{ "aboutHtml": "

Tev1 4B Experimental ialah model pengelasan Together AI untuk soalan dengan set jawapan tetap. Pengeluar memperhalus model ini daripada Qwen3.5 4B dan melaporkan 4.7 bilion parameter. Model menggunakan penjanaan teks tanpa mod pemikiran untuk memilih satu pilihan: input yang didokumenkan ialah keadaan, satu soalan dan pilihan berlabel, manakala output yang diminta ialah tepat satu huruf. Aplikasi memetakan huruf itu kepada kunci semantik pilihan. Ini membezakan aliran kerja keputusannya daripada model yang terus mengembalikan kebarangkalian terkalibrasi atau skor jangkaan berdasarkan rubrik.

Keadaan, soalan dan 2–24 pilihan

Antara muka pengeluar mewakili keputusan sebagai objek JSON dengan state, question dan options. Setiap pilihan mengandungi label huruf daripada A hingga X, kunci semantik dan penerangan. Berikan antara dua hingga 24 pilihan dan pastikan setiap penerangan menjelaskan bila jawapan itu terpakai. Huruf ialah label output yang ringkas; kunci semantik ialah makna yang digunakan oleh perisian di sekelilingnya. Kekalkan pemetaan itu bersama senarai pilihan tepat yang digunakan untuk keputusan tersebut.

Bagi mesej sokongan, keadaan perlu mengandungi mesej dan konteks berkaitan, manakala soalan menetapkan niat atau destinasi yang perlu dipilih. Senarai contoh boleh membezakan kegagalan integrasi yang dilaporkan, masalah akses dan permintaan maklumat produk, dengan pilihan none apabila niat yang disenaraikan tidak sesuai. Takrifkan kes yang bertindih dan jangan mengharapkan model menyimpulkan dasar penghalaan organisasi daripada label yang disingkatkan.

Penjanaan tanpa pemikiran dan bentuk jawapan yang diminta

Contoh yang diterbitkan Together menyediakan arahan sistem yang menganggap kandungan dalam state sebagai data, memilih satu pilihan yang disenaraikan dan meminta hurufnya sahaja tanpa penjelasan. Tetapan yang disyorkan ialah temperature 0, peruntukan penjanaan lapan token dan pemikiran dinyahdayakan. Pembuat menyatakan secara jelas bahawa tetapan ini tidak dimasukkan secara automatik oleh endpoint awam; fungsi pembantu contoh membekalkannya, manakala permintaan langsung mesti menetapkannya sendiri. Gunakan tetapan ini untuk meminta respons pengelasan pendek tanpa pemikiran seperti yang dimaksudkan.

Peruntukan lapan token ialah tetapan output contoh untuk aliran kerja jawapan pendek ini, bukan spesifikasi maksimum output sejagat. Output berguna yang dimaksudkan tetap huruf yang dipilih. Jika fungsi pembantu kemudian memaparkan objek label dan kunci, bezakan objek yang ditafsirkan itu daripada kandungan mentah yang dijana model. Pemilihan kategori tidak dengan sendirinya mengemas kini tiket, meluluskan operasi atau melaksanakan tindakan seterusnya.

Pengelasan, peraturan dan penarafan kategori

Pembuat menerangkan pengesanan niat, penerapan dasar, penghalaan aliran kerja, kategori dokumen, sentimen dan pemahaman ya/tidak berdasarkan petikan sebagai corak tugas yang disokong. Tugas boolean boleh menyediakan dua pilihan dengan kunci yang bermaksud true dan false; aplikasi mentafsir pilihan terpilih berdasarkan makna tersebut. Tugas sentimen boleh menyediakan tahap yang diterangkan dan mengembalikan kunci bagi satu kategori terpilih. Pilihan kategori itu bukan purata berwajaran kebarangkalian merentas tahap, dan huruf yang dikembalikan bukan nilai keyakinan berangka.

Bagi keputusan berasaskan peraturan, sertakan fakta berkaitan dan peraturan dalam tugas, bukannya meminta model mereka dasar. Contohnya, taklimat penghalaan dokumen boleh menerangkan folder yang dibenarkan dan bahan yang tergolong dalam setiap folder. Tugas taksonomi penyelidikan boleh menyediakan tajuk dan abstrak makalah bersama penerangan topik. Hasil perlu ditafsirkan berdasarkan alternatif yang diberikan, dengan bukti asal dikekalkan untuk pilihan yang kabur atau dipertikaikan.

Skop latihan dan identiti edisi

Halaman model merekodkan 37,840 contoh latihan yang meliputi implikasi logik, soalan ya/tidak berdasarkan petikan, niat perbankan, kategori berita, tahap sentimen, dasar yang dinyatakan secara programatik, penghalaan dan taksonomi makalah penyelidikan. Panduan iringan mendokumenkan penyeragaman tugas ini kepada format keputusan bersama dan penalaan halus model pengelasan. Ini menjelaskan tumpuan profil pada set jawapan terhad; ia tidak membuktikan bahawa setiap dasar, domain atau taksonomi baharu akan dikendalikan dengan betul tanpa penilaian khusus tugas.

Tev1 4B Experimental ialah model Together yang dinamakan itu, bukan profil asas umum Qwen3.5 4B dan bukan checkpoint daripada pembuat model keputusan lain. Kekalkan penyediaan output dan kontrak input edisi eksperimen ini sendiri. Kes penggunaan keputusan yang serupa atau keluarga asas yang dikenali tidak mewajarkan peminjaman sokongan imej, kalibrasi kebarangkalian, panggilan alat atau had pemprosesan soalan secara kelompok daripada model lain.

Konteks dan semakan hasil

Spesifikasi model Together melaporkan tetingkap konteks 32.8K token dan input teks dengan output teks. Konteks perlu memuatkan arahan, keadaan, soalan dan pilihan yang digunakan dalam permintaan pengelasan. Sediakan hanya bukti yang diperlukan oleh soalan, sambil mengekalkan takrif yang membezakan alternatif. Ringkaskan prompt pengelasan dengan membuang konteks yang tidak berkaitan sambil mengekalkan takrif pilihan.

Pengeluar mengenal pasti model ini sebagai keluaran eksperimen yang bertujuan dinilai pada beban kerja keputusan sebenar. Periksa bahawa respons mentah ialah salah satu label yang diberikan sebelum memetakannya kepada kunci semantik, dan bandingkan pengelasan dengan bahan berlabel yang mewakili tugas sasaran. Huruf yang sah menunjukkan pemilihan yang berbentuk betul, bukan bukti bahawa tafsirannya tepat. Simpan input, pilihan, huruf yang dikembalikan dan kunci yang dipetakan bersama-sama supaya artifak akhir boleh menyokong penghalaan, pengkategorian atau semakan dasar tanpa kehilangan cara keputusan itu ditakrifkan.

