{ "aboutHtml": "

DeepSeek V3.2 — DeepSeek kompaniyasining mulohaza va agent ishi uchun, uzun kontekstni samarali qayta ishlashga urg‘u berilgan matn modeli. Ishlab chiqaruvchi asosiy o‘zgarishlarni DeepSeek Sparse Attention, kengaytirilgan mustahkamlovchi o‘qitish tizimi va agent vazifalarini o‘qitish jarayoni atrofida tartiblaydi. U yozma savollar va kontekstni qabul qilib, javob, kod yoki vosita chaqiruvi tarkibini o‘z ichiga olishi mumkin bo‘lgan matn yaratadi. U oldingi V3.2 Exp relizidan va alohida Speciale mulohaza variantidan farq qiladi.

DeepSeek Sparse Attention yashirin diqqat arxitekturasiga indekslovchi va tokenlarni nozik darajada tanlashni qo‘shadi. Uzun ketma-ketlikda indekslovchi asosiy diqqat hisobida ishlatiladigan avvalgi token ma’lumotini tanlaydi. Hisobotda bu V3.1 Terminus modelidan arxitekturaviy o‘zgarish ekani va V3.2 Exp bilan bir xil arxitekturadan foydalanishi aytiladi. E’lon qilingan konteksti 128K token bo‘lib, katta manba materiali va davom etayotgan vazifani qo‘llab-quvvatlaydi; yaratilgan mulohaza va vositalar tarixi ham mavjud kontekstni sarflaydi.

Keyingi o‘qitish matematika, dasturlash, mantiqiy mulohaza, umumiy agent vazifalari, agent yordamidagi kodlash va qidiruvda fikrlashli hamda fikrlashsiz javoblarni qamrab oladi. Soha mutaxassislari yakuniy modelga birlashtiriladigan ma’lumotni beradi, undan keyin aralash mustahkamlovchi o‘qitish o‘tkaziladi. Oddiy savolda bevosita javob mos bo‘lishi mumkin; murakkab masalada fikrlash jarayoni yakuniy natijani ko‘rsatishdan oldin yechim ishlab chiqishi mumkin. Kerakli javob yoki yakuniy materialni oraliq mulohazadan mustaqil belgilang.

Nashrdagi muhim o‘zgarish — vositalar bilan fikrlash. Yangilangan chat formati tahlil va amalni bir-biriga aloqasiz bosqichlar deb ko‘rish o‘rniga vosita chaqirish vazifasi davomida mulohazani davom ettirishga imkon beradi. Model tanlagan amalni ilova bajarib, keyingi qadam uchun natijasini qaytaradi. Ishlab chiqaruvchining vosita konteksti qoidasida faqat vositaga oid xabarlar qo‘shilayotganida oldingi mulohaza saqlanadi; yangi foydalanuvchi xabari kelganda esa vosita chaqiruvlari va natijalarini saqlagan holda bu mulohaza chiqarib tashlanadi. Suhbat rollarini to‘g‘ri ajratish bu xatti-harakat uchun muhim.

Kod yozishda manba parchasini yoki tegishli fayllarni, kuzatilgan muammoni, kutilgan natijani va o‘zgartirish saqlashi kerak bo‘lgan shartlarni bering. Namunaviy topshiriq: “Berilgan kod va vosita natijalaridan foydalanib sababni toping, eng kichik tuzatishni taklif qiling va uni asoslovchi tekshiruv natijasi bilan yakuniy patchni qaytaring.” Qidiruv vazifasida savolni, kerakli dalillarni va tugallangan javob mezonini tavsiflang. Qidiruv va bajarish vositalari matnning o‘zi tomonidan emas, modelni o‘rab turgan ilova tomonidan beriladi.

Ishlab chiqaruvchi mahalliy foydalanishda temperature 1.0 va top-p 0.95 qiymatlarini tavsiya qiladi. V3.2 qayta ko‘rilgan vosita chaqiruvi ifodasini va maxsus xabar kodlovchisini joriy etadi. Uning developer roli ishlab chiqaruvchining qidiruv agenti shabloni uchun ajratilgan va rasmiy API bu rolni qabul qilmaydi. Etalon parser to‘g‘ri shakllangan chiqishni kutadi va noto‘g‘ri natijalarni tuzatmaydi; ilova yaratilgan maydon yoki vosita argumentlaridan foydalanganda, ular asosida amal qilishdan oldin tuzilishini tekshirishi kerak.

Texnik hisobotda uzun mulohaza yo‘llari va ortiqcha o‘zini tekshirish amaliy cheklovlar sifatida ko‘rsatilgan. Agent vazifasi asl manba materiali sig‘gan taqdirda ham 128K chegaraga yetishi mumkin, chunki vosita natijalari va takroriy mulohazalar to‘planadi. Tegishli kuzatuvlarning ixcham qaydini saqlang va yakuniy materialni aniq belgilang. Bilimga sezgir ishda o‘qitilish bilimidan har bir faktni aniqlashni kutish o‘rniga vakolatli materialni biriktiring yoki mos qidiruv vositasini bering.

DeepSeek V3.2 Speciale — alohida, katta hisoblash sarfli chuqur mulohaza varianti bo‘lib, model kartasiga ko‘ra vosita chaqirishni qo‘llab-quvvatlamaydi. Uning xususiyatlarini standart V3.2 vosita profili sifatida ishlatmaslik kerak. Xuddi shunday, keyingi V4 avlodi va tajribaviy avvalgi nashr alohida identifikatsiya hamda konfiguratsiya tanlovlariga ega. Model va topshiriq formati muhim bo‘lgan vazifalarni taqqoslashda nomlangan V3.2 nashrini saqlang.

