{
  "aboutHtml": "<p>Kimi K3 — Moonshot AI kompaniyasining uzoq davom etadigan dasturlash, bilim ishi va mulohaza uchun ochiq vaznli multimodal agent modeli. U matnni tasvir va videoni bevosita vizual tushunish bilan birlashtirib, matnli javob yoki vosita so‘rovini yaratadi. Ishlab chiqaruvchi uzun muhandislik seanslari, katta repozitoriylar hamda kod bilan birga skrinshot yoki vizual qayta aloqadan foydalanadigan vazifalarni ta’kidlaydi. Foydali topshiriq kerakli material, foydalaniladigan dalillar va ish tugallanganini belgilaydigan shartni aniqlaydi.</p><h4>Arxitektura va uzun kontekst</h4><p>Model kartasi jami 2,8 trillion parametr va 104 milliard faollashtirilgan parametrli siyrak Mixture of Expertsni ta’riflaydi. Uning Stable LatentMoE dizayni har bir token uchun 896 ekspertdan 16 tasini tanlaydi, bunda Kimi Delta Attention va Attention Residualsdan darvozali diqqat bilan birga foydalanadi. Aniq kontekst uzunligi 1 048 576 token. Bu katta vazifa konteksti uchun joy, manba chegaralarini yoki natija uchun kerakli joyni e’tiborsiz qoldirishga sabab emas.</p><p>E’lon qilingan asl material MXFP4 vaznlari va MXFP8 faollashuvlari bilan kvantlashni hisobga olgan o‘qitishdan foydalanadi. Bu ishlab chiqaruvchining reliz formati bo‘lib, alohida taqdim etilgan kvantlangan nashrdan yoki muayyan yo‘nalish modelga qanday xizmat ko‘rsatishi haqidagi da’vodan farq qiladi. Ochiq vaznlar va katta parametrlar soni faol parametrlar sonini umumiy saqlash yoki apparat talabiga aylantirmaydi.</p><h4>Katta dasturlash vazifasini tayyorlang</h4><p>Tegishli repozitoriy materiali, mavjud xatti-harakat, so‘ralgan o‘zgarish va moslik cheklovlarini bering. Natija ta’sir qilishi shart bo‘lgan fayllar yoki interfeysni, muvaffaqiyatni belgilaydigan tekshiruvlarni hamda muammoni ko‘rsatadigan berilgan xato yoki kirishni belgilang. Foydali natija hech qachon bajarilmagan harakatlar tavsifi emas, tushuntirish va haqiqatan ishlagan tekshiruvlardan dalil bilan aniq yo‘naltirilgan kod o‘zgarishi bo‘lishi mumkin.</p><p>Vizual ishlab chiqish vazifasida tegishli kod va aniq nomuvofiqlik bilan birga skrinshot yoki kerakli natijaning ravshan ko‘rinishini kiriting. Ishlab chiqaruvchi frontend ishi, o‘yinlar va CADni qamrab oladigan, vizual qayta aloqadan foydalanadigan jarayonlarni ta’riflaydi. Kodni kuzatilgan natijaga bog‘laydigan o‘zgarishni so‘rang va yetkazilgan materialni u bilan tekshirish uchun tayanch manbani saqlang.</p><h4>Tasvirlar, video va bilim ishini tayyorlash</h4><p>Ishlab chiqaruvchining tezkor boshlash yo‘riqnomasi vizual xabarlar uchun turi belgilangan mazmun obyektlaridan foydalanadi; content massiv bo‘lib, ushbu massivning ketma-ket yozilgan matnli ifodasi emas. Uning tasvir jarayoni ommaviy tasvir manzili o‘rniga kodlangan tasvir ma’lumoti yoki qo‘llanadigan fayl havolasidan foydalanadi. Video misoli video faylini yuklaydi va hosil bo‘lgan havolani uning mazmuni haqidagi savol bilan beradi. O‘qiladigan manbani bering hamda muhim kuzatuv, oraliq yoki bog‘lanishni belgilang. Ishlab chiqaruvchining vizual jarayoni JPEG, PNG, GIF, WebP, BMP, HEIC va HEIF tasvirlarini hamda MP4, MPEG, MOV, AVI, FLV, MPG, WebM, WMV va 3GPP videolarini qabul qiladi. Animatsiyalangan GIF yoki WebP video sifatida dekodlanishi mumkin. SVG manbasini matn sifatida bering. Ishlab chiqaruvchi tasvirlar uchun 4096 × 2160 gacha, video uchun 1920 × 1080 gacha o‘lchamlarni tavsiya qiladi; bular rad etish chegaralari emas, aniqlik tavsiyalaridir. So‘rov tanasini hujjatlashtirilgan 100M hajm chegarasi ichida saqlang va katta yoki qayta-qayta ishlatiladigan mediani fayl sifatida yuklang.</p><p>Hujjatlarga boy tadqiqotda manbalarni belgilang va yakuniy hisobot javob berishi kerak bo‘lgan savollarni ayting. Video tushuntirishida cheklanmagan izoh so‘rash o‘rniga tahlil qilinadigan hodisalar yoki ketma-ketlikni ko‘rsating. K3 vizual mazmundan mulohaza uchun dalil sifatida foydalanib, matn yoki vosita so‘rovlarini qaytaradi. Ilova alohida tasvir yoki video materiallari yaratish uchun ushbu so‘rovlarni media vositalariga uzatishi mumkin.</p><h4>Fikrlash doimo yoqilgan</h4><p>K3ning ishlab chiqaruvchi interfeysida fikrlash doimo yoqilgan. Yuqori darajadagi reasoning_effort sozlamasi low, high va max qiymatlarini qabul qiladi, standart qiymat max. Bu tanlovlar modelga xos; fikrlamaslik sozlamasi yoki boshqa oilaning daraja qiymatini taxmin qilmaslik kerak. Ishlab chiqaruvchining ko‘chirish yo‘riqnomasi eski thinking konfiguratsiyasini ko‘chirish o‘rniga reasoning_effort dan foydalanish bilan K3ni K2.xdan farqlaydi.</p><p>Ishlab chiqaruvchi oqimli natijalarda reasoning_content va yakuniy javob content qismlarini alohida hujjatlashtiradi. Ko‘p navbatli suhbat yoki vosita jarayoni uchun qaytgan yordamchi xabari to‘liq, jumladan reasoning_content va tool_calls bilan o‘zgartirilmay qayta berilishini talab qiladi. Faqat ko‘rinadigan yakuniy javobni saqlash modelning saqlangan fikrlash jarayoni keyingi qadamda kutadigan ma’lumotni yo‘qotadi.</p><h4>Tuzilmali yakuniy javoblar va qisman davom ettirish</h4><p>Tezkor boshlash yo‘riqnomasi yakuniy xabar mazmuni uchun qat’iy JSON-schema natijasini hujjatlashtiradi. Maydonlar va ularning ma’nolarini ilovaga kerakli material atrofida belgilang hamda yakuniy mazmunni mulohaza maydoni bilan birlashtirmasdan tahlil qiling. Tuzilmali natija berilgan materialdan ajratilgan ma’lumot yoki belgilangan hisobot shaklini ifodalashi mumkin; sxema uning shaklini cheklaydi, qiymatlar to‘g‘riligini esa manba dalillari belgilaydi.</p><p>Partial rejimi berilgan matn prefiksini davom ettirishi mumkin. Ishlab chiqaruvchi misoli tarix oxiriga qisman yordamchi xabarini joylashtiradi va ko‘rsatish uchun shu prefiksni qaytgan davom bilan birlashtiradi. Zarur material mazmunli qat’iy boshlanishga ega bo‘lsa, prefiksni yaratilgan qolgan qismdan farqlagan holda bundan foydalaning.</p><h4>Vositalar va ularning natijalari uzluksizligi</h4><p>K3 maxsus funksiya vositalarini qo‘llab-quvvatlaydi. Ishlab chiqaruvchi misoli birinchi navbatda vositani talab qiladi, yordamchining to‘liq xabarini saqlaydi, har bir qaytgan chaqiruvni bajaradi va yakuniy javobni so‘rashdan oldin mos vosita natijasini qo‘shadi. Taklif etilgan chaqiruv amal muvaffaqiyatli bo‘lganining dalili emas; haqiqiy qaytgan natija keyingi qadam uchun dalilga aylanadi.