", "aboutText": "Tev1 4B Experimental ialah model pengelasan Together AI untuk soalan dengan set jawapan tetap. Pengeluar memperhalus model ini daripada Qwen3.5 4B dan melaporkan 4.7 bilion parameter. Model menggunakan penjanaan teks tanpa mod pemikiran untuk memilih satu pilihan: input yang didokumenkan ialah keadaan, satu soalan dan pilihan berlabel, manakala output yang diminta ialah tepat satu huruf. Aplikasi memetakan huruf itu kepada kunci semantik pilihan. Ini membezakan aliran kerja keputusannya daripada model yang terus mengembalikan kebarangkalian terkalibrasi atau skor jangkaan berdasarkan rubrik.\n\n### Keadaan, soalan dan 2–24 pilihan\n\nAntara muka pengeluar mewakili keputusan sebagai objek JSON dengan state, question dan options. Setiap pilihan mengandungi label huruf daripada A hingga X, kunci semantik dan penerangan. Berikan antara dua hingga 24 pilihan dan pastikan setiap penerangan menjelaskan bila jawapan itu terpakai. Huruf ialah label output yang ringkas; kunci semantik ialah makna yang digunakan oleh perisian di sekelilingnya. Kekalkan pemetaan itu bersama senarai pilihan tepat yang digunakan untuk keputusan tersebut.\n\nBagi mesej sokongan, keadaan perlu mengandungi mesej dan konteks berkaitan, manakala soalan menetapkan niat atau destinasi yang perlu dipilih. Senarai contoh boleh membezakan kegagalan integrasi yang dilaporkan, masalah akses dan permintaan maklumat produk, dengan pilihan none apabila niat yang disenaraikan tidak sesuai. Takrifkan kes yang bertindih dan jangan mengharapkan model menyimpulkan dasar penghalaan organisasi daripada label yang disingkatkan.\n\n### Penjanaan tanpa pemikiran dan bentuk jawapan yang diminta\n\nContoh yang diterbitkan Together menyediakan arahan sistem yang menganggap kandungan dalam state sebagai data, memilih satu pilihan yang disenaraikan dan meminta hurufnya sahaja tanpa penjelasan. Tetapan yang disyorkan ialah temperature 0, peruntukan penjanaan lapan token dan pemikiran dinyahdayakan. Pembuat menyatakan secara jelas bahawa tetapan ini tidak dimasukkan secara automatik oleh endpoint awam; fungsi pembantu contoh membekalkannya, manakala permintaan langsung mesti menetapkannya sendiri. Gunakan tetapan ini untuk meminta respons pengelasan pendek tanpa pemikiran seperti yang dimaksudkan.\n\nPeruntukan lapan token ialah tetapan output contoh untuk aliran kerja jawapan pendek ini, bukan spesifikasi maksimum output sejagat. Output berguna yang dimaksudkan tetap huruf yang dipilih. Jika fungsi pembantu kemudian memaparkan objek label dan kunci, bezakan objek yang ditafsirkan itu daripada kandungan mentah yang dijana model. Pemilihan kategori tidak dengan sendirinya mengemas kini tiket, meluluskan operasi atau melaksanakan tindakan seterusnya.\n\n### Pengelasan, peraturan dan penarafan kategori\n\nPembuat menerangkan pengesanan niat, penerapan dasar, penghalaan aliran kerja, kategori dokumen, sentimen dan pemahaman ya/tidak berdasarkan petikan sebagai corak tugas yang disokong. Tugas boolean boleh menyediakan dua pilihan dengan kunci yang bermaksud true dan false; aplikasi mentafsir pilihan terpilih berdasarkan makna tersebut. Tugas sentimen boleh menyediakan tahap yang diterangkan dan mengembalikan kunci bagi satu kategori terpilih. Pilihan kategori itu bukan purata berwajaran kebarangkalian merentas tahap, dan huruf yang dikembalikan bukan nilai keyakinan berangka.\n\nBagi keputusan berasaskan peraturan, sertakan fakta berkaitan dan peraturan dalam tugas, bukannya meminta model mereka dasar. Contohnya, taklimat penghalaan dokumen boleh menerangkan folder yang dibenarkan dan bahan yang tergolong dalam setiap folder. Tugas taksonomi penyelidikan boleh menyediakan tajuk dan abstrak makalah bersama penerangan topik. Hasil perlu ditafsirkan berdasarkan alternatif yang diberikan, dengan bukti asal dikekalkan untuk pilihan yang kabur atau dipertikaikan.\n\n### Skop latihan dan identiti edisi\n\nHalaman model merekodkan 37,840 contoh latihan yang meliputi implikasi logik, soalan ya/tidak berdasarkan petikan, niat perbankan, kategori berita, tahap sentimen, dasar yang dinyatakan secara programatik, penghalaan dan taksonomi makalah penyelidikan. Panduan iringan mendokumenkan penyeragaman tugas ini kepada format keputusan bersama dan penalaan halus model pengelasan. Ini menjelaskan tumpuan profil pada set jawapan terhad; ia tidak membuktikan bahawa setiap dasar, domain atau taksonomi baharu akan dikendalikan dengan betul tanpa penilaian khusus tugas.\n\nTev1 4B Experimental ialah model Together yang dinamakan itu, bukan profil asas umum Qwen3.5 4B dan bukan checkpoint daripada pembuat model keputusan lain. Kekalkan penyediaan output dan kontrak input edisi eksperimen ini sendiri. Kes penggunaan keputusan yang serupa atau keluarga asas yang dikenali tidak mewajarkan peminjaman sokongan imej, kalibrasi kebarangkalian, panggilan alat atau had pemprosesan soalan secara kelompok daripada model lain.\n\n### Konteks dan semakan hasil\n\nSpesifikasi model Together melaporkan tetingkap konteks 32.8K token dan input teks dengan output teks. Konteks perlu memuatkan arahan, keadaan, soalan dan pilihan yang digunakan dalam permintaan pengelasan. Sediakan hanya bukti yang diperlukan oleh soalan, sambil mengekalkan takrif yang membezakan alternatif. Ringkaskan prompt pengelasan dengan membuang konteks yang tidak berkaitan sambil mengekalkan takrif pilihan.\n\nPengeluar mengenal pasti model ini sebagai keluaran eksperimen yang bertujuan dinilai pada beban kerja keputusan sebenar. Periksa bahawa respons mentah ialah salah satu label yang diberikan sebelum memetakannya kepada kunci semantik, dan bandingkan pengelasan dengan bahan berlabel yang mewakili tugas sasaran. Huruf yang sah menunjukkan pemilihan yang berbentuk betul, bukan bukti bahawa tafsirannya tepat. Simpan input, pilihan, huruf yang dikembalikan dan kunci yang dipetakan bersama-sama supaya artifak akhir boleh menyokong penghalaan, pengkategorian atau semakan dasar tanpa kehilangan cara keputusan itu ditakrifkan.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "ab08601996593394bd4d004451348ca6a6c5343c82873738d4dbed55e9c7d6fb", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "ms", "methods": [ { "html": "
•

Together: Tev1 4B Experimental

Together /togethercomputer/tev1-4b-experimental

Pengenalan

Tev1 4B Experimental ialah pengelas teks Together AI untuk keputusan dengan pilihan terhad: berikan keadaan, satu soalan dan 2–24 pilihan berlabel, dan output yang didokumenkan ialah satu huruf. Aplikasi memetakan huruf itu kepada kunci kategori; output tersebut bukan taburan kebarangkalian atau respons skor jangkaan yang dihasilkan secara natif.