Amaliy, manbaga asoslangan tahlilda materiallarni belgilang va farazlar hamda yetishmayotgan ma’lumotni ajratgan holda tegishli parchalar tasdiqlaydigan xulosani so‘rang. Agent uchun ruxsat etilgan funksiyalarni, kutilgan yakuniy natijani va bajarilganlik mezonini ayting. Bu modelning mulohaza va vosita jarayonini berilgan dalilga bog‘langan, tekshirish mumkin bo‘lgan matn, kod yoki tahliliy material atrofida tayyorlaydi.

", "aboutText": "DeepSeek V3.2 — DeepSeek kompaniyasining mulohaza va agent ishi uchun, uzun kontekstni samarali qayta ishlashga urg‘u berilgan matn modeli. Ishlab chiqaruvchi asosiy o‘zgarishlarni DeepSeek Sparse Attention, kengaytirilgan mustahkamlovchi o‘qitish tizimi va agent vazifalarini o‘qitish jarayoni atrofida tartiblaydi. U yozma savollar va kontekstni qabul qilib, javob, kod yoki vosita chaqiruvi tarkibini o‘z ichiga olishi mumkin bo‘lgan matn yaratadi. U oldingi V3.2 Exp relizidan va alohida Speciale mulohaza variantidan farq qiladi.\n\nDeepSeek Sparse Attention yashirin diqqat arxitekturasiga indekslovchi va tokenlarni nozik darajada tanlashni qo‘shadi. Uzun ketma-ketlikda indekslovchi asosiy diqqat hisobida ishlatiladigan avvalgi token ma’lumotini tanlaydi. Hisobotda bu V3.1 Terminus modelidan arxitekturaviy o‘zgarish ekani va V3.2 Exp bilan bir xil arxitekturadan foydalanishi aytiladi. E’lon qilingan konteksti 128K token bo‘lib, katta manba materiali va davom etayotgan vazifani qo‘llab-quvvatlaydi; yaratilgan mulohaza va vositalar tarixi ham mavjud kontekstni sarflaydi.\n\nKeyingi o‘qitish matematika, dasturlash, mantiqiy mulohaza, umumiy agent vazifalari, agent yordamidagi kodlash va qidiruvda fikrlashli hamda fikrlashsiz javoblarni qamrab oladi. Soha mutaxassislari yakuniy modelga birlashtiriladigan ma’lumotni beradi, undan keyin aralash mustahkamlovchi o‘qitish o‘tkaziladi. Oddiy savolda bevosita javob mos bo‘lishi mumkin; murakkab masalada fikrlash jarayoni yakuniy natijani ko‘rsatishdan oldin yechim ishlab chiqishi mumkin. Kerakli javob yoki yakuniy materialni oraliq mulohazadan mustaqil belgilang.\n\nNashrdagi muhim o‘zgarish — vositalar bilan fikrlash. Yangilangan chat formati tahlil va amalni bir-biriga aloqasiz bosqichlar deb ko‘rish o‘rniga vosita chaqirish vazifasi davomida mulohazani davom ettirishga imkon beradi. Model tanlagan amalni ilova bajarib, keyingi qadam uchun natijasini qaytaradi. Ishlab chiqaruvchining vosita konteksti qoidasida faqat vositaga oid xabarlar qo‘shilayotganida oldingi mulohaza saqlanadi; yangi foydalanuvchi xabari kelganda esa vosita chaqiruvlari va natijalarini saqlagan holda bu mulohaza chiqarib tashlanadi. Suhbat rollarini to‘g‘ri ajratish bu xatti-harakat uchun muhim.\n\nKod yozishda manba parchasini yoki tegishli fayllarni, kuzatilgan muammoni, kutilgan natijani va o‘zgartirish saqlashi kerak bo‘lgan shartlarni bering. Namunaviy topshiriq: “Berilgan kod va vosita natijalaridan foydalanib sababni toping, eng kichik tuzatishni taklif qiling va uni asoslovchi tekshiruv natijasi bilan yakuniy patchni qaytaring.” Qidiruv vazifasida savolni, kerakli dalillarni va tugallangan javob mezonini tavsiflang. Qidiruv va bajarish vositalari matnning o‘zi tomonidan emas, modelni o‘rab turgan ilova tomonidan beriladi.\n\nIshlab chiqaruvchi mahalliy foydalanishda temperature 1.0 va top-p 0.95 qiymatlarini tavsiya qiladi. V3.2 qayta ko‘rilgan vosita chaqiruvi ifodasini va maxsus xabar kodlovchisini joriy etadi. Uning developer roli ishlab chiqaruvchining qidiruv agenti shabloni uchun ajratilgan va rasmiy API bu rolni qabul qilmaydi. Etalon parser to‘g‘ri shakllangan chiqishni kutadi va noto‘g‘ri natijalarni tuzatmaydi; ilova yaratilgan maydon yoki vosita argumentlaridan foydalanganda, ular asosida amal qilishdan oldin tuzilishini tekshirishi kerak.\n\nTexnik hisobotda uzun mulohaza yo‘llari va ortiqcha o‘zini tekshirish amaliy cheklovlar sifatida ko‘rsatilgan. Agent vazifasi asl manba materiali sig‘gan taqdirda ham 128K chegaraga yetishi mumkin, chunki vosita natijalari va takroriy mulohazalar to‘planadi. Tegishli kuzatuvlarning ixcham qaydini saqlang va yakuniy materialni aniq belgilang. Bilimga sezgir ishda o‘qitilish bilimidan har bir faktni aniqlashni kutish o‘rniga vakolatli materialni biriktiring yoki mos qidiruv vositasini bering.\n\nDeepSeek V3.2 Speciale — alohida, katta hisoblash sarfli chuqur mulohaza varianti bo‘lib, model kartasiga ko‘ra vosita chaqirishni qo‘llab-quvvatlamaydi. Uning xususiyatlarini standart V3.2 vosita profili sifatida ishlatmaslik kerak. Xuddi shunday, keyingi V4 avlodi va tajribaviy avvalgi nashr alohida identifikatsiya hamda konfiguratsiya tanlovlariga ega. Model va topshiriq formati muhim bo‘lgan vazifalarni taqqoslashda nomlangan V3.2 nashrini saqlang.\n\nAmaliy, manbaga asoslangan tahlilda materiallarni belgilang va farazlar hamda yetishmayotgan ma’lumotni ajratgan holda tegishli parchalar tasdiqlaydigan xulosani so‘rang. Agent uchun ruxsat etilgan funksiyalarni, kutilgan yakuniy natijani va bajarilganlik mezonini ayting. Bu modelning mulohaza va vosita jarayonini berilgan dalilga bog‘langan, tekshirish mumkin bo‘lgan matn, kod yoki tahliliy material atrofida tayyorlaydi.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "737ac186ca738e793263156861ee1dfcf1452dea4cb9f52fe60c24ca88d6b76c", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "uz", "methods": [ { "html": "
DS

