoted_unit": "/ 1K tokens" }, "label": "Ultra", "units": [ { "amount": "0.00004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.00000004", "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" } ] } ], "examples": [ { "code": "{\n \"documents\": [\n \"Paris is the capital of France.\",\n \"Berlin is the capital of Germany.\"\n ],\n \"model\": \"voyageai/rerank-3-lite\",\n \"query\": \"What is the capital of France?\",\n \"top_n\": 3\n}", "label": "Retained official request structure; documentary example", "language": "json" }, { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_REQUEST_FILE:?Set your actual JSON request file}\"\nexport AILOOT_REQUEST_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads(Path(os.environ['AILOOT_REQUEST_FILE']).read_text(encoding='utf-8'))\nif not isinstance(p,dict): raise SystemExit('Request must be a JSON object')\np['model']='voyageai/rerank-3-lite'\nPath('request.json').write_text(json.dumps(p,ensure_ascii=False),encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/rerank \\\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\nprint(json.dumps(json.loads(Path('result.json').read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n", "label": "Use your actual request material and retain the complete result", "language": "bash", "material_policy": "Use real owner-supplied state/questions or query/documents. No invented file ID, document, image URL, job ID or returned result." } ], "family": "rerank", "fast_multiplier": null, "flex_multiplier": null, "fmt": "rerank", "http": "POST", "in": null, "input": [ "text" ], "label": "Pemeringkatan semula", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "native_endpoint": "rerank", "out": null, "output": [ "rerank" ], "path": "/v1/rerank", "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": "per_request", "image_input_price": null, "image_output_price": null, "per_request_price": null, "unit_prices": { "input_token": 4e-08 } }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "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": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "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" } ] }, { "dimensions": { "native_endpoint": "rerank", "quoted_unit": "/ 1K tokens" }, "label": "Ultra", "units": [ { "amount": "0.00004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.00000004", "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" } ] } ], "request_model_id": "voyageai/rerank-3-lite", "route_label": "Ultra", "status_reads": [], "tiers": [], "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "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": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "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" }, { "amount": "0.00004000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.00000004", "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" } ] } ], "model_aliases": [ { "canonical_model_id": "voyageai/rerank-3-lite", "request_model_id": "voyageai/rerank-3-lite", "route_label": "Ultra" } ], "name": "VoyageAI by MongoDB: rerank-3-lite", "price": { "in": null, "in_label": null, "out": null, "out_label": null, "sort_in": null, "sort_out": null, "varies": true }, "public_id": "voyageai/rerank-3-lite", "short": "Voyage rerank-3-lite memberi skor dan menyusun semula dokumen teks calon untuk pertanyaan, dengan tumpuan pada carian yang responsif. Ia menyokong arahan kerelevanan dan tetingkap pertanyaan-dokumen 32,000 token, menjadikannya berguna selepas pemerolehan maklumat berasaskan vektor atau kata kunci dalam aliran kerja carian dan RAG." }, "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": "Voyage rerank-3-lite memberi skor dan menyusun semula dokumen teks calon untuk pertanyaan, dengan tumpuan pada carian yang responsif. Ia menyokong arahan kerelevanan dan tetingkap pertanyaan-dokumen 32,000 token, menjadikannya berguna selepas pemerolehan maklumat berasaskan vektor atau kata kunci dalam aliran kerja carian dan RAG.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "aba8587fc00c8c7a3e1623c7649868971f2485c9845c017bf02561a0bb63f1de", "renderer_sha256": "1dab5ba62521e9568c8b7c82005622cabbf330a075df7cce1f83274a04009460" }, "sourceRevision": "747960d5b853e1bc89bb340277d94b0938b2bba8dadc1adce4657d4f8fd2507c" }