Input yang diterima
Teks
Hasil
decisions
Tentang model

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

Tev1 4B Experimental ialah model pengelasan Together AI untuk soalan dengan set jawapan tetap. Pengeluar memperhalus model ini daripada Qwen3.5 4B dan melaporkan 4.7 bilion parameter. Model menggunakan penjanaan teks tanpa mod pemikiran untuk memilih satu pilihan: input yang didokumenkan ialah keadaan, satu soalan dan pilihan berlabel, manakala output yang diminta ialah tepat satu huruf. Aplikasi memetakan huruf itu kepada kunci semantik pilihan. Ini membezakan aliran kerja keputusannya daripada model yang terus mengembalikan kebarangkalian terkalibrasi atau skor jangkaan berdasarkan rubrik.

Keadaan, soalan dan 2–24 pilihan

Antara muka pengeluar mewakili keputusan sebagai objek JSON dengan state, question dan options. Setiap pilihan mengandungi label huruf daripada A hingga X, kunci semantik dan penerangan. Berikan antara dua hingga 24 pilihan dan pastikan setiap penerangan menjelaskan bila jawapan itu terpakai. Huruf ialah label output yang ringkas; kunci semantik ialah makna yang digunakan oleh perisian di sekelilingnya. Kekalkan pemetaan itu bersama senarai pilihan tepat yang digunakan untuk keputusan tersebut.

Bagi mesej sokongan, keadaan perlu mengandungi mesej dan konteks berkaitan, manakala soalan menetapkan niat atau destinasi yang perlu dipilih. Senarai contoh boleh membezakan kegagalan integrasi yang dilaporkan, masalah akses dan permintaan maklumat produk, dengan pilihan none apabila niat yang disenaraikan tidak sesuai. Takrifkan kes yang bertindih dan jangan mengharapkan model menyimpulkan dasar penghalaan organisasi daripada label yang disingkatkan.

Penjanaan tanpa pemikiran dan bentuk jawapan yang diminta

Contoh yang diterbitkan Together menyediakan arahan sistem yang menganggap kandungan dalam state sebagai data, memilih satu pilihan yang disenaraikan dan meminta hurufnya sahaja tanpa penjelasan. Tetapan yang disyorkan ialah temperature 0, peruntukan penjanaan lapan token dan pemikiran dinyahdayakan. Pembuat menyatakan secara jelas bahawa tetapan ini tidak dimasukkan secara automatik oleh endpoint awam; fungsi pembantu contoh membekalkannya, manakala permintaan langsung mesti menetapkannya sendiri. Gunakan tetapan ini untuk meminta respons pengelasan pendek tanpa pemikiran seperti yang dimaksudkan.

Peruntukan lapan token ialah tetapan output contoh untuk aliran kerja jawapan pendek ini, bukan spesifikasi maksimum output sejagat. Output berguna yang dimaksudkan tetap huruf yang dipilih. Jika fungsi pembantu kemudian memaparkan objek label dan kunci, bezakan objek yang ditafsirkan itu daripada kandungan mentah yang dijana model. Pemilihan kategori tidak dengan sendirinya mengemas kini tiket, meluluskan operasi atau melaksanakan tindakan seterusnya.

Pengelasan, peraturan dan penarafan kategori

Pembuat menerangkan pengesanan niat, penerapan dasar, penghalaan aliran kerja, kategori dokumen, sentimen dan pemahaman ya/tidak berdasarkan petikan sebagai corak tugas yang disokong. Tugas boolean boleh menyediakan dua pilihan dengan kunci yang bermaksud true dan false; aplikasi mentafsir pilihan terpilih berdasarkan makna tersebut. Tugas sentimen boleh menyediakan tahap yang diterangkan dan mengembalikan kunci bagi satu kategori terpilih. Pilihan kategori itu bukan purata berwajaran kebarangkalian merentas tahap, dan huruf yang dikembalikan bukan nilai keyakinan berangka.

Bagi keputusan berasaskan peraturan, sertakan fakta berkaitan dan peraturan dalam tugas, bukannya meminta model mereka dasar. Contohnya, taklimat penghalaan dokumen boleh menerangkan folder yang dibenarkan dan bahan yang tergolong dalam setiap folder. Tugas taksonomi penyelidikan boleh menyediakan tajuk dan abstrak makalah bersama penerangan topik. Hasil perlu ditafsirkan berdasarkan alternatif yang diberikan, dengan bukti asal dikekalkan untuk pilihan yang kabur atau dipertikaikan.

Skop latihan dan identiti edisi

Halaman model merekodkan 37,840 contoh latihan yang meliputi implikasi logik, soalan ya/tidak berdasarkan petikan, niat perbankan, kategori berita, tahap sentimen, dasar yang dinyatakan secara programatik, penghalaan dan taksonomi makalah penyelidikan. Panduan iringan mendokumenkan penyeragaman tugas ini kepada format keputusan bersama dan penalaan halus model pengelasan. Ini menjelaskan tumpuan profil pada set jawapan terhad; ia tidak membuktikan bahawa setiap dasar, domain atau taksonomi baharu akan dikendalikan dengan betul tanpa penilaian khusus tugas.

Tev1 4B Experimental ialah model Together yang dinamakan itu, bukan profil asas umum Qwen3.5 4B dan bukan checkpoint daripada pembuat model keputusan lain. Kekalkan penyediaan output dan kontrak input edisi eksperimen ini sendiri. Kes penggunaan keputusan yang serupa atau keluarga asas yang dikenali tidak mewajarkan peminjaman sokongan imej, kalibrasi kebarangkalian, panggilan alat atau had pemprosesan soalan secara kelompok daripada model lain.

Konteks dan semakan hasil

Spesifikasi model Together melaporkan tetingkap konteks 32.8K token dan input teks dengan output teks. Konteks perlu memuatkan arahan, keadaan, soalan dan pilihan yang digunakan dalam permintaan pengelasan. Sediakan hanya bukti yang diperlukan oleh soalan, sambil mengekalkan takrif yang membezakan alternatif. Ringkaskan prompt pengelasan dengan membuang konteks yang tidak berkaitan sambil mengekalkan takrif pilihan.

Pengeluar mengenal pasti model ini sebagai keluaran eksperimen yang bertujuan dinilai pada beban kerja keputusan sebenar. Periksa bahawa respons mentah ialah salah satu label yang diberikan sebelum memetakannya kepada kunci semantik, dan bandingkan pengelasan dengan bahan berlabel yang mewakili tugas sasaran. Huruf yang sah menunjukkan pemilihan yang berbentuk betul, bukan bukti bahawa tafsirannya tepat. Simpan input, pilihan, huruf yang dikembalikan dan kunci yang dipetakan bersama-sama supaya artifak akhir boleh menyokong penghalaan, pengkategorian atau semakan dasar tanpa kehilangan cara keputusan itu ditakrifkan.