</p><p>Uning dinamik yuklash jarayoni xabar tarixining muayyan joyida to‘liq vosita ta’rifini kiritadi. Ta’rifga uning nomi, maqsadi va parametrlari kerak; server bu e’lonni mustaqil saqlamagani uchun u keyingi tarixda ham qolishi shart. Uzun vazifa allaqachon tugallangan ishdan davom etishi uchun vosita imkoniyatlari, berilgan argumentlar va haqiqiy kuzatuvlarni bog‘liq saqlang.</p><h4>Chiqish boshqaruvlari va takroriy kontekst</h4><p>Ishlab chiqaruvchi 131 072 tokenli standart yaratish limitini hujjatlashtiradi; u modelning umumiy kontekst cheklovlari ichida 1 048 576 gacha sozlanadi. Uning joriy K3 API qiymatlari qat’iy: temperature 1.0, top_p 0.95, bitta natija, presence va frequency jarimalari nol; chaqiruvchilarga ushbu namuna olish boshqaruvlarini yubormaslik aytiladi. Bular boshqa joyga ko‘chiriladigan sozlanadigan boshqaruvlar ro‘yxati emas, aynan ishlab chiqaruvchi katalog variantining sozlamalari.</p><p>Mos takroriy prefikslar uchun kontekst keshlash avtomatik; hujjatlashtirilgan TTL tanlovlari 5 daqiqa va 1 soat, standart esa 5 daqiqa. Qisman kesh bloklari keshga tushmagan bo‘lib qoladi. Qayta ishlatiladigan kontekstni barqaror saqlang va faqat takrorlangan matnga qarab keshga tushganini da’vo qilish o‘rniga haqiqiy sarfni tekshiring. Yakuniy material uchun berilgan manbalar, haqiqiy vosita dalillari va zarur chiqish tuzilmasini saqlang hamda uzun javob yoki muhandislik natijasi aytilgan tugallanish mezonlariga mosligini tekshiring.</p>",
  "aboutText": "Kimi K3 — Moonshot AI kompaniyasining uzoq davom etadigan dasturlash, bilim ishi va mulohaza uchun ochiq vaznli multimodal agent modeli. U matnni tasvir va videoni bevosita vizual tushunish bilan birlashtirib, matnli javob yoki vosita so‘rovini yaratadi. Ishlab chiqaruvchi uzun muhandislik seanslari, katta repozitoriylar hamda kod bilan birga skrinshot yoki vizual qayta aloqadan foydalanadigan vazifalarni ta’kidlaydi. Foydali topshiriq kerakli material, foydalaniladigan dalillar va ish tugallanganini belgilaydigan shartni aniqlaydi.\n\n### Arxitektura va uzun kontekst\n\nModel kartasi jami 2,8 trillion parametr va 104 milliard faollashtirilgan parametrli siyrak Mixture of Expertsni ta’riflaydi. Uning Stable LatentMoE dizayni har bir token uchun 896 ekspertdan 16 tasini tanlaydi, bunda Kimi Delta Attention va Attention Residualsdan darvozali diqqat bilan birga foydalanadi. Aniq kontekst uzunligi 1 048 576 token. Bu katta vazifa konteksti uchun joy, manba chegaralarini yoki natija uchun kerakli joyni e’tiborsiz qoldirishga sabab emas.\n\nE’lon qilingan asl material MXFP4 vaznlari va MXFP8 faollashuvlari bilan kvantlashni hisobga olgan o‘qitishdan foydalanadi. Bu ishlab chiqaruvchining reliz formati bo‘lib, alohida taqdim etilgan kvantlangan nashrdan yoki muayyan yo‘nalish modelga qanday xizmat ko‘rsatishi haqidagi da’vodan farq qiladi. Ochiq vaznlar va katta parametrlar soni faol parametrlar sonini umumiy saqlash yoki apparat talabiga aylantirmaydi.\n\n### Katta dasturlash vazifasini tayyorlang\n\nTegishli repozitoriy materiali, mavjud xatti-harakat, so‘ralgan o‘zgarish va moslik cheklovlarini bering. Natija ta’sir qilishi shart bo‘lgan fayllar yoki interfeysni, muvaffaqiyatni belgilaydigan tekshiruvlarni hamda muammoni ko‘rsatadigan berilgan xato yoki kirishni belgilang. Foydali natija hech qachon bajarilmagan harakatlar tavsifi emas, tushuntirish va haqiqatan ishlagan tekshiruvlardan dalil bilan aniq yo‘naltirilgan kod o‘zgarishi bo‘lishi mumkin.\n\nVizual ishlab chiqish vazifasida tegishli kod va aniq nomuvofiqlik bilan birga skrinshot yoki kerakli natijaning ravshan ko‘rinishini kiriting. Ishlab chiqaruvchi frontend ishi, o‘yinlar va CADni qamrab oladigan, vizual qayta aloqadan foydalanadigan jarayonlarni ta’riflaydi. Kodni kuzatilgan natijaga bog‘laydigan o‘zgarishni so‘rang va yetkazilgan materialni u bilan tekshirish uchun tayanch manbani saqlang.\n\n### Tasvirlar, video va bilim ishini tayyorlash\n\nIshlab chiqaruvchining tezkor boshlash yo‘riqnomasi vizual xabarlar uchun turi belgilangan mazmun obyektlaridan foydalanadi; content massiv bo‘lib, ushbu massivning ketma-ket yozilgan matnli ifodasi emas. Uning tasvir jarayoni ommaviy tasvir manzili o‘rniga kodlangan tasvir ma’lumoti yoki qo‘llanadigan fayl havolasidan foydalanadi. Video misoli video faylini yuklaydi va hosil bo‘lgan havolani uning mazmuni haqidagi savol bilan beradi. O‘qiladigan manbani bering hamda muhim kuzatuv, oraliq yoki bog‘lanishni belgilang. Ishlab chiqaruvchining vizual jarayoni JPEG, PNG, GIF, WebP, BMP, HEIC va HEIF tasvirlarini hamda MP4, MPEG, MOV, AVI, FLV, MPG, WebM, WMV va 3GPP videolarini qabul qiladi. Animatsiyalangan GIF yoki WebP video sifatida dekodlanishi mumkin. SVG manbasini matn sifatida bering. Ishlab chiqaruvchi tasvirlar uchun 4096 × 2160 gacha, video uchun 1920 × 1080 gacha o‘lchamlarni tavsiya qiladi; bular rad etish chegaralari emas, aniqlik tavsiyalaridir. So‘rov tanasini hujjatlashtirilgan 100M hajm chegarasi ichida saqlang va katta yoki qayta-qayta ishlatiladigan mediani fayl sifatida yuklang.\n\nHujjatlarga boy tadqiqotda manbalarni belgilang va yakuniy hisobot javob berishi kerak bo‘lgan savollarni ayting. Video tushuntirishida cheklanmagan izoh so‘rash o‘rniga tahlil qilinadigan hodisalar yoki ketma-ketlikni ko‘rsating. K3 vizual mazmundan mulohaza uchun dalil sifatida foydalanib, matn yoki vosita so‘rovlarini qaytaradi. Ilova alohida tasvir yoki video materiallari yaratish uchun ushbu so‘rovlarni media vositalariga uzatishi mumkin.\n\n### Fikrlash doimo yoqilgan\n\nK3ning ishlab chiqaruvchi interfeysida fikrlash doimo yoqilgan. Yuqori darajadagi reasoning_effort sozlamasi low, high va max qiymatlarini qabul qiladi, standart qiymat max. Bu tanlovlar modelga xos; fikrlamaslik sozlamasi yoki boshqa oilaning daraja qiymatini taxmin qilmaslik kerak. Ishlab chiqaruvchining ko‘chirish yo‘riqnomasi eski thinking konfiguratsiyasini ko‘chirish o‘rniga reasoning_effort dan foydalanish bilan K3ni K2.xdan farqlaydi.