DeepSeek: DeepSeek V3.2

DeepSeek /deepseek-v3.2-thinking

Boshlash

DeepSeek V3.2 matnli mulohazani vosita qo‘llanilishi va uzun kontekst tahlili bilan birlashtiradi. Uning siyrak diqqat arxitekturasi va yangilangan suhbat formati kodlash, qidiruv va ko‘p bosqichli agent vazifalarini qo‘llaydi; 128K kontekst hamda alohida fikrlash va bevosita javob jarayonlari mavjud.

Qabul qilinadigan kirish ma’lumotlari
Matn
Natijalar
Matn
Model haqida

Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.

DeepSeek V3.2 — DeepSeek kompaniyasining mulohaza va agent ishi uchun, uzun kontekstni samarali qayta ishlashga urg‘u berilgan matn modeli. Ishlab chiqaruvchi asosiy o‘zgarishlarni DeepSeek Sparse Attention, kengaytirilgan mustahkamlovchi o‘qitish tizimi va agent vazifalarini o‘qitish jarayoni atrofida tartiblaydi. U yozma savollar va kontekstni qabul qilib, javob, kod yoki vosita chaqiruvi tarkibini o‘z ichiga olishi mumkin bo‘lgan matn yaratadi. U oldingi V3.2 Exp relizidan va alohida Speciale mulohaza variantidan farq qiladi.

DeepSeek Sparse Attention yashirin diqqat arxitekturasiga indekslovchi va tokenlarni nozik darajada tanlashni qo‘shadi. Uzun ketma-ketlikda indekslovchi asosiy diqqat hisobida ishlatiladigan avvalgi token ma’lumotini tanlaydi. Hisobotda bu V3.1 Terminus modelidan arxitekturaviy o‘zgarish ekani va V3.2 Exp bilan bir xil arxitekturadan foydalanishi aytiladi. E’lon qilingan konteksti 128K token bo‘lib, katta manba materiali va davom etayotgan vazifani qo‘llab-quvvatlaydi; yaratilgan mulohaza va vositalar tarixi ham mavjud kontekstni sarflaydi.

Keyingi o‘qitish matematika, dasturlash, mantiqiy mulohaza, umumiy agent vazifalari, agent yordamidagi kodlash va qidiruvda fikrlashli hamda fikrlashsiz javoblarni qamrab oladi. Soha mutaxassislari yakuniy modelga birlashtiriladigan ma’lumotni beradi, undan keyin aralash mustahkamlovchi o‘qitish o‘tkaziladi. Oddiy savolda bevosita javob mos bo‘lishi mumkin; murakkab masalada fikrlash jarayoni yakuniy natijani ko‘rsatishdan oldin yechim ishlab chiqishi mumkin. Kerakli javob yoki yakuniy materialni oraliq mulohazadan mustaqil belgilang.

Nashrdagi muhim o‘zgarish — vositalar bilan fikrlash. Yangilangan chat formati tahlil va amalni bir-biriga aloqasiz bosqichlar deb ko‘rish o‘rniga vosita chaqirish vazifasi davomida mulohazani davom ettirishga imkon beradi. Model tanlagan amalni ilova bajarib, keyingi qadam uchun natijasini qaytaradi. Ishlab chiqaruvchining vosita konteksti qoidasida faqat vositaga oid xabarlar qo‘shilayotganida oldingi mulohaza saqlanadi; yangi foydalanuvchi xabari kelganda esa vosita chaqiruvlari va natijalarini saqlagan holda bu mulohaza chiqarib tashlanadi. Suhbat rollarini to‘g‘ri ajratish bu xatti-harakat uchun muhim.

Kod yozishda manba parchasini yoki tegishli fayllarni, kuzatilgan muammoni, kutilgan natijani va o‘zgartirish saqlashi kerak bo‘lgan shartlarni bering. Namunaviy topshiriq: “Berilgan kod va vosita natijalaridan foydalanib sababni toping, eng kichik tuzatishni taklif qiling va uni asoslovchi tekshiruv natijasi bilan yakuniy patchni qaytaring.” Qidiruv vazifasida savolni, kerakli dalillarni va tugallangan javob mezonini tavsiflang. Qidiruv va bajarish vositalari matnning o‘zi tomonidan emas, modelni o‘rab turgan ilova tomonidan beriladi.