Tersedia di Ailoot · input & kaedah

Ailoot Ultra · System One POST /v1/systemone
Input
text
Output
decisions
Format output
json
MedanJenisKeperluanNilai & hadLalai
MedanmodelJenisstringKeperluanDiperlukanNilai & had
togethercomputer/tev1-4b-experimental
Lalai—
MedanproviderJenisschemaKeperluanPilihanNilai & hadLalai—
MedanquestionsJenisobjectKeperluanDiperlukanNilai & hadLalai—
Medansession_idJenisstringKeperluanPilihanNilai & hadLalai—
MedanstateJenisschemaKeperluanDiperlukanNilai & hadLalai—
MedantraceJenisschemaKeperluanPilihanNilai & hadLalai—
MedanuserJenisstringKeperluanPilihanNilai & hadLalai—
Medanquestions.<id>.typeJenisstringKeperluanDiperlukanNilai & had
noul, choice, score
Lalai—
Medanquestions.<id>.instructionsJenisstring|object|arrayKeperluanDiperlukanNilai & hadLalai—
Medanquestions.<id>.criteriaJenisobject|arrayKeperluanPilihanNilai & had
Syarat: choice/score: wajib; noul: pilihan. Kriteria choice ialah objek; score ialah tatasusunan dengan minItems1.
Lalai—
Medanquestions.<id>.criteria.trueJenisstring|object|arrayKeperluanDiperlukanNilai & had
Terpakai apabila: Objek kriteria noul dibekalkan
Lalai—
Medanquestions.<id>.criteria.falseJenisstring|object|arrayKeperluanDiperlukanNilai & had
Terpakai apabila: Objek kriteria noul dibekalkan
Lalai—
Gabungan bahan input

noul · Diperlukan: state, questions.<id>.type=noul, questions.<id>.instructions

choice · Diperlukan: state, questions.<id>.type=choice, questions.<id>.instructions, criteria object

score · Diperlukan: state, questions.<id>.type=score, questions.<id>.instructions, criteria array with minItems1

Parameter kaedah dan kitar hayat
ParameterKontrak
Parametercontent_typeKontrakapplication/json
ParameterrequiredKontrakmodel, state, questions
Parametermaterial_typesKontraktext
Parameteroptional_controlsKontrakprovider, session_id, 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 kadarToken konteks, melebihiToken konteks, sehingga dan termasukCaj
KonfigurasiKadar asas tokenJadual kadarKadar asasToken konteks, melebihi—Token konteks, sehingga dan termasukTiada had atasCaj
Input · Token input $0.000084 / 1K token
Output · Token output $0 / 1K token
Input · Bacaan cache — / 1K token
Input · Penulisan cache — / 1K token
Input · Penulisan cache, 1 jam — / 1K token
KonfigurasiTahap panjang permintaan 1Jadual kadar—Token konteks, melebihi0Token konteks, sehingga dan termasukTiada had atasCaj
Input · Token input $0.000084 / 1K token
Output · Token output $0 / 1K token
Input · Bacaan cache — / 1K token
Input · Penulisan cache — / 1K token
Input · Penulisan cache, 1 jam — / 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 · System One

{\n  "model": "togethercomputer/tev1-4b-experimental",\n  "questions": {\n    "is_bug": {\n      "criteria": {\n        "false": "The customer is asking a question or requesting a feature.",\n        "true": "The customer describes broken or unexpected product behavior."\n      },\n      "instructions": "Is the customer reporting a software defect?",\n      "type": "noul"\n    },\n    "team": {\n      "criteria": {\n        "account": "Login, permissions, or profile issues.",\n        "frontend": "Rendering, layout, or browser compatibility issues.",\n        "payments": "Checkout, billing, or payment processing issues."\n      },\n      "instructions": "Which team should own this ticket?",\n      "type": "choice"\n    },\n    "urgency": {\n      "criteria": [\n        "Can wait for the next release",\n        "Should be fixed this week",\n        "Blocking revenue right now"\n      ],\n      "instructions": "How urgent is this ticket?",\n      "type": "score"\n    }\n  },\n  "state": {\n    "customer_tier": "enterprise",\n    "ticket": "My checkout page shows a blank screen after I click Pay. I have tried two browsers."\n  }\n}

Terima dan simpan hasil

Ailoot Ultra · System One

json

Simpan semua hasil yang selesai

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

Setiap jawapan bagi ID soalan yang diberikan dikekalkan berserta jenis tepatnya, nilai noul/choice/score, keyakinan, kebarangkalian dan petunjuk. 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
Medananswers.<id>.typeJenisstring
Medananswers.<id>.noulJenisnumber
Medananswers.<id>.choiceJenisstring
Medananswers.<id>.scoreJenisnumber
Medananswers.<id>.confidenceJenisnumber
Medananswers.<id>.probabilitiesJenisobject
Medananswers.<id>.legendJenisobject
Medanusage.input_tokensJenisinteger
Medanusage.output_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 togethercomputer/tev1-4b-experimental

Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

ID pemanggil berkaitan

togethercomputer/tev1-4b-experimental

", "method_identity": { "effective_request_model_id": "togethercomputer/tev1-4b-experimental", "fmt": "systemone", "http": "POST", "path": "/v1/systemone", "request_model_id": "togethercomputer/tev1-4b-experimental", "route_label": "Ultra" }, "method_key": "Ultra|systemone|/v1/systemone|togethercomputer%2Ftev1-4b-experimental", "ordinal": 0, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Every supplied question-ID answer with its exact type, noul/choice/score value, confidence, probabilities and legend is retained. 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": [ { "mode": "noul", "optional": [ "criteria true/false descriptions" ], "required": [ "state", "questions..type=noul", "questions..instructions" ] }, { "mode": "choice", "required": [ "state", "questions..type=choice", "questions..instructions", "criteria object" ] }, { "mode": "score", "required": [ "state", "questions..type=score", "questions..instructions", "criteria array with minItems1" ] } ], "operation_modes": [ "noul", "choice", "score" ], "outputs": { "all_results": "Setiap jawapan bagi ID soalan yang diberikan dikekalkan berserta jenis tepatnya, nilai noul/choice/score, keyakinan, kebarangkalian dan petunjuk. Keseluruhan JSON asal disimpan dan hanya dikembalikan selepas penyelesaian caj.", "family": "decisions", "fields": [ { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "id", "type": "string" }, { "description": null, "name": "provider", "type": "string" }, { "description": null, "name": "answers..type", "type": "string" }, { "description": null, "name": "answers..noul", "type": "number" }, { "description": null, "name": "answers..choice", "type": "string" }, { "description": null, "name": "answers..score", "type": "number" }, { "description": null, "name": "answers..confidence", "type": "number" }, { "description": null, "name": "answers..probabilities", "type": "object" }, { "description": null, "name": "answers..legend", "type": "object" }, { "description": null, "name": "usage.input_tokens", "type": "integer" }, { "description": null, "name": "usage.output_tokens", "type": "integer" }, { "description": null, "name": "usage.cost", "type": "number" } ], "format": "json", "schema": { "properties": { "answers": { "additionalProperties": { "description": "A Decisions answer using a boolean, choice, or score evaluation.", "discriminator": { "mapping": { "choice": "#/components/schemas/DecisionsChoiceAnswer", "noul": "#/components/schemas/DecisionsNoulAnswer", "score": "#/components/schemas/DecisionsScoreAnswer" }, "propertyName": "type" }, "oneOf": [ { "$ref": "#/components/schemas/DecisionsNoulAnswer" }, { "$ref": "#/components/schemas/DecisionsChoiceAnswer" }, { "$ref": "#/components/schemas/DecisionsScoreAnswer" } ] }, "type": "object" }, "id": { "type": "string" }, "model": { "type": "string" }, "provider": { "type": "string" }, "usage": { "properties": { "cost": { "format": "double", "type": "number" }, "input_tokens": { "type": "integer" }, "output_tokens": { "type": "integer" } }, "required": [ "input_tokens", "output_tokens" ], "type": "object" } }, "required": [ "model", "answers", "usage" ], "type": "object" } }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "togethercomputer/tev1-4b-experimental" ], "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, "enum": null, "enum_known": false, "name": "questions", "required": true, "type": "object" }, { "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": "The content to evaluate: a plain string, or a JSON object or array of related context.", "enum": null, "enum_known": false, "name": "state", "required": true, "type": "schema" }, { "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, "enum": null, "enum_known": false, "maxLength": 256, "name": "user", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "noul", "choice", "score" ], "enum_known": true, "name": "questions..type", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "questions..instructions", "required": true, "type": "string|object|array" }, { "availability": "source_interface", "conditions": "choice/score: wajib; noul: pilihan. Kriteria choice ialah objek; score ialah tatasusunan dengan minItems1.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "questions..criteria", "required": false, "type": "object|array" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "questions..criteria.true", "required": true, "type": "string|object|array", "when": "Objek kriteria noul dibekalkan" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "questions..criteria.false", "required": true, "type": "string|object|array", "when": "Objek kriteria noul dibekalkan" } ], "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", "trace", "user" ], "required": [ "model", "state", "questions" ] }, "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": 32768, "manufacturer_input": [ "text" ], "manufacturer_output": [ "decisions" ] }, "method": { "http": "POST", "path": "/v1/systemone" }, "method_aliases": [], "operation_modes": [ "noul", "choice", "score" ], "output": { "all_results": "Every supplied question-ID answer with its exact type, noul/choice/score value, confidence, probabilities and legend is retained. Entire original JSON is stored and returned only after settlement.", "family": "decisions", "fields": [ { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "id", "type": "string" }, { "description": null, "name": "provider", "type": "string" }, { "description": null, "name": "answers..type", "type": "string" }, { "description": null, "name": "answers..noul", "type": "number" }, { "description": null, "name": "answers..choice", "type": "string" }, { "description": null, "name": "answers..score", "type": "number" }, { "description": null, "name": "answers..confidence", "type": "number" }, { "description": null, "name": "answers..probabilities", "type": "object" }, { "description": null, "name": "answers..legend", "type": "object" }, { "description": null, "name": "usage.input_tokens", "type": "integer" }, { "description": null, "name": "usage.output_tokens", "type": "integer" }, { "description": null, "name": "usage.cost", "type": "number" } ], "format": "json", "schema": { "properties": { "answers": { "additionalProperties": { "description": "A Decisions answer using a boolean, choice, or score evaluation.", "discriminator": { "mapping": { "choice": "#/components/schemas/DecisionsChoiceAnswer", "noul": "#/components/schemas/DecisionsNoulAnswer", "score": "#/components/schemas/DecisionsScoreAnswer" }, "propertyName": "type" }, "oneOf": [ { "$ref": "#/components/schemas/DecisionsNoulAnswer" }, { "$ref": "#/components/schemas/DecisionsChoiceAnswer" }, { "$ref": "#/components/schemas/DecisionsScoreAnswer" } ] }, "type": "object" }, "id": { "type": "string" }, "model": { "type": "string" }, "provider": { "type": "string" }, "usage": { "properties": { "cost": { "format": "double", "type": "number" }, "input_tokens": { "type": "integer" }, "output_tokens": { "type": "integer" } }, "required": [ "input_tokens", "output_tokens" ], "type": "object" } }, "required": [ "model", "answers", "usage" ], "type": "object" } }, "schema": { "request": { "properties": { "model": { "enum": [ "togethercomputer/tev1-4b-experimental" ], "type": "string" }, "provider": { "allOf": [ { "$ref": "#/components/schemas/ProviderPreferences" }, { "description": "Provider routing preferences for the request." } ] }, "questions": { "additionalProperties": { "description": "A Decisions question using a boolean, choice, or ordered score evaluation.", "discriminator": { "mapping": { "choice": "#/components/schemas/DecisionsChoiceQuestion", "noul": "#/components/schemas/DecisionsNoulQuestion", "score": "#/components/schemas/DecisionsScoreQuestion" }, "propertyName": "type" }, "oneOf": [ { "$ref": "#/components/schemas/DecisionsNoulQuestion" }, { "$ref": "#/components/schemas/DecisionsChoiceQuestion" }, { "$ref": "#/components/schemas/DecisionsScoreQuestion" } ] }, "type": "object" }, "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" }, "state": { "anyOf": [ { "type": "string" }, { "additionalProperties": {}, "type": "object" }, { "items": {}, "type": "array" } ], "description": "The content to evaluate: a plain string, or a JSON object or array of related context." }, "trace": { "$ref": "#/components/schemas/TraceConfig" }, "user": { "maxLength": 256, "type": "string" } }, "required": [ "model", "state", "questions" ], "type": "object" }, "response": { "properties": { "answers": { "additionalProperties": { "description": "A Decisions answer using a boolean, choice, or score evaluation.", "discriminator": { "mapping": { "choice": "#/components/schemas/DecisionsChoiceAnswer", "noul": "#/components/schemas/DecisionsNoulAnswer", "score": "#/components/schemas/DecisionsScoreAnswer" }, "propertyName": "type" }, "oneOf": [ { "$ref": "#/components/schemas/DecisionsNoulAnswer" }, { "$ref": "#/components/schemas/DecisionsChoiceAnswer" }, { "$ref": "#/components/schemas/DecisionsScoreAnswer" } ] }, "type": "object" }, "id": { "type": "string" }, "model": { "type": "string" }, "provider": { "type": "string" }, "usage": { "properties": { "cost": { "format": "double", "type": "number" }, "input_tokens": { "type": "integer" }, "output_tokens": { "type": "integer" } }, "required": [ "input_tokens", "output_tokens" ], "type": "object" } }, "required": [ "model", "answers", "usage" ], "type": "object" } } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Kadar asas token", "units": [ { "amount": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Tahap panjang permintaan 1", "units": [ { "amount": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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": "{\n \"model\": \"togethercomputer/tev1-4b-experimental\",\n \"questions\": {\n \"is_bug\": {\n \"criteria\": {\n \"false\": \"The customer is asking a question or requesting a feature.\",\n \"true\": \"The customer describes broken or unexpected product behavior.\"\n },\n \"instructions\": \"Is the customer reporting a software defect?\",\n \"type\": \"noul\"\n },\n \"team\": {\n \"criteria\": {\n \"account\": \"Login, permissions, or profile issues.\",\n \"frontend\": \"Rendering, layout, or browser compatibility issues.\",\n \"payments\": \"Checkout, billing, or payment processing issues.\"\n },\n \"instructions\": \"Which team should own this ticket?\",\n \"type\": \"choice\"\n },\n \"urgency\": {\n \"criteria\": [\n \"Can wait for the next release\",\n \"Should be fixed this week\",\n \"Blocking revenue right now\"\n ],\n \"instructions\": \"How urgent is this ticket?\",\n \"type\": \"score\"\n }\n },\n \"state\": {\n \"customer_tier\": \"enterprise\",\n \"ticket\": \"My checkout page shows a blank screen after I click Pay. I have tried two browsers.\"\n }\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']='togethercomputer/tev1-4b-experimental'\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/systemone \\\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": "systemone", "fast_multiplier": null, "flex_multiplier": null, "fmt": "systemone", "http": "POST", "in": 0.084, "input": [ "text" ], "label": "System One", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "native_endpoint": "systemone", "out": 0, "output": [ "decisions" ], "path": "/v1/systemone", "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": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Request-length tier 1", "units": [ { "amount": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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": "togethercomputer/tev1-4b-experimental", "route_label": "Ultra", "status_reads": [], "tiers": [ { "cache_read": null, "cache_read_multiplier": null, "cache_write": null, "cache_write_1h": null, "cache_write_multiplier": null, "created_at": "0001-01-01T00:00:00Z", "in": 0.084, "input_multiplier": null, "interval_boundary": "min_exclusive_max_inclusive", "max": null, "max_tokens": null, "min": 0, "min_tokens": 0, "null_rate_policy": "unknown or inherited; never zero", "out": 0, "output_multiplier": null, "per_request_price": null, "sort_order": 0, "tier_label": "", "updated_at": "0001-01-01T00:00:00Z" } ], "units": [ { "amount": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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": "togethercomputer/tev1-4b-experimental", "nativeProvenance": { "input_facts_canonical_sha256": "99897e3349561e11ad1edcc6cb2a53e9e5335888e5921934fae28db7a981a745", "input_html_sha256": "53986e35fad33e323a2fc8d2e55832048e17625909fac53a85eb515727aaa9d7", "private_audit_sha256": "afd2eaf58ae75516812bdc490f631f8edb791dfe8194ae581a512ebee1719ac6", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/ms/togethercomputer-tev1-4b-experimental/", "description": "Tev1 4B Experimental ialah pengelas teks Together AI untuk keputusan dengan pilihan terhad: berikan keadaan, satu soalan dan 2–24 pilihan berlabel, dan output yang didokumenkan ialah satu huruf. Aplikasi memetakan huruf itu kepada kunci kategori; output tersebut bukan taburan kebarangkalian atau respons skor jangkaan yang dihasilkan secara natif.", "locale": "ms", "md_url": "https://ailoot.ai/models/ms/togethercomputer-tev1-4b-experimental/index.md", "title": "Together: Tev1 4B Experimental — Ailoot", "url": "https://ailoot.ai/models/ms/togethercomputer-tev1-4b-experimental/" }, "rawModel": { "about": "Tev1 4B Experimental ialah model pengelasan Together AI untuk soalan dengan set jawapan tetap. Pengeluar memperhalus model ini daripada Qwen3.5 4B dan melaporkan 4.7 bilion parameter. Model menggunakan penjanaan teks tanpa mod pemikiran untuk memilih satu pilihan: input yang didokumenkan ialah keadaan, satu soalan dan pilihan berlabel, manakala output yang diminta ialah tepat satu huruf. Aplikasi memetakan huruf itu kepada kunci semantik pilihan. Ini membezakan aliran kerja keputusannya daripada model yang terus mengembalikan kebarangkalian terkalibrasi atau skor jangkaan berdasarkan rubrik.\n\n### Keadaan, soalan dan 2–24 pilihan\n\nAntara muka pengeluar mewakili keputusan sebagai objek JSON dengan state, question dan options. Setiap pilihan mengandungi label huruf daripada A hingga X, kunci semantik dan penerangan. Berikan antara dua hingga 24 pilihan dan pastikan setiap penerangan menjelaskan bila jawapan itu terpakai. Huruf ialah label output yang ringkas; kunci semantik ialah makna yang digunakan oleh perisian di sekelilingnya. Kekalkan pemetaan itu bersama senarai pilihan tepat yang digunakan untuk keputusan tersebut.\n\nBagi mesej sokongan, keadaan perlu mengandungi mesej dan konteks berkaitan, manakala soalan menetapkan niat atau destinasi yang perlu dipilih. Senarai contoh boleh membezakan kegagalan integrasi yang dilaporkan, masalah akses dan permintaan maklumat produk, dengan pilihan none apabila niat yang disenaraikan tidak sesuai. Takrifkan kes yang bertindih dan jangan mengharapkan model menyimpulkan dasar penghalaan organisasi daripada label yang disingkatkan.\n\n### Penjanaan tanpa pemikiran dan bentuk jawapan yang diminta\n\nContoh yang diterbitkan Together menyediakan arahan sistem yang menganggap kandungan dalam state sebagai data, memilih satu pilihan yang disenaraikan dan meminta hurufnya sahaja tanpa penjelasan. Tetapan yang disyorkan ialah temperature 0, peruntukan penjanaan lapan token dan pemikiran dinyahdayakan. Pembuat menyatakan secara jelas bahawa tetapan ini tidak dimasukkan secara automatik oleh endpoint awam; fungsi pembantu contoh membekalkannya, manakala permintaan langsung mesti menetapkannya sendiri. Gunakan tetapan ini untuk meminta respons pengelasan pendek tanpa pemikiran seperti yang dimaksudkan.\n\nPeruntukan lapan token ialah tetapan output contoh untuk aliran kerja jawapan pendek ini, bukan spesifikasi maksimum output sejagat. Output berguna yang dimaksudkan tetap huruf yang dipilih. Jika fungsi pembantu kemudian memaparkan objek label dan kunci, bezakan objek yang ditafsirkan itu daripada kandungan mentah yang dijana model. Pemilihan kategori tidak dengan sendirinya mengemas kini tiket, meluluskan operasi atau melaksanakan tindakan seterusnya.\n\n### Pengelasan, peraturan dan penarafan kategori\n\nPembuat menerangkan pengesanan niat, penerapan dasar, penghalaan aliran kerja, kategori dokumen, sentimen dan pemahaman ya/tidak berdasarkan petikan sebagai corak tugas yang disokong. Tugas boolean boleh menyediakan dua pilihan dengan kunci yang bermaksud true dan false; aplikasi mentafsir pilihan terpilih berdasarkan makna tersebut. Tugas sentimen boleh menyediakan tahap yang diterangkan dan mengembalikan kunci bagi satu kategori terpilih. Pilihan kategori itu bukan purata berwajaran kebarangkalian merentas tahap, dan huruf yang dikembalikan bukan nilai keyakinan berangka.