\n\nIshlab chiqaruvchi oqimli natijalarda reasoning_content va yakuniy javob content qismlarini alohida hujjatlashtiradi. Ko‘p navbatli suhbat yoki vosita jarayoni uchun qaytgan yordamchi xabari to‘liq, jumladan reasoning_content va tool_calls bilan o‘zgartirilmay qayta berilishini talab qiladi. Faqat ko‘rinadigan yakuniy javobni saqlash modelning saqlangan fikrlash jarayoni keyingi qadamda kutadigan ma’lumotni yo‘qotadi.\n\n### Tuzilmali yakuniy javoblar va qisman davom ettirish\n\nTezkor boshlash yo‘riqnomasi yakuniy xabar mazmuni uchun qat’iy JSON-schema natijasini hujjatlashtiradi. Maydonlar va ularning ma’nolarini ilovaga kerakli material atrofida belgilang hamda yakuniy mazmunni mulohaza maydoni bilan birlashtirmasdan tahlil qiling. Tuzilmali natija berilgan materialdan ajratilgan ma’lumot yoki belgilangan hisobot shaklini ifodalashi mumkin; sxema uning shaklini cheklaydi, qiymatlar to‘g‘riligini esa manba dalillari belgilaydi.\n\nPartial rejimi berilgan matn prefiksini davom ettirishi mumkin. Ishlab chiqaruvchi misoli tarix oxiriga qisman yordamchi xabarini joylashtiradi va ko‘rsatish uchun shu prefiksni qaytgan davom bilan birlashtiradi. Zarur material mazmunli qat’iy boshlanishga ega bo‘lsa, prefiksni yaratilgan qolgan qismdan farqlagan holda bundan foydalaning.\n\n### Vositalar va ularning natijalari uzluksizligi\n\nK3 maxsus funksiya vositalarini qo‘llab-quvvatlaydi. Ishlab chiqaruvchi misoli birinchi navbatda vositani talab qiladi, yordamchining to‘liq xabarini saqlaydi, har bir qaytgan chaqiruvni bajaradi va yakuniy javobni so‘rashdan oldin mos vosita natijasini qo‘shadi. Taklif etilgan chaqiruv amal muvaffaqiyatli bo‘lganining dalili emas; haqiqiy qaytgan natija keyingi qadam uchun dalilga aylanadi.\n\nUning dinamik yuklash jarayoni xabar tarixining muayyan joyida to‘liq vosita ta’rifini kiritadi. Ta’rifga uning nomi, maqsadi va parametrlari kerak; server bu e’lonni mustaqil saqlamagani uchun u keyingi tarixda ham qolishi shart. Uzun vazifa allaqachon tugallangan ishdan davom etishi uchun vosita imkoniyatlari, berilgan argumentlar va haqiqiy kuzatuvlarni bog‘liq saqlang.\n\n### Chiqish boshqaruvlari va takroriy kontekst\n\nIshlab chiqaruvchi 131 072 tokenli standart yaratish limitini hujjatlashtiradi; u modelning umumiy kontekst cheklovlari ichida 1 048 576 gacha sozlanadi. Uning joriy K3 API qiymatlari qat’iy: temperature 1.0, top_p 0.95, bitta natija, presence va frequency jarimalari nol; chaqiruvchilarga ushbu namuna olish boshqaruvlarini yubormaslik aytiladi. Bular boshqa joyga ko‘chiriladigan sozlanadigan boshqaruvlar ro‘yxati emas, aynan ishlab chiqaruvchi katalog variantining sozlamalari.\n\nMos takroriy prefikslar uchun kontekst keshlash avtomatik; hujjatlashtirilgan TTL tanlovlari 5 daqiqa va 1 soat, standart esa 5 daqiqa. Qisman kesh bloklari keshga tushmagan bo‘lib qoladi. Qayta ishlatiladigan kontekstni barqaror saqlang va faqat takrorlangan matnga qarab keshga tushganini da’vo qilish o‘rniga haqiqiy sarfni tekshiring. Yakuniy material uchun berilgan manbalar, haqiqiy vosita dalillari va zarur chiqish tuzilmasini saqlang hamda uzun javob yoki muhandislik natijasi aytilgan tugallanish mezonlariga mosligini tekshiring.",
  "editorialOverlay": {
    "copy_fields": null,
    "copy_sha256": null,
    "copy_source": null,
    "html_sha256": "1938e0874c303e11b40171190123954e41644b9f8a253647e27869b95387abde",
    "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06",
    "raw_model_unchanged": true,
    "schema": "ailoot-native-model-editorial-v1"
  },
  "locale": "uz",
  "methods": [
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">•</span><h2 id=\"sheet-title\">MoonshotAI: Kimi K3 (batch)</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Yopish\">×</button></div><div class=\"idline\"><span>MoonshotAI /</span><code>moonshotai/kimi-k3:batch</code><button type=\"button\" id=\"copy-id\">ID ni nusxalash</button></div><nav class=\"card-jump-nav\" aria-label=\"Model kartochkasi bo‘limlari\"><button type=\"button\" data-card-jump=\"overview\">Boshlash</button><button type=\"button\" data-card-jump=\"methods\">Kirish ma’lumotlari va usullar</button><button type=\"button\" data-card-jump=\"pricing\">Tariflar</button><button type=\"button\" data-card-jump=\"examples\">Namunalar</button><button type=\"button\" data-card-jump=\"results\">Natijalar</button><button type=\"button\" data-card-jump=\"aliases\">Taxalluslar</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API usullari\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Ultra|batches|/v1/batches|moonshotai%2Fkimi-k3%3Abatch\">Paketli vazifalar</button></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">Boshlash</h3><p class=\"mdesc-full\">Kimi K3 — Moonshot AI kompaniyasining uzun dasturlash vazifalari va bilim ishi uchun boshidan multimodal yaratilgan mulohaza modeli. U matn, tasvir va videoni o‘qiydi, matn yaratadi hamda 1 048 576 tokenli kontekst va qadamlar bo‘ylab saqlanadigan fikrlash tarixi bilan vositalarga tayangan jarayonlarni qo‘llab-quvvatlaydi.</p><dl class=\"card-io\" data-card-io><div><dt>Qabul qilinadigan kirish ma’lumotlari</dt><dd>Matn</dd></div><div><dt>Natijalar</dt><dd>Matn</dd></div></dl><details class=\"card-about\"><summary>Model haqida</summary><p class=\"note-s\" data-model-method-boundary>Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.</p><div class=\"mabout\" id=\"m-about\"><p>Kimi K3 — Moonshot AI kompaniyasining uzoq davom etadigan dasturlash, bilim ishi va mulohaza uchun ochiq vaznli multimodal agent modeli. U matnni tasvir va videoni bevosita vizual tushunish bilan birlashtirib, matnli javob yoki vosita so‘rovini yaratadi. Ishlab chiqaruvchi uzun muhandislik seanslari, katta repozitoriylar hamda kod bilan birga skrinshot yoki vizual qayta aloqadan foydalanadigan vazifalarni ta’kidlaydi. Foydali topshiriq kerakli material, foydalaniladigan dalillar va ish tugallanganini belgilaydigan shartni aniqlaydi.</p><h4>Arxitektura va uzun kontekst</h4><p>Model kartasi jami 2,8 trillion parametr va 104 milliard faollashtirilgan parametrli siyrak Mixture of Expertsni ta’riflaydi. Uning Stable LatentMoE dizayni har bir token uchun 896 ekspertdan 16 tasini tanlaydi, bunda Kimi Delta Attention va Attention Residualsdan darvozali diqqat bilan birga foydalanadi. Aniq kontekst uzunligi 1 048 576 token. Bu katta vazifa konteksti uchun joy, manba chegaralarini yoki natija uchun kerakli joyni e’tiborsiz qoldirishga sabab emas.