Ishlab chiqaruvchi mahalliy foydalanishda temperature 1.0 va top-p 0.95 qiymatlarini tavsiya qiladi. V3.2 qayta ko‘rilgan vosita chaqiruvi ifodasini va maxsus xabar kodlovchisini joriy etadi. Uning developer roli ishlab chiqaruvchining qidiruv agenti shabloni uchun ajratilgan va rasmiy API bu rolni qabul qilmaydi. Etalon parser to‘g‘ri shakllangan chiqishni kutadi va noto‘g‘ri natijalarni tuzatmaydi; ilova yaratilgan maydon yoki vosita argumentlaridan foydalanganda, ular asosida amal qilishdan oldin tuzilishini tekshirishi kerak.

Texnik hisobotda uzun mulohaza yo‘llari va ortiqcha o‘zini tekshirish amaliy cheklovlar sifatida ko‘rsatilgan. Agent vazifasi asl manba materiali sig‘gan taqdirda ham 128K chegaraga yetishi mumkin, chunki vosita natijalari va takroriy mulohazalar to‘planadi. Tegishli kuzatuvlarning ixcham qaydini saqlang va yakuniy materialni aniq belgilang. Bilimga sezgir ishda o‘qitilish bilimidan har bir faktni aniqlashni kutish o‘rniga vakolatli materialni biriktiring yoki mos qidiruv vositasini bering.

DeepSeek V3.2 Speciale — alohida, katta hisoblash sarfli chuqur mulohaza varianti bo‘lib, model kartasiga ko‘ra vosita chaqirishni qo‘llab-quvvatlamaydi. Uning xususiyatlarini standart V3.2 vosita profili sifatida ishlatmaslik kerak. Xuddi shunday, keyingi V4 avlodi va tajribaviy avvalgi nashr alohida identifikatsiya hamda konfiguratsiya tanlovlariga ega. Model va topshiriq formati muhim bo‘lgan vazifalarni taqqoslashda nomlangan V3.2 nashrini saqlang.

Amaliy, manbaga asoslangan tahlilda materiallarni belgilang va farazlar hamda yetishmayotgan ma’lumotni ajratgan holda tegishli parchalar tasdiqlaydigan xulosani so‘rang. Agent uchun ruxsat etilgan funksiyalarni, kutilgan yakuniy natijani va bajarilganlik mezonini ayting. Bu modelning mulohaza va vosita jarayonini berilgan dalilga bog‘langan, tekshirish mumkin bo‘lgan matn, kod yoki tahliliy material atrofida tayyorlaydi.

Ailoot da mavjud · kirish ma’lumotlari va usullar

Ailoot Ultra · OpenAI Chat POST /v1/chat/completions
Kirish
text
Chiqish
text
Chiqish formati
json yoki SSE
MaydonTurTalabQiymatlar va cheklovlarStandart
MaydonmodelTurstringTalabMajburiyQiymatlar va cheklovlar
deepseek-v3.2-thinking
Standart—
MaydonmessagesTurmessage[]TalabMajburiyQiymatlar va cheklovlar
Elementlarning eng kam soni: 1
Standart—
Maydonmessages[].roleTurstringTalabMajburiyQiymatlar va cheklovlar
Modelga bogʻliq
Standart—
Maydonmessages[].contentTurstringTalabIxtiyoriyQiymatlar va cheklovlar
Quyidagi holatda qo‘llanadi: Matnli suhbat
Standart—
MaydonstreamTurbooleanTalabIxtiyoriyQiymatlar va cheklovlarStandartfalse
Kirish materiallari birikmalari

Matn · UTF8 matni

messages[].content

Usul parametrlari va hayot sikli
ParametrParametr talablari
Parametrcontent_typeParametr talablariapplication/json
ParametrrequiredParametr talablarimodel, messages
Parametrmaterial_typesParametr talablaritext
ParametrmessagesParametr talablarirole/content tuzilishidagi xabarlar massivi
Parametrfile_materialParametr talablariHaqiqiy UTF-8 hujjati aynan matn sifatida kiritiladi; fayl IDsi faraz qilinmaydi
Parametroptional_controlsParametr talablaristream
Parametrcontrol_scopeParametr talablariMatnli suhbat; stream mantiqiy qiymat bo‘lib, standart holatda false.
Parametroutput_modalitiesParametr talablaritext
Parametrhosted_operationsParametr talablarifalse
Parametrmultimodal_input_bindingParametr talablarinull

Usul taxalluslari: /chat/completions

Hayot sikli: synchronous_or_streamed

Aniq model IDsini messages bilan yuboring.

Kontekst uzunligi chiqishning yuqori chegarasi emas.

Matn fayli aynan matnni taqdim etishi mumkin; tasvir, audio va fayl obyekti kirishlari aniq bog‘lashni talab qiladi.

Tariflar

Tarif ma’lumotlari so‘rov imkoniyatlarini qo‘shmaydi. Qo‘llab-quvvatlanadigan parametrlar tanlangan usulda ko‘rsatilgan.