\n\nBagi keputusan berasaskan peraturan, sertakan fakta berkaitan dan peraturan dalam tugas, bukannya meminta model mereka dasar. Contohnya, taklimat penghalaan dokumen boleh menerangkan folder yang dibenarkan dan bahan yang tergolong dalam setiap folder. Tugas taksonomi penyelidikan boleh menyediakan tajuk dan abstrak makalah bersama penerangan topik. Hasil perlu ditafsirkan berdasarkan alternatif yang diberikan, dengan bukti asal dikekalkan untuk pilihan yang kabur atau dipertikaikan.\n\n### Skop latihan dan identiti edisi\n\nHalaman model merekodkan 37,840 contoh latihan yang meliputi implikasi logik, soalan ya/tidak berdasarkan petikan, niat perbankan, kategori berita, tahap sentimen, dasar yang dinyatakan secara programatik, penghalaan dan taksonomi makalah penyelidikan. Panduan iringan mendokumenkan penyeragaman tugas ini kepada format keputusan bersama dan penalaan halus model pengelasan. Ini menjelaskan tumpuan profil pada set jawapan terhad; ia tidak membuktikan bahawa setiap dasar, domain atau taksonomi baharu akan dikendalikan dengan betul tanpa penilaian khusus tugas.\n\nTev1 4B Experimental ialah model Together yang dinamakan itu, bukan profil asas umum Qwen3.5 4B dan bukan checkpoint daripada pembuat model keputusan lain. Kekalkan penyediaan output dan kontrak input edisi eksperimen ini sendiri. Kes penggunaan keputusan yang serupa atau keluarga asas yang dikenali tidak mewajarkan peminjaman sokongan imej, kalibrasi kebarangkalian, panggilan alat atau had pemprosesan soalan secara kelompok daripada model lain.\n\n### Konteks dan semakan hasil\n\nSpesifikasi model Together melaporkan tetingkap konteks 32.8K token dan input teks dengan output teks. Konteks perlu memuatkan arahan, keadaan, soalan dan pilihan yang digunakan dalam permintaan pengelasan. Sediakan hanya bukti yang diperlukan oleh soalan, sambil mengekalkan takrif yang membezakan alternatif. Ringkaskan prompt pengelasan dengan membuang konteks yang tidak berkaitan sambil mengekalkan takrif pilihan.\n\nPengeluar mengenal pasti model ini sebagai keluaran eksperimen yang bertujuan dinilai pada beban kerja keputusan sebenar. Periksa bahawa respons mentah ialah salah satu label yang diberikan sebelum memetakannya kepada kunci semantik, dan bandingkan pengelasan dengan bahan berlabel yang mewakili tugas sasaran. Huruf yang sah menunjukkan pemilihan yang berbentuk betul, bukan bukti bahawa tafsirannya tepat. Simpan input, pilihan, huruf yang dikembalikan dan kunci yang dipetakan bersama-sama supaya artifak akhir boleh menyokong penghalaan, pengkategorian atau semakan dasar tanpa kehilangan cara keputusan itu ditakrifkan.", "alias_of": null, "aliases": [], "author": "Together", "available": null, "canonical_model": "togethercomputer/tev1-4b-experimental", "capabilities": { "context_length": 32768, "manufacturer_input": [ "text" ], "manufacturer_output": [ "decisions" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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": [ "systemone" ], "id": "togethercomputer/tev1-4b-experimental", "input": [ "text" ], "kind": "decision", "max_out": null, "methods": [ { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Every supplied question-ID answer with its exact type, noul/choice/score value, confidence, probabilities and legend is retained. 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": [ { "mode": "noul", "optional": [ "criteria true/false descriptions" ], "required": [ "state", "questions..type=noul", "questions..instructions" ] }, { "mode": "choice", "required": [ "state", "questions..type=choice", "questions..instructions", "criteria object" ] }, { "mode": "score", "required": [ "state", "questions..type=score", "questions..instructions", "criteria array with minItems1" ] } ], "operation_modes": [ "noul", "choice", "score" ], "outputs": { "all_results": "Setiap jawapan bagi ID soalan yang diberikan dikekalkan berserta jenis tepatnya, nilai noul/choice/score, keyakinan, kebarangkalian dan petunjuk. Keseluruhan JSON asal disimpan dan hanya dikembalikan selepas penyelesaian caj.", "family": "decisions", "fields": [ { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "id", "type": "string" }, { "description": null, "name": "provider", "type": "string" }, { "description": null, "name": "answers..type", "type": "string" }, { "description": null, "name": "answers..noul", "type": "number" }, { "description": null, "name": "answers..choice", "type": "string" }, { "description": null, "name": "answers..score", "type": "number" }, { "description": null, "name": "answers..confidence", "type": "number" }, { "description": null, "name": "answers..probabilities", "type": "object" }, { "description": null, "name": "answers..legend", "type": "object" }, { "description": null, "name": "usage.input_tokens", "type": "integer" }, { "description": null, "name": "usage.output_tokens", "type": "integer" }, { "description": null, "name": "usage.cost", "type": "number" } ], "format": "json", "schema": { "properties": { "answers": { "additionalProperties": { "description": "A Decisions answer using a boolean, choice, or score evaluation.", "discriminator": { "mapping": { "choice": "#/components/schemas/DecisionsChoiceAnswer", "noul": "#/components/schemas/DecisionsNoulAnswer", "score": "#/components/schemas/DecisionsScoreAnswer" }, "propertyName": "type" }, "oneOf": [ { "$ref": "#/components/schemas/DecisionsNoulAnswer" }, { "$ref": "#/components/schemas/DecisionsChoiceAnswer" }, { "$ref": "#/components/schemas/DecisionsScoreAnswer" } ] }, "type": "object" }, "id": { "type": "string" }, "model": { "type": "string" }, "provider": { "type": "string" }, "usage": { "properties": { "cost": { "format": "double", "type": "number" }, "input_tokens": { "type": "integer" }, "output_tokens": { "type": "integer" } }, "required": [ "input_tokens", "output_tokens" ], "type": "object" } }, "required": [ "model", "answers", "usage" ], "type": "object" } }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "togethercomputer/tev1-4b-experimental" ], "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, "enum": null, "enum_known": false, "name": "questions", "required": true, "type": "object" }, { "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": "The content to evaluate: a plain string, or a JSON object or array of related context.", "enum": null, "enum_known": false, "name": "state", "required": true, "type": "schema" }, { "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, "enum": null, "enum_known": false, "maxLength": 256, "name": "user", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "noul", "choice", "score" ], "enum_known": true, "name": "questions..type", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "questions..instructions", "required": true, "type": "string|object|array" }, { "availability": "source_interface", "conditions": "choice/score: wajib; noul: pilihan. Kriteria choice ialah objek; score ialah tatasusunan dengan minItems1.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "questions..criteria", "required": false, "type": "object|array" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "questions..criteria.true", "required": true, "type": "string|object|array", "when": "Objek kriteria noul dibekalkan" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "questions..criteria.false", "required": true, "type": "string|object|array", "when": "Objek kriteria noul dibekalkan" } ], "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", "trace", "user" ], "required": [ "model", "state", "questions" ] }, "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": 32768, "manufacturer_input": [ "text" ], "manufacturer_output": [ "decisions" ] }, "method": { "http": "POST", "path": "/v1/systemone" }, "method_aliases": [], "operation_modes": [ "noul", "choice", "score" ], "output": { "all_results": "Every supplied question-ID answer with its exact type, noul/choice/score value, confidence, probabilities and legend is retained. Entire original JSON is stored and returned only after settlement.", "family": "decisions", "fields": [ { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "id", "type": "string" }, { "description": null, "name": "provider", "type": "string" }, { "description": null, "name": "answers..type", "type": "string" }, { "description": null, "name": "answers..noul", "type": "number" }, { "description": null, "name": "answers..choice", "type": "string" }, { "description": null, "name": "answers..score", "type": "number" }, { "description": null, "name": "answers..confidence", "type": "number" }, { "description": null, "name": "answers..probabilities", "type": "object" }, { "description": null, "name": "answers..legend", "type": "object" }, { "description": null, "name": "usage.input_tokens", "type": "integer" }, { "description": null, "name": "usage.output_tokens", "type": "integer" }, { "description": null, "name": "usage.cost", "type": "number" } ], "format": "json", "schema": { "properties": { "answers": { "additionalProperties": { "description": "A