</p><p>E’lon qilingan asl material MXFP4 vaznlari va MXFP8 faollashuvlari bilan kvantlashni hisobga olgan o‘qitishdan foydalanadi. Bu ishlab chiqaruvchining reliz formati bo‘lib, alohida taqdim etilgan kvantlangan nashrdan yoki muayyan yo‘nalish modelga qanday xizmat ko‘rsatishi haqidagi da’vodan farq qiladi. Ochiq vaznlar va katta parametrlar soni faol parametrlar sonini umumiy saqlash yoki apparat talabiga aylantirmaydi.</p><h4>Katta dasturlash vazifasini tayyorlang</h4><p>Tegishli repozitoriy materiali, mavjud xatti-harakat, so‘ralgan o‘zgarish va moslik cheklovlarini bering. Natija ta’sir qilishi shart bo‘lgan fayllar yoki interfeysni, muvaffaqiyatni belgilaydigan tekshiruvlarni hamda muammoni ko‘rsatadigan berilgan xato yoki kirishni belgilang. Foydali natija hech qachon bajarilmagan harakatlar tavsifi emas, tushuntirish va haqiqatan ishlagan tekshiruvlardan dalil bilan aniq yo‘naltirilgan kod o‘zgarishi bo‘lishi mumkin.</p><p>Vizual ishlab chiqish vazifasida tegishli kod va aniq nomuvofiqlik bilan birga skrinshot yoki kerakli natijaning ravshan ko‘rinishini kiriting. Ishlab chiqaruvchi frontend ishi, o‘yinlar va CADni qamrab oladigan, vizual qayta aloqadan foydalanadigan jarayonlarni ta’riflaydi. Kodni kuzatilgan natijaga bog‘laydigan o‘zgarishni so‘rang va yetkazilgan materialni u bilan tekshirish uchun tayanch manbani saqlang.</p><h4>Tasvirlar, video va bilim ishini tayyorlash</h4><p>Ishlab chiqaruvchining tezkor boshlash yo‘riqnomasi vizual xabarlar uchun turi belgilangan mazmun obyektlaridan foydalanadi; content massiv bo‘lib, ushbu massivning ketma-ket yozilgan matnli ifodasi emas. Uning tasvir jarayoni ommaviy tasvir manzili o‘rniga kodlangan tasvir ma’lumoti yoki qo‘llanadigan fayl havolasidan foydalanadi. Video misoli video faylini yuklaydi va hosil bo‘lgan havolani uning mazmuni haqidagi savol bilan beradi. O‘qiladigan manbani bering hamda muhim kuzatuv, oraliq yoki bog‘lanishni belgilang. Ishlab chiqaruvchining vizual jarayoni JPEG, PNG, GIF, WebP, BMP, HEIC va HEIF tasvirlarini hamda MP4, MPEG, MOV, AVI, FLV, MPG, WebM, WMV va 3GPP videolarini qabul qiladi. Animatsiyalangan GIF yoki WebP video sifatida dekodlanishi mumkin. SVG manbasini matn sifatida bering. Ishlab chiqaruvchi tasvirlar uchun 4096 × 2160 gacha, video uchun 1920 × 1080 gacha o‘lchamlarni tavsiya qiladi; bular rad etish chegaralari emas, aniqlik tavsiyalaridir. So‘rov tanasini hujjatlashtirilgan 100M hajm chegarasi ichida saqlang va katta yoki qayta-qayta ishlatiladigan mediani fayl sifatida yuklang.</p><p>Hujjatlarga boy tadqiqotda manbalarni belgilang va yakuniy hisobot javob berishi kerak bo‘lgan savollarni ayting. Video tushuntirishida cheklanmagan izoh so‘rash o‘rniga tahlil qilinadigan hodisalar yoki ketma-ketlikni ko‘rsating. K3 vizual mazmundan mulohaza uchun dalil sifatida foydalanib, matn yoki vosita so‘rovlarini qaytaradi. Ilova alohida tasvir yoki video materiallari yaratish uchun ushbu so‘rovlarni media vositalariga uzatishi mumkin.</p><h4>Fikrlash doimo yoqilgan</h4><p>K3ning ishlab chiqaruvchi interfeysida fikrlash doimo yoqilgan. Yuqori darajadagi reasoning_effort sozlamasi low, high va max qiymatlarini qabul qiladi, standart qiymat max. Bu tanlovlar modelga xos; fikrlamaslik sozlamasi yoki boshqa oilaning daraja qiymatini taxmin qilmaslik kerak. Ishlab chiqaruvchining ko‘chirish yo‘riqnomasi eski thinking konfiguratsiyasini ko‘chirish o‘rniga reasoning_effort dan foydalanish bilan K3ni K2.xdan farqlaydi.</p><p>Ishlab chiqaruvchi oqimli natijalarda reasoning_content va yakuniy javob content qismlarini alohida hujjatlashtiradi. Ko‘p navbatli suhbat yoki vosita jarayoni uchun qaytgan yordamchi xabari to‘liq, jumladan reasoning_content va tool_calls bilan o‘zgartirilmay qayta berilishini talab qiladi. Faqat ko‘rinadigan yakuniy javobni saqlash modelning saqlangan fikrlash jarayoni keyingi qadamda kutadigan ma’lumotni yo‘qotadi.</p><h4>Tuzilmali yakuniy javoblar va qisman davom ettirish</h4><p>Tezkor boshlash yo‘riqnomasi yakuniy xabar mazmuni uchun qat’iy JSON-schema natijasini hujjatlashtiradi. Maydonlar va ularning ma’nolarini ilovaga kerakli material atrofida belgilang hamda yakuniy mazmunni mulohaza maydoni bilan birlashtirmasdan tahlil qiling. Tuzilmali natija berilgan materialdan ajratilgan ma’lumot yoki belgilangan hisobot shaklini ifodalashi mumkin; sxema uning shaklini cheklaydi, qiymatlar to‘g‘riligini esa manba dalillari belgilaydi.</p><p>Partial rejimi berilgan matn prefiksini davom ettirishi mumkin. Ishlab chiqaruvchi misoli tarix oxiriga qisman yordamchi xabarini joylashtiradi va ko‘rsatish uchun shu prefiksni qaytgan davom bilan birlashtiradi. Zarur material mazmunli qat’iy boshlanishga ega bo‘lsa, prefiksni yaratilgan qolgan qismdan farqlagan holda bundan foydalaning.</p><h4>Vositalar va ularning natijalari uzluksizligi</h4><p>K3 maxsus funksiya vositalarini qo‘llab-quvvatlaydi. Ishlab chiqaruvchi misoli birinchi navbatda vositani talab qiladi, yordamchining to‘liq xabarini saqlaydi, har bir qaytgan chaqiruvni bajaradi va yakuniy javobni so‘rashdan oldin mos vosita natijasini qo‘shadi. Taklif etilgan chaqiruv amal muvaffaqiyatli bo‘lganining dalili emas; haqiqiy qaytgan natija keyingi qadam uchun dalilga aylanadi.</p><p>Uning dinamik yuklash jarayoni xabar tarixining muayyan joyida to‘liq vosita ta’rifini kiritadi. Ta’rifga uning nomi, maqsadi va parametrlari kerak; server bu e’lonni mustaqil saqlamagani uchun u keyingi tarixda ham qolishi shart. Uzun vazifa allaqachon tugallangan ishdan davom etishi uchun vosita imkoniyatlari, berilgan argumentlar va haqiqiy kuzatuvlarni bog‘liq saqlang.</p><h4>Chiqish boshqaruvlari va takroriy kontekst</h4><p>Ishlab chiqaruvchi 131 072 tokenli standart yaratish limitini hujjatlashtiradi; u modelning umumiy kontekst cheklovlari ichida 1 048 576 gacha sozlanadi. Uning joriy K3 API qiymatlari qat’iy: temperature 1.0, top_p 0.95, bitta natija, presence va frequency jarimalari nol; chaqiruvchilarga ushbu namuna olish boshqaruvlarini yubormaslik aytiladi. Bular boshqa joyga ko‘chiriladigan sozlanadigan boshqaruvlar ro‘yxati emas, aynan ishlab chiqaruvchi katalog variantining sozlamalari.