Tezkor rejim
Ko‘rsatilmagan Tezkor rejim tanlanganda
Flex rejimi
Ko‘rsatilmagan flex rejimi tanlanganda
Maksimal fikrlash darajasi
Ko‘rsatilmagan Maksimal fikrlash darajasi uchun standart (default) tuzatish qo‘llanganda

Ailoot tariflari

Sozlamalar bo‘yicha narxlar

SozlamaTariflar jadvaliTo‘lov
SozlamaTokenlar uchun bazaviy tariflarTariflar jadvaliAsosiy tarifTo‘lov
Kirish · Kirish tokenlari $0.00058 / 1K token
Chiqish · Chiqish tokenlari $0.00086 / 1K token
Kirish · Keshdan o‘qish $0 / 1K token
Kirish · Keshga yozish $0 / 1K token
Kirish · Keshga yozish, 1 soat — / 1K token

Ailoot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →

So‘rov namunalari

Ailoot Ultra · OpenAI Chat

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"deepseek-v3.2-thinking","messages":[{"role":"user","content":"hello"}],"stream":false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n    if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\n

Natijalarni olish va saqlash

Ailoot Ultra · OpenAI Chat

json yoki SSE

Barcha tayyor natijalarni saqlash

Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.

Har bir javob variantini va uning kontenti, vosita chaqiruvlari hamda fikrlash ma’lumotlarini saqlang. SSEda o‘zgarish qismlarini variant va vosita indeksi bo‘yicha yig‘ing, yakuniy tugash sababi va sarf ma’lumotlarini saqlang.

Asl javobni tekshirish kerak bo‘lsa

So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.

Javob maydonlari
MaydonTur
Maydonchoices[].indexTurinteger
Maydonchoices[].message.contentTurstring|null
Maydonchoices[].message.tool_callsTurtool_call[]
Maydonchoices[].message.reasoning_contentTurstring
Maydonchoices[].message.reasoning_detailsTurobject|array
Maydonchoices[].finish_reasonTurstring|null
MaydonusageTurobject
Xatolar va keyingi qadamlar
JavobShartKeyingi qadam
Javob400 · invalid_request_errorShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘riKeyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating.