Decisions answer using a boolean, choice, or score evaluation.", "discriminator": { "mapping": { "choice": "#/components/schemas/DecisionsChoiceAnswer", "noul": "#/components/schemas/DecisionsNoulAnswer", "score": "#/components/schemas/DecisionsScoreAnswer" }, "propertyName": "type" }, "oneOf": [ { "$ref": "#/components/schemas/DecisionsNoulAnswer" }, { "$ref": "#/components/schemas/DecisionsChoiceAnswer" }, { "$ref": "#/components/schemas/DecisionsScoreAnswer" } ] }, "type": "object" }, "id": { "type": "string" }, "model": { "type": "string" }, "provider": { "type": "string" }, "usage": { "properties": { "cost": { "format": "double", "type": "number" }, "input_tokens": { "type": "integer" }, "output_tokens": { "type": "integer" } }, "required": [ "input_tokens", "output_tokens" ], "type": "object" } }, "required": [ "model", "answers", "usage" ], "type": "object" } }, "schema": { "request": { "properties": { "model": { "enum": [ "togethercomputer/tev1-4b-experimental" ], "type": "string" }, "provider": { "allOf": [ { "$ref": "#/components/schemas/ProviderPreferences" }, { "description": "Provider routing preferences for the request." } ] }, "questions": { "additionalProperties": { "description": "A Decisions question using a boolean, choice, or ordered score evaluation.", "discriminator": { "mapping": { "choice": "#/components/schemas/DecisionsChoiceQuestion", "noul": "#/components/schemas/DecisionsNoulQuestion", "score": "#/components/schemas/DecisionsScoreQuestion" }, "propertyName": "type" }, "oneOf": [ { "$ref": "#/components/schemas/DecisionsNoulQuestion" }, { "$ref": "#/components/schemas/DecisionsChoiceQuestion" }, { "$ref": "#/components/schemas/DecisionsScoreQuestion" } ] }, "type": "object" }, "session_id": { "description": "A unique identifier for grouping related requests (e.g., a conversation or agent workflow). Used for observability grouping in Broadcast and private logging; never sent to the provider. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters.", "example": "session-1234", "maxLength": 256, "type": "string" }, "state": { "anyOf": [ { "type": "string" }, { "additionalProperties": {}, "type": "object" }, { "items": {}, "type": "array" } ], "description": "The content to evaluate: a plain string, or a JSON object or array of related context." }, "trace": { "$ref": "#/components/schemas/TraceConfig" }, "user": { "maxLength": 256, "type": "string" } }, "required": [ "model", "state", "questions" ], "type": "object" }, "response": { "properties": { "answers": { "additionalProperties": { "description": "A Decisions answer using a boolean, choice, or score evaluation.", "discriminator": { "mapping": { "choice": "#/components/schemas/DecisionsChoiceAnswer", "noul": "#/components/schemas/DecisionsNoulAnswer", "score": "#/components/schemas/DecisionsScoreAnswer" }, "propertyName": "type" }, "oneOf": [ { "$ref": "#/components/schemas/DecisionsNoulAnswer" }, { "$ref": "#/components/schemas/DecisionsChoiceAnswer" }, { "$ref": "#/components/schemas/DecisionsScoreAnswer" } ] }, "type": "object" }, "id": { "type": "string" }, "model": { "type": "string" }, "provider": { "type": "string" }, "usage": { "properties": { "cost": { "format": "double", "type": "number" }, "input_tokens": { "type": "integer" }, "output_tokens": { "type": "integer" } }, "required": [ "input_tokens", "output_tokens" ], "type": "object" } }, "required": [ "model", "answers", "usage" ], "type": "object" } } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Kadar asas token", "units": [ { "amount": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Tahap panjang permintaan 1", "units": [ { "amount": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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": "{\n \"model\": \"togethercomputer/tev1-4b-experimental\",\n \"questions\": {\n \"is_bug\": {\n \"criteria\": {\n \"false\": \"The customer is asking a question or requesting a feature.\",\n \"true\": \"The customer describes broken or unexpected product behavior.\"\n },\n \"instructions\": \"Is the customer reporting a software defect?\",\n \"type\": \"noul\"\n },\n \"team\": {\n \"criteria\": {\n \"account\": \"Login, permissions, or profile issues.\",\n \"frontend\": \"Rendering, layout, or browser compatibility issues.\",\n \"payments\": \"Checkout, billing, or payment processing issues.\"\n },\n \"instructions\": \"Which team should own this ticket?\",\n \"type\": \"choice\"\n },\n \"urgency\": {\n \"criteria\": [\n \"Can wait for the next release\",\n \"Should be fixed this week\",\n \"Blocking revenue right now\"\n ],\n \"instructions\": \"How urgent is this ticket?\",\n \"type\": \"score\"\n }\n },\n \"state\": {\n \"customer_tier\": \"enterprise\",\n \"ticket\": \"My checkout page shows a blank screen after I click Pay. I have tried two browsers.\"\n }\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']='togethercomputer/tev1-4b-experimental'\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/systemone \\\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": "systemone", "fast_multiplier": null, "flex_multiplier": null, "fmt": "systemone", "http": "POST", "in": 0.084, "input": [ "text" ], "label": "System One", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "native_endpoint": "systemone", "out": 0, "output": [ "decisions" ], "path": "/v1/systemone", "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": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Request-length tier 1", "units": [ { "amount": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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": "togethercomputer/tev1-4b-experimental", "route_label": "Ultra", "status_reads": [], "tiers": [ { "cache_read": null, "cache_read_multiplier": null, "cache_write": null, "cache_write_1h": null, "cache_write_multiplier": null, "created_at": "0001-01-01T00:00:00Z", "in": 0.084, "input_multiplier": null, "interval_boundary": "min_exclusive_max_inclusive", "max": null, "max_tokens": null, "min": 0, "min_tokens": 0, "null_rate_policy": "unknown or inherited; never zero", "out": 0, "output_multiplier": null, "per_request_price": null, "sort_order": 0, "tier_label": "", "updated_at": "0001-01-01T00:00:00Z" } ], "units": [ { "amount": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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": "togethercomputer/tev1-4b-experimental", "request_model_id": "togethercomputer/tev1-4b-experimental", "route_label": "Ultra" } ], "name": "Together: Tev1 4B Experimental", "price": { "in": 0.084, "in_label": null, "out": 0, "out_label": null, "scope_label": "Token rates", "sort_in": 0.084, "sort_out": 0, "varies": true }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "System One · Base token rates", "units": [ { "amount": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "System One · Request-length tier 1", "units": [ { "amount": "0.000084000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.000000084", "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" } ] } ], "public_id": "togethercomputer/tev1-4b-experimental", "short": "Tev1 4B Experimental ialah pengelas teks Together AI untuk keputusan dengan pilihan terhad: berikan keadaan, satu soalan dan 2–24 pilihan berlabel, dan output yang didokumenkan ialah satu huruf. Aplikasi memetakan huruf itu kepada kunci kategori; output tersebut bukan taburan kebarangkalian atau respons skor jangkaan yang dihasilkan secara natif." }, "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": "Tev1 4B Experimental ialah pengelas teks Together AI untuk keputusan dengan pilihan terhad: berikan keadaan, satu soalan dan 2–24 pilihan berlabel, dan output yang didokumenkan ialah satu huruf. Aplikasi memetakan huruf itu kepada kunci kategori; output tersebut bukan taburan kebarangkalian atau respons skor jangkaan yang dihasilkan secara natif.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "3c11dab158602d530ba47da4ee2604b8e910cf6b2f09576b9d425b2e6281b96b", "renderer_sha256": "1dab5ba62521e9568c8b7c82005622cabbf330a075df7cce1f83274a04009460" }, "sourceRevision": "0d4bbe8a451607b27c7503ba09cae8045d6c12fa3ae7d50f00a6e88cddc8f35b" }