</p><p>Mos takroriy prefikslar uchun kontekst keshlash avtomatik; hujjatlashtirilgan TTL tanlovlari 5 daqiqa va 1 soat, standart esa 5 daqiqa. Qisman kesh bloklari keshga tushmagan bo‘lib qoladi. Qayta ishlatiladigan kontekstni barqaror saqlang va faqat takrorlangan matnga qarab keshga tushganini da’vo qilish o‘rniga haqiqiy sarfni tekshiring. Yakuniy material uchun berilgan manbalar, haqiqiy vosita dalillari va zarur chiqish tuzilmasini saqlang hamda uzun javob yoki muhandislik natijasi aytilgan tugallanish mezonlariga mosligini tekshiring.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot da mavjud · kirish ma’lumotlari va usullar</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · Paketli ishlov berish</b> <code>POST /v1/batches</code></summary><dl class=\"method-capabilities\"><div><dt>Kirish</dt><dd><code>text</code></dd></div><div><dt>Chiqish</dt><dd><code>text</code></dd></div><div><dt>Chiqish formati</dt><dd>Javobga bevosita kiritilgan results[].response.body JSON ma’lumotlari</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>Maydon</th><th>Tur</th><th>Talab</th><th>Qiymatlar va cheklovlar</th><th>Standart</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">endpoint</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span><code>string</code></td><td data-cell-label=\"Talab\"><span class=\"card-cell-label\">Talab</span>Majburiy</td><td data-cell-label=\"Qiymatlar va cheklovlar\"><span class=\"card-cell-label\">Qiymatlar va cheklovlar</span><div>/v1/chat/completions</div></td><td data-cell-label=\"Standart\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standart</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span><code>string</code></td><td data-cell-label=\"Talab\"><span class=\"card-cell-label\">Talab</span>Majburiy</td><td data-cell-label=\"Qiymatlar va cheklovlar\"><span class=\"card-cell-label\">Qiymatlar va cheklovlar</span><div>moonshotai/kimi-k3:batch</div></td><td data-cell-label=\"Standart\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standart</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">requests</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span><code>batch_item[]</code></td><td data-cell-label=\"Talab\"><span class=\"card-cell-label\">Talab</span>Majburiy</td><td data-cell-label=\"Qiymatlar va cheklovlar\"><span class=\"card-cell-label\">Qiymatlar va cheklovlar</span><div>Elementlarning eng kam soni: 1</div></td><td data-cell-label=\"Standart\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standart</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">requests[].custom_id</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span><code>string</code></td><td data-cell-label=\"Talab\"><span class=\"card-cell-label\">Talab</span>Majburiy</td><td data-cell-label=\"Qiymatlar va cheklovlar\"><span class=\"card-cell-label\">Qiymatlar va cheklovlar</span></td><td data-cell-label=\"Standart\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standart</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">requests[].body.messages</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span><code>message[]</code></td><td data-cell-label=\"Talab\"><span class=\"card-cell-label\">Talab</span>Majburiy</td><td data-cell-label=\"Qiymatlar va cheklovlar\"><span class=\"card-cell-label\">Qiymatlar va cheklovlar</span></td><td data-cell-label=\"Standart\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standart</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">completion_window</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span><code>string</code></td><td data-cell-label=\"Talab\"><span class=\"card-cell-label\">Talab</span>Ixtiyoriy</td><td data-cell-label=\"Qiymatlar va cheklovlar\"><span class=\"card-cell-label\">Qiymatlar va cheklovlar</span><div>24h</div></td><td data-cell-label=\"Standart\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standart</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">provider</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span><code>object|null</code></td><td data-cell-label=\"Talab\"><span class=\"card-cell-label\">Talab</span>Ixtiyoriy</td><td data-cell-label=\"Qiymatlar va cheklovlar\"><span class=\"card-cell-label\">Qiymatlar va cheklovlar</span></td><td data-cell-label=\"Standart\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standart</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">requests[].body.model</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span><code>string</code></td><td data-cell-label=\"Talab\"><span class=\"card-cell-label\">Talab</span>Ixtiyoriy</td><td data-cell-label=\"Qiymatlar va cheklovlar\"><span class=\"card-cell-label\">Qiymatlar va cheklovlar</span><div>moonshotai/kimi-k3:batch, moonshotai/kimi-k3</div></td><td data-cell-label=\"Standart\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standart</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">provider.only</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span><code>string[]</code></td><td data-cell-label=\"Talab\"><span class=\"card-cell-label\">Talab</span>Ixtiyoriy</td><td data-cell-label=\"Qiymatlar va cheklovlar\"><span class=\"card-cell-label\">Qiymatlar va cheklovlar</span><div>deepinfra/bf16</div></td><td data-cell-label=\"Standart\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standart</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">provider.allow_fallbacks</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span><code>boolean|null</code></td><td data-cell-label=\"Talab\"><span class=\"card-cell-label\">Talab</span>Ixtiyoriy</td><td data-cell-label=\"Qiymatlar va cheklovlar\"><span class=\"card-cell-label\">Qiymatlar va cheklovlar</span><div>false, null</div></td><td data-cell-label=\"Standart\" data-default=\"unspecified\"><span class=\"card-cell-label\">Standart</span>—</td></tr></tbody></table></div><details class=\"note-s\" data-method-contract><summary>Usul parametrlari va hayot sikli</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>Parametr</th><th>Parametr