Taxalluslar

Model taxalluslari

Ailoot Ultra deepseek-v3.2-thinking

Usul yo‘llari taxalluslari

/chat/completions

Chaqirish uchun tegishli ID lar

deepseek-v3.2-thinking

", "method_identity": { "effective_request_model_id": "deepseek-v3.2-thinking", "fmt": "chat", "http": "POST", "path": "/v1/chat/completions", "request_model_id": "deepseek-v3.2-thinking", "route_label": "Ultra" }, "method_key": "Ultra|chat|/v1/chat/completions|deepseek-v3.2-thinking", "ordinal": 0, "rawMethod": { "available": null, "cache_read": 0, "cache_write": 0, "cache_write_1h": null, "contract": { "data": { "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "errors": [ { "code": null, "condition": "Majburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri", "http_status": 400, "recovery": "Yangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating.", "type": "invalid_request_error" } ], "hints": [ "Model context is not an output cap.", "Send the conversation as text messages. Stream must be a boolean; omitted stream defaults to false." ], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/chat/completions" }, "job_read": null, "mode": "synchronous_or_streamed", "unknown": "So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan." }, "material_combinations": [ { "mode": "text", "representation": "messages[].content", "required_material": "UTF8 matni" } ], "operation_modes": [ "conversation" ], "outputs": { "all_results": "Har bir javob variantini va uning kontenti, vosita chaqiruvlari hamda fikrlash ma’lumotlarini saqlang. SSEda o‘zgarish qismlarini variant va vosita indeksi bo‘yicha yig‘ing, yakuniy tugash sababi va sarf ma’lumotlarini saqlang.", "family": "text", "fields": [ { "description": null, "name": "choices[].index", "type": "integer" }, { "description": null, "name": "choices[].message.content", "type": "string|null" }, { "description": null, "name": "choices[].message.tool_calls", "type": "tool_call[]" }, { "description": null, "name": "choices[].message.reasoning_content", "type": "string" }, { "description": null, "name": "choices[].message.reasoning_details", "type": "object|array" }, { "description": null, "name": "choices[].finish_reason", "type": "string|null" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json yoki SSE" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "deepseek-v3.2-thinking" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "messages", "required": true, "type": "message[]" }, { "availability": "model_dependent", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "messages[].role", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "messages[].content", "required": false, "type": "string", "when": "Matnli suhbat" }, { "availability": "source_interface", "default": false, "default_known": true, "enum": null, "enum_known": false, "name": "stream", "required": false, "type": "boolean" } ], "profile_binding": "Text conversation at the exact model ID and method path.", "unsupported": [ "additional models/models list", "plugins", "route", "hosted tools; ordinary client function tools remain separate", "non-text output modalities", "provider.options overrides", "one-hour prompt-cache TTL" ] }, "hints": [ "Aniq model IDsini messages bilan yuboring.", "Kontekst uzunligi chiqishning yuqori chegarasi emas.", "Matn fayli aynan matnni taqdim etishi mumkin; tasvir, audio va fayl obyekti kirishlari aniq bog‘lashni talab qiladi." ], "input": { "content_type": "application/json", "control_scope": "Matnli suhbat; stream mantiqiy qiymat bo‘lib, standart holatda false.", "file_material": "Haqiqiy UTF-8 hujjati aynan matn sifatida kiritiladi; fayl IDsi faraz qilinmaydi", "hosted_operations": false, "material_types": [ "text" ], "messages": "role/content tuzilishidagi xabarlar massivi", "multimodal_input_binding": null, "optional_controls": [ "stream" ], "output_modalities": [ "text" ], "required": [ "model", "messages" ] }, "lifecycle": { "mode": "synchronous_or_streamed", "unknown": "preserve original request id; no generic chat job retrieval path" }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/chat/completions" }, "method_aliases": [ "/chat/completions" ], "operation_modes": [ "text_chat" ], "output": { "content": "choices[].message.content or stream delta", "family": "text", "format": "json or supported SSE", "tool_calls": "retain actual returned function calls" } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Tokenlar uchun bazaviy tariflar", "units": [ { "amount": "0.00058000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000058", "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": "0.00086000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.00000086", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\":\"deepseek-v3.2-thinking\",\"messages\":[{\"role\":\"user\",\"content\":\"hello\"}],\"stream\":false}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"choices\",[]):\n if x.get(\"message\",{}).get(\"content\"): print(x[\"message\"][\"content\"])\nPY_RESULT\n", "label": "curl · retained exact creation", "language": "bash" }, { "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.chat.completions.create(model=\"deepseek-v3.2-thinking\", messages=[{\"role\":\"user\",\"content\":\"hello\"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n file = Path(stem + \"-\" + label + \".\" + ext)\n file.write_bytes(raw)\n print(\"Saved\", file)\n for index, block in enumerate(data.get(\"content\") or []):\n print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get(\"choices\") or []:\n print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n for index, item in enumerate(data.get(\"output\") or []):\n print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n for ci, candidate in enumerate(data.get(\"candidates\") or []):\n for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n if blob and blob.get(\"data\"):\n mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(result.to_dict(mode=\"json\"))\n", "label": "Python SDK · all choices", "language": "python" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "chat", "hints": [ "Send exact model ID with messages.", "Context length is not an output cap.", "A text file may supply literal text; image/audio/file-object inputs need exact binding." ], "http": "POST", "in": 0.58, "input": [ "text" ], "label": "OpenAI Chat", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [ "/chat/completions" ], "out": 0.86, "output": [ "text" ], "path": "/v1/chat/completions", "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": "0.00058000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000058", "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": "0.00086000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.00000086", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "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": "deepseek-v3.2-thinking", "route_label": "Ultra", "status_reads": [], "tiers": [], "units": [ { "amount": "0.00058000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000058", "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": "0.00086000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.00000086", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "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": "deepseek-v3.2-thinking", "nativeProvenance": { "input_facts_canonical_sha256": "49a87fa60f8f5647e1c1a082fc0023584f5defd2e75e240d761be9e2ce265be9", "input_html_sha256": "11956205ebcc43780446b6f44e9f636751851fdf7755e228a2cd8bca1d2a9e2a", "private_audit_sha256": "9609365f4e9c7018ea5e8daf15ff6afd86d6ebd70d95ca4d141d083c9361b5b1", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/uz/deepseek-v3-2-thinking/", "description": "DeepSeek V3.2 matnli mulohazani vosita qo‘llanilishi va uzun kontekst tahlili bilan birlashtiradi. Uning siyrak diqqat arxitekturasi va yangilangan suhbat formati kodlash, qidiruv va ko‘p bosqichli agent vazifalarini qo‘llaydi; 128K kontekst hamda alohida fikrlash va bevosita javob jarayonlari mavjud.", "locale": "uz", "md_url": "https://ailoot.ai/models/uz/deepseek-v3-2-thinking/index.md", "title": "DeepSeek: DeepSeek V3.2 — Ailoot", "url": "https://ailoot.ai/models/uz/deepseek-v3-2-thinking/" }, "rawModel": { "about": "DeepSeek V3.2 — DeepSeek kompaniyasining mulohaza va agent ishi uchun, uzun kontekstni samarali qayta ishlashga urg‘u berilgan matn modeli. Ishlab chiqaruvchi asosiy o‘zgarishlarni DeepSeek Sparse Attention, kengaytirilgan mustahkamlovchi o‘qitish tizimi va agent vazifalarini o‘qitish jarayoni atrofida tartiblaydi. U yozma savollar va kontekstni qabul qilib, javob, kod yoki vosita chaqiruvi tarkibini o‘z ichiga olishi mumkin bo‘lgan matn yaratadi. U oldingi V3.2 Exp relizidan va alohida Speciale mulohaza variantidan farq qiladi.\n\nDeepSeek Sparse Attention yashirin diqqat arxitekturasiga indekslovchi va tokenlarni nozik darajada tanlashni qo‘shadi. Uzun ketma-ketlikda indekslovchi asosiy diqqat hisobida ishlatiladigan avvalgi token ma’lumotini tanlaydi. Hisobotda bu V3.1 Terminus modelidan arxitekturaviy o‘zgarish ekani va V3.2 Exp bilan bir xil arxitekturadan foydalanishi aytiladi. E’lon qilingan konteksti 128K token bo‘lib, katta manba materiali va davom etayotgan vazifani qo‘llab-quvvatlaydi; yaratilgan mulohaza va vositalar tarixi ham mavjud kontekstni sarflaydi.\n\nKeyingi o‘qitish matematika, dasturlash, mantiqiy mulohaza, umumiy agent vazifalari, agent yordamidagi kodlash va qidiruvda fikrlashli hamda fikrlashsiz javoblarni qamrab oladi. Soha mutaxassislari yakuniy modelga birlashtiriladigan ma’lumotni beradi, undan keyin aralash mustahkamlovchi o‘qitish o‘tkaziladi. Oddiy savolda bevosita javob mos bo‘lishi mumkin; murakkab masalada fikrlash jarayoni yakuniy natijani ko‘rsatishdan oldin yechim ishlab chiqishi mumkin. Kerakli javob yoki yakuniy materialni oraliq mulohazadan mustaqil belgilang.\n\nNashrdagi muhim o‘zgarish — vositalar bilan fikrlash. Yangilangan chat formati tahlil va amalni bir-biriga aloqasiz bosqichlar deb ko‘rish o‘rniga vosita chaqirish vazifasi davomida mulohazani davom ettirishga imkon beradi. Model tanlagan amalni ilova bajarib, keyingi qadam uchun natijasini qaytaradi. Ishlab chiqaruvchining vosita konteksti qoidasida faqat vositaga oid xabarlar qo‘shilayotganida oldingi mulohaza saqlanadi; yangi foydalanuvchi xabari kelganda esa vosita chaqiruvlari va natijalarini saqlagan holda bu mulohaza chiqarib tashlanadi. Suhbat rollarini to‘g‘ri ajratish bu xatti-harakat uchun muhim.\n\nKod yozishda manba parchasini yoki tegishli fayllarni, kuzatilgan muammoni, kutilgan natijani va o‘zgartirish saqlashi kerak bo‘lgan shartlarni bering. Namunaviy topshiriq: “Berilgan kod va vosita natijalaridan foydalanib sababni toping, eng kichik tuzatishni taklif qiling va uni asoslovchi tekshiruv natijasi bilan yakuniy patchni qaytaring.” Qidiruv vazifasida savolni, kerakli dalillarni va tugallangan javob mezonini tavsiflang. Qidiruv va bajarish vositalari matnning o‘zi tomonidan emas, modelni o‘rab turgan ilova tomonidan beriladi.\n\nIshlab chiqaruvchi mahalliy foydalanishda temperature 1.0 va top-p 0.95 qiymatlarini tavsiya qiladi. V3.2 qayta ko‘rilgan vosita chaqiruvi ifodasini va maxsus xabar kodlovchisini joriy etadi. Uning developer roli ishlab chiqaruvchining qidiruv agenti shabloni uchun ajratilgan va rasmiy API bu rolni qabul qilmaydi. Etalon parser to‘g‘ri shakllangan chiqishni kutadi va noto‘g‘ri natijalarni tuzatmaydi; ilova yaratilgan maydon yoki vosita argumentlaridan foydalanganda, ular asosida amal qilishdan oldin tuzilishini tekshirishi kerak.\n\nTexnik hisobotda uzun mulohaza yo‘llari va ortiqcha o‘zini tekshirish amaliy cheklovlar sifatida ko‘rsatilgan. Agent vazifasi asl manba materiali sig‘gan taqdirda ham 128K chegaraga yetishi mumkin, chunki vosita natijalari va takroriy mulohazalar to‘planadi. Tegishli kuzatuvlarning ixcham qaydini saqlang va yakuniy materialni aniq belgilang. Bilimga sezgir ishda o‘qitilish bilimidan har bir faktni aniqlashni kutish o‘rniga vakolatli materialni biriktiring yoki mos qidiruv vositasini bering.\n\nDeepSeek V3.2 Speciale — alohida, katta hisoblash sarfli chuqur mulohaza varianti bo‘lib, model kartasiga ko‘ra vosita chaqirishni qo‘llab-quvvatlamaydi. Uning xususiyatlarini standart V3.2 vosita profili sifatida ishlatmaslik kerak. Xuddi shunday, keyingi V4 avlodi va tajribaviy avvalgi nashr alohida identifikatsiya hamda konfiguratsiya tanlovlariga ega. Model va topshiriq formati muhim bo‘lgan vazifalarni taqqoslashda nomlangan V3.2 nashrini saqlang.\n\nAmaliy, manbaga asoslangan tahlilda materiallarni belgilang va farazlar hamda yetishmayotgan ma’lumotni ajratgan holda tegishli parchalar tasdiqlaydigan xulosani so‘rang. Agent uchun ruxsat etilgan funksiyalarni, kutilgan yakuniy natijani va bajarilganlik mezonini ayting. Bu modelning mulohaza va vosita jarayonini berilgan dalilga bog‘langan, tekshirish mumkin bo‘lgan matn, kod yoki tahliliy material atrofida tayyorlaydi.", "alias_of": null, "aliases": [], "author": "DeepSeek", "capabilities": { "context_length": 163840, "manufacturer_input": [ "text" ], "manufacturer_output": [ "text" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.00058000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000058", "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": "0.00086000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.00000086", "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": "Konfiguratsiya narxlari tafsilotlarda to‘liq ko‘rsatilgan." } ], "ctx": null, "formats": [ "chat" ], "id": "deepseek-v3.2-thinking", "input": [ "text" ], "kind": "text", "max_out": null, "methods": [ { "available": null, "cache_read": 0, "cache_write": 0, "cache_write_1h": null, "contract": { "data": { "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "errors": [ { "code": null, "condition": "Majburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri", "http_status": 400, "recovery": "Yangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating.", "type": "invalid_request_error" } ], "hints": [ "Model context is not an output cap.", "Send the conversation as text messages. Stream must be a boolean; omitted stream defaults to false." ], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/chat/completions" }, "job_read": null, "mode": "synchronous_or_streamed", "unknown": "So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan." }, "material_combinations": [ { "mode": "text", "representation": "messages[].content", "required_material": "UTF8 matni" } ], "operation_modes": [ "conversation" ], "outputs": { "all_results": "Har bir javob variantini va uning kontenti, vosita chaqiruvlari hamda fikrlash ma’lumotlarini saqlang. SSEda o‘zgarish qismlarini variant va vosita indeksi bo‘yicha yig‘ing, yakuniy tugash sababi va sarf ma’lumotlarini saqlang.", "family": "text", "fields": [ { "description": null, "name": "choices[].index", "type": "integer" }, { "description": null, "name": "choices[].message.content", "type": "string|null" }, { "description": null, "name": "choices[].message.tool_calls", "type": "tool_call[]" }, { "description": null, "name": "choices[].message.reasoning_content", "type": "string" }, { "description": null, "name": "choices[].message.reasoning_details", "type": "object|array" }, { "description": null, "name": "choices[].finish_reason", "type": "string|null" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json yoki SSE" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "deepseek-v3.2-thinking" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "messages", "required": true, "type": "message[]" }, { "availability": "model_dependent", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "messages[].role", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "messages[].content", "required": false, "type": "string", "when": "Matnli suhbat" }, { "availability": "source_interface", "default": false, "default_known": true, "enum": null, "enum_known": false, "name": "stream", "required": false, "type": "boolean" } ], "profile_binding": "Text conversation at the exact model ID and method path.", "unsupported": [ "additional models/models list", "plugins", "route", "hosted tools; ordinary client function tools remain separate", "non-text output modalities", "provider.options overrides", "one-hour prompt-cache TTL" ] }, "hints": [ "Aniq model IDsini messages bilan yuboring.", "Kontekst uzunligi chiqishning yuqori chegarasi emas.", "Matn fayli aynan matnni taqdim etishi mumkin; tasvir, audio va fayl obyekti kirishlari aniq bog‘lashni talab qiladi." ], "input": { "content_type": "application/json", "control_scope": "Matnli suhbat; stream mantiqiy qiymat bo‘lib, standart holatda false.", "file_material": "Haqiqiy UTF-8 hujjati aynan matn sifatida kiritiladi; fayl IDsi faraz qilinmaydi", "hosted_operations": false, "material_types": [ "text" ], "messages": "role/content tuzilishidagi xabarlar massivi", "multimodal_input_binding": null, "optional_controls": [ "stream" ], "output_modalities": [ "text" ], "required": [ "model", "messages" ] }, "lifecycle": { "mode": "synchronous_or_streamed", "unknown": "preserve original request id; no generic chat job retrieval path" }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/chat/completions" }, "method_aliases": [ "/chat/completions" ], "operation_modes": [ "text_chat" ], "output": { "content": "choices[].message.content or stream delta", "family": "text", "format": "json or supported SSE", "tool_calls": "retain actual returned function calls" } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Tokenlar uchun bazaviy tariflar", "units": [ { "amount": "0.00058000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000058", "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": "0.00086000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.00000086", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\":\"deepseek-v3.2-thinking\",\"messages\":[{\"role\":\"user\",\"content\":\"hello\"}],\"stream\":false}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"choices\",[]):\n if x.get(\"message\",{}).get(\"content\"): print(x[\"message\"][\"content\"])\nPY_RESULT\n", "label": "curl · retained exact creation", "language": "bash" }, { "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.chat.completions.create(model=\"deepseek-v3.2-thinking\", messages=[{\"role\":\"user\",\"content\":\"hello\"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n file = Path(stem + \"-\" + label + \".\" + ext)\n file.write_bytes(raw)\n print(\"Saved\", file)\n for index, block in enumerate(data.get(\"content\") or []):\n print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get(\"choices\") or []:\n print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n for index, item in enumerate(data.get(\"output\") or []):\n print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n for ci, candidate in enumerate(data.get(\"candidates\") or []):\n for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n if blob and blob.get(\"data\"):\n mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(result.to_dict(mode=\"json\"))\n", "label": "Python SDK · all choices", "language": "python" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "chat", "hints": [ "Send exact model ID with messages.", "Context length is not an output cap.", "A text file may supply literal text; image/audio/file-object inputs need exact binding." ], "http": "POST", "in": 0.58, "input": [ "text" ], "label": "OpenAI Chat", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [ "/chat/completions" ], "out": 0.86, "output": [ "text" ], "path": "/v1/chat/completions", "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": "0.00058000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000058", "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": "0.00086000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.00000086", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "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": "deepseek-v3.2-thinking", "route_label": "Ultra", "status_reads": [], "tiers": [], "units": [ { "amount": "0.00058000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000058", "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": "0.00086000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0.00000086", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "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": "deepseek-v3.2-thinking", "request_model_id": "deepseek-v3.2-thinking", "route_label": "Ultra" } ], "name": "DeepSeek: DeepSeek V3.2", "price": { "in": 0.58, "in_label": null, "out": 0.86, "out_label": null, "scope_label": "Token rates", "sort_in": 0.58, "sort_out": 0.86, "varies": false }, "short": "DeepSeek V3.2 matnli mulohazani vosita qo‘llanilishi va uzun kontekst tahlili bilan birlashtiradi. Uning siyrak diqqat arxitekturasi va yangilangan suhbat formati kodlash, qidiruv va ko‘p bosqichli agent vazifalarini qo‘llaydi; 128K kontekst hamda alohida fikrlash va bevosita javob jarayonlari mavjud." }, "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": "DeepSeek V3.2 matnli mulohazani vosita qo‘llanilishi va uzun kontekst tahlili bilan birlashtiradi. Uning siyrak diqqat arxitekturasi va yangilangan suhbat formati kodlash, qidiruv va ko‘p bosqichli agent vazifalarini qo‘llaydi; 128K kontekst hamda alohida fikrlash va bevosita javob jarayonlari mavjud.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "039c1184f62da476c13d2a48b7a9efd4677db50d51a2b113a2e046c392dd8aad", "renderer_sha256": "aa8a0fca1bd770c042b64987512b6187fca2067aea3ddc877f68b163d80e7df6" }, "sourceRevision": "0f30e5108462618a58e16bbc652c60c37235f4f3082202674d2650e411d8f507" }