talablari</th></tr></thead><tbody><tr><th data-cell-label=\"Parametr\" scope=\"row\"><span class=\"card-cell-label\">Parametr</span><code>content_type</code></th><td data-cell-label=\"Parametr talablari\"><span class=\"card-cell-label\">Parametr talablari</span>application/json</td></tr><tr><th data-cell-label=\"Parametr\" scope=\"row\"><span class=\"card-cell-label\">Parametr</span><code>required</code></th><td data-cell-label=\"Parametr talablari\"><span class=\"card-cell-label\">Parametr talablari</span>endpoint, model, requests</td></tr><tr><th data-cell-label=\"Parametr\" scope=\"row\"><span class=\"card-cell-label\">Parametr</span><code>material_types</code></th><td data-cell-label=\"Parametr talablari\"><span class=\"card-cell-label\">Parametr talablari</span>text</td></tr><tr><th data-cell-label=\"Parametr\" scope=\"row\"><span class=\"card-cell-label\">Parametr</span><code>representation</code></th><td data-cell-label=\"Parametr talablari\"><span class=\"card-cell-label\">Parametr talablari</span>So‘rovga bevosita kiritilgan requests[] massivi; har bir elementda custom_id va body mavjud.</td></tr><tr><th data-cell-label=\"Parametr\" scope=\"row\"><span class=\"card-cell-label\">Parametr</span><code>request_endpoint_profile</code></th><td data-cell-label=\"Parametr talablari\"><span class=\"card-cell-label\">Parametr talablari</span>/v1/chat/completions</td></tr><tr><th data-cell-label=\"Parametr\" scope=\"row\"><span class=\"card-cell-label\">Parametr</span><code>file_material</code></th><td data-cell-label=\"Parametr talablari\"><span class=\"card-cell-label\">Parametr talablari</span>Chaqiruvchi haqiqiy UTF-8 JSONL ma’lumotlarini mahalliy tarzda requests[] ichiga o‘qishi mumkin. Yuklash maqsadi, input_file_id yoki faylga havola ishlatilmaydi. Mijoz materiali yo‘q yoki bo‘sh bo‘lsa, tayyorlash POST dan oldin to‘xtaydi.</td></tr><tr><th data-cell-label=\"Parametr\" scope=\"row\"><span class=\"card-cell-label\">Parametr</span><code>serialization_order</code></th><td data-cell-label=\"Parametr talablari\"><span class=\"card-cell-label\">Parametr talablari</span>endpoint, model, provider (agar berilgan bo‘lsa), completion_window (agar berilgan bo‘lsa), requests eng oxirida</td></tr><tr><th data-cell-label=\"Parametr\" scope=\"row\"><span class=\"card-cell-label\">Parametr</span><code>optional_controls</code></th><td data-cell-label=\"Parametr talablari\"><span class=\"card-cell-label\">Parametr talablari</span>provider.only, provider.allow_fallbacks, completion_window</td></tr><tr><th data-cell-label=\"Parametr\" scope=\"row\"><span class=\"card-cell-label\">Parametr</span><code>schema_scope</code></th><td data-cell-label=\"Parametr talablari\"><span class=\"card-cell-label\">Parametr talablari</span>Hujjatlarda ko‘rsatilgan Batch tuzilmasiga bevosita kiritilgan matnli Chat Completions so‘rovlarining tanalari.</td></tr></tbody></table></div><p>Hayot sikli: <code>asynchronous</code></p><p class=\"note-s\"><code>GET /v1/batches/{operation_id}</code> · Dastlabki yaratish javobida amalda qaytarilgan response.id; aynan o‘sha foydalanuvchi/kalit/guruh</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">Tariflar</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>Tarif ma’lumotlari so‘rov imkoniyatlarini qo‘shmaydi. Qo‘llab-quvvatlanadigan parametrlar tanlangan usulda ko‘rsatilgan.</p><dl data-price-conditions><dt>Tezkor rejim</dt><dd>Ko‘rsatilmagan <span class=\"note-s\">Tezkor rejim tanlanganda</span></dd><dt>Flex rejimi</dt><dd>Ko‘rsatilmagan <span class=\"note-s\">flex rejimi tanlanganda</span></dd><dt>Maksimal fikrlash darajasi</dt><dd>Ko‘rsatilmagan <span class=\"note-s\">Maksimal fikrlash darajasi uchun standart (default) tuzatish qo‘llanganda</span></dd><dt>Ochiq ko‘rsatilgan keshlash narxlari</dt><dd>Yoqilmagan <span class=\"note-s\">Ochiq ko‘rsatilgan keshlash so‘ralganda</span></dd></dl></div><div data-declared-tariff-pricing><h4>Ailoot tariflari</h4><h4>Sozlamalar bo‘yicha narxlar</h4><p class=\"note-s\">Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>Sozlama</th><th>Tariflar jadvali</th><th>Kontekst tokenlari soni bundan ko‘p</th><th>Kontekst tokenlari soni bundan oshmaydi, chegara kiradi</th><th>To‘lov</th></tr></thead><tbody><tr><th data-cell-label=\"Sozlama\" scope=\"row\"><span class=\"card-cell-label\">Sozlama</span>Tokenlar uchun bazaviy tariflar</th><td data-cell-label=\"Tariflar jadvali\"><span class=\"card-cell-label\">Tariflar jadvali</span>Asosiy tarif</td><td data-cell-label=\"Kontekst tokenlari soni bundan ko‘p\"><span class=\"card-cell-label\">Kontekst tokenlari soni bundan ko‘p</span>—</td><td data-cell-label=\"Kontekst tokenlari soni bundan oshmaydi, chegara kiradi\"><span class=\"card-cell-label\">Kontekst tokenlari soni bundan oshmaydi, chegara kiradi</span>Yuqori chegara yo‘q</td><td data-cell-label=\"To‘lov\"><span class=\"card-cell-label\">To‘lov</span><div><span>Kirish · Kirish tokenlari</span> <b>$0.00456</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Chiqish · Chiqish tokenlari</span> <b>$0.0228</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Kirish · Keshdan o‘qish</span> <b>$0.000456</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Kirish · Keshga yozish</span> <b>—</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Kirish · Keshga yozish, 1 soat</span> <b>—</b> <span class=\"price-unit\">/ 1K token</span></div></td></tr><tr><th data-cell-label=\"Sozlama\" scope=\"row\"><span class=\"card-cell-label\">Sozlama</span>So‘rov uzunligi bo‘yicha 1-daraja</th><td data-cell-label=\"Tariflar jadvali\"><span class=\"card-cell-label\">Tariflar jadvali</span>—</td><td data-cell-label=\"Kontekst tokenlari soni bundan ko‘p\"><span class=\"card-cell-label\">Kontekst tokenlari soni bundan ko‘p</span>0</td><td data-cell-label=\"Kontekst tokenlari soni bundan oshmaydi, chegara kiradi\"><span class=\"card-cell-label\">Kontekst tokenlari soni bundan oshmaydi, chegara kiradi</span>Yuqori chegara yo‘q</td><td data-cell-label=\"To‘lov\"><span class=\"card-cell-label\">To‘lov</span><div><span>Kirish · Kirish tokenlari</span> <b>$0.00456</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Chiqish · Chiqish tokenlari</span> <b>$0.0228</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Kirish · Keshdan o‘qish</span> <b>$0.000456</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Kirish · Keshga yozish</span> <b>—</b> <span class=\"price-unit\">/ 1K token</span></div><div><span>Kirish · Keshga yozish, 1 soat</span> <b>—</b> <span class=\"price-unit\">/ 1K token</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">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. <a href=\"/docs/uz/billing/reserve/\">Summani band qilish va to‘lovni hisoblash tartibi →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">So‘rov namunalari</h3><h4>Ailoot Ultra · Paketli ishlov berish</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Kod variantlari\"><button class=\"cg-tab\" id=\"model-code-1975-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1975-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl · Saqlangan sinov namunasi</button><button class=\"cg-tab\" id=\"model-code-1975-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1975-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python HTTP · Mijozning haqiqiy JSONL ma’lumotlari</button><button class=\"cg-tab\" id=\"model-code-1975-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1975-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python · Har bir yakunlangan natijani saqlang</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Kodni nusxalash\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-1975-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-1975-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json\nfrom pathlib import Path\nbody=json.loads(&#39;{&quot;endpoint&quot;:&quot;/v1/chat/completions&quot;,&quot;model&quot;:&quot;moonshotai/kimi-k3:batch&quot;,&quot;requests&quot;:[{&quot;custom_id&quot;:&quot;req-0001&quot;,&quot;body&quot;:{&quot;messages&quot;:[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Hello!&quot;}],&quot;max_tokens&quot;:16}}]}&#39;)\nPath(&quot;batch-request.json&quot;).write_text(json.dumps(body,ensure_ascii=False),encoding=&quot;utf-8&quot;)\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @batch-request.json -D batch-response-headers.txt -o batch-create-response.json\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-1975-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-1975-tab-1\" hidden><pre data-lang=\"python\"><code>import json, os\nfrom pathlib import Path\nfrom urllib.request import Request, urlopen\n\ndef prepare_requests(customer_path):\n    path = Path(customer_path)\n    if not path.is_file(): raise ValueError(&quot;Customer JSONL file is missing&quot;)\n    items = [json.loads(line) for line in path.read_text(encoding=&quot;utf-8&quot;).splitlines() if line.strip()]\n    if not items: raise ValueError(&quot;Customer JSONL contains no requests&quot;)\n    ids = set()\n    for item in items:\n        if set(item) != {&quot;custom_id&quot;, &quot;body&quot;}: raise ValueError(&quot;Each item needs custom_id and body&quot;)\n        cid = item[&quot;custom_id&quot;]\n        if not isinstance(cid, str) or not cid.strip() or cid in ids: raise ValueError(&quot;custom_id must be nonempty and unique&quot;)\n        ids.add(cid)\n        if not isinstance(item[&quot;body&quot;], dict) or not item[&quot;body&quot;].get(&quot;messages&quot;): raise ValueError(&quot;Supply actual text messages&quot;)\n        supplied_model = item[&quot;body&quot;].get(&quot;model&quot;)\n        if supplied_model is not None and supplied_model not in [&#39;moonshotai/kimi-k3:batch&#39;, &#39;moonshotai/kimi-k3&#39;]: raise ValueError(&quot;body.model must be an exact documented caller or wire ID&quot;)\n    return {&quot;endpoint&quot;:&quot;/v1/chat/completions&quot;, &quot;model&quot;:&quot;moonshotai/kimi-k3:batch&quot;, &quot;requests&quot;:items}\n\nif __name__ == &quot;__main__&quot;:\n    material = os.environ.get(&quot;AILOOT_BATCH_REQUESTS_JSONL&quot;, &quot;&quot;)\n    if not material: raise SystemExit(&quot;Set AILOOT_BATCH_REQUESTS_JSONL to your actual customer file&quot;)\n    body = prepare_requests(material)\n    key = os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;)\n    if not key: raise SystemExit(&quot;Set AILOOT_API_KEY&quot;)\n    request = Request(&quot;https://api.ailoot.ai/v1/batches&quot;, data=json.dumps(body, ensure_ascii=False).encode(&quot;utf-8&quot;), headers={&quot;Authorization&quot;:&quot;Bearer &quot; + key, &quot;Content-Type&quot;:&quot;application/json&quot;}, method=&quot;POST&quot;)\n    with urlopen(request) as response:\n        raw = response.read()\n        Path(&quot;batch-create-response.json&quot;).write_bytes(raw)\n        print(raw.decode(&quot;utf-8&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-1975-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-1975-tab-2\" hidden><pre data-lang=\"python\"><code>import json\nfrom pathlib import Path\nraw = Path(&quot;batch-status-response.json&quot;).read_bytes()\nresponse = json.loads(raw)\nif response.get(&quot;status&quot;) != &quot;completed&quot;:\n    raise SystemExit(&quot;Keep the original operation; read its status without resubmitting&quot;)\nresults = response.get(&quot;results&quot;)\nif not isinstance(results, list) or not results:\n    raise SystemExit(&quot;Preserve the original response; completed results are missing&quot;)\nPath(&quot;batch-results.jsonl&quot;).write_text(&quot;&quot;.join(json.dumps(item, ensure_ascii=False) + &quot;\\n&quot; for item in results), encoding=&quot;utf-8&quot;)\n# Preserve batch-status-response.json with aggregate usage and every result/error.\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">Natijalarni olish va saqlash</h3><h4>Ailoot Ultra · Paketli ishlov berish</h4><p class=\"note-s\">Javobga bevosita kiritilgan results[].response.body JSON ma’lumotlari</p><ul class=\"card-result-paths\"><li><code>GET /v1/batches/{operation_id}</code></li></ul><h5>Vazifa holatini tekshirish</h5><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Kod variantlari\"><button class=\"cg-tab\" id=\"model-code-1976-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1976-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl · asl operatsiya holati</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Kodni nusxalash\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-1976-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-1976-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\nBATCH_OPERATION_ID=&quot;$(python3 - &lt;&lt;&#39;PY_ID&#39;\nimport json\nfrom pathlib import Path\nfrom urllib.parse import quote\nresponse = json.loads(Path(&quot;batch-create-response.json&quot;).read_text(encoding=&quot;utf-8&quot;))\noperation = response.get(&quot;id&quot;)\nif not isinstance(operation, str) or not operation: raise SystemExit(&quot;No actual original operation ID; preserve the response and do not resubmit&quot;)\nprint(quote(operation, safe=&quot;&quot;))\nPY_ID\n)&quot;\ncurl --fail-with-body --silent --show-error &quot;https://api.ailoot.ai/v1/batches/$BATCH_OPERATION_ID&quot; \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -o batch-status-response.json\n</code></pre></div></div></div><div class=\"card-result-process\" data-all-results><h5>Barcha tayyor natijalarni saqlash</h5><p class=\"note-s\">Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.</p><p class=\"note-s\">Dastlabki holat haqidagi to‘liq JSON ni, har bir natija/custom_id ni va to‘liq javob yoki xato tanasini saqlang. Tugallangan results[] ni hech narsani filtrlab tashlamasdan JSONL sifatida saqlang.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>Asl javobni tekshirish kerak bo‘lsa</h5><p class=\"note-s\">Dastlabki operatsiya ID sini saqlang. 503 result_pending_check javobida X-Should-Retry:false mavjud; natijasi noma’lum bo‘lgan dastlabki paketni hech qachon qayta yubormang.</p></div><details class=\"card-about\" data-output-fields><summary>Javob maydonlari</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>Maydon</th><th>Tur</th></tr></thead><tbody><tr><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">results[].custom_id</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span>string</td></tr><tr><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">results[].response.body.choices[].message.content</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span>string|null</td></tr><tr><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">results[].error</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span>object|null</td></tr><tr><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span>object|null</td></tr><tr><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span>string</td></tr><tr><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span>string</td></tr><tr><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">endpoint</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span>string</td></tr><tr><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">status</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span>string</td></tr><tr><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">request_counts</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span>object</td></tr><tr><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">results[].id</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span>string</td></tr><tr><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">results[].response.status_code</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span>integer</td></tr><tr><th data-cell-label=\"Maydon\" scope=\"row\"><span class=\"card-cell-label\">Maydon</span><code class=\"card-field-name\">results[].response.request_id</code></th><td data-cell-label=\"Tur\" data-field-type><span class=\"card-cell-label\">Tur</span>string</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>Xatolar va keyingi qadamlar</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>Javob</th><th>Shart</th><th>Keyingi qadam</th></tr></thead><tbody><tr><th data-cell-label=\"Javob\" scope=\"row\"><span class=\"card-cell-label\">Javob</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"Shart\"><span class=\"card-cell-label\">Shart</span>Hujjatlarda ko‘rsatilgan, so‘rovga bevosita kiritiladigan tuzilma yaroqsiz, kalitlar takrorlangan, element identifikatori noto‘g‘ri yoki so‘rov modelning sozlangan imkoniyatlariga zid.</td><td data-cell-label=\"Keyingi qadam\"><span class=\"card-cell-label\">Keyingi qadam</span>Har qanday yangi yuborishdan oldin ko‘rsatilgan maydonlarni tuzating.</td></tr><tr><th data-cell-label=\"Javob\" scope=\"row\"><span class=\"card-cell-label\">Javob</span>401 · <code>authentication_error</code></th><td data-cell-label=\"Shart\"><span class=\"card-cell-label\">Shart</span>API kaliti yaroqsiz.</td><td data-cell-label=\"Keyingi qadam\"><span class=\"card-cell-label\">Keyingi qadam</span>Foydalanishga ruxsat berilgan Ailoot kalitidan foydalaning.</td></tr><tr><th data-cell-label=\"Javob\" scope=\"row\"><span class=\"card-cell-label\">Javob</span>403 · <code>permission_error</code></th><td data-cell-label=\"Shart\"><span class=\"card-cell-label\">Shart</span>Paketli ishlov berish guruhi mavjud emas.</td><td data-cell-label=\"Keyingi qadam\"><span class=\"card-cell-label\">Keyingi qadam</span>Kalit/guruhning foydalanish huquqini tekshiring.</td></tr><tr><th data-cell-label=\"Javob\" scope=\"row\"><span class=\"card-cell-label\">Javob</span>422 · <code>invalid_request_error</code></th><td data-cell-label=\"Shart\"><span class=\"card-cell-label\">Shart</span>Paketli ishlov berish to‘lovi balansdan yechiladi; obuna orqali yaratish rad etiladi.</td><td data-cell-label=\"Keyingi qadam\"><span class=\"card-cell-label\">Keyingi qadam</span>Foydalanishga ruxsat berilgan, to‘lovi balansdan yechiladigan guruhdan foydalaning.</td></tr><tr><th data-cell-label=\"Javob\" scope=\"row\"><span class=\"card-cell-label\">Javob</span>422 · <code>price_unavailable</code></th><td data-cell-label=\"Shart\"><span class=\"card-cell-label\">Shart</span>Paket kirish ma’lumotlari uchun narx hisoblab bo‘lmaydi.</td><td data-cell-label=\"Keyingi qadam\"><span class=\"card-cell-label\">Keyingi qadam</span>Javobni saqlang; tegishli API oilasi uchun hujjatlarda belgilangan kirish ma’lumotlaridan foydalaning.</td></tr><tr><th data-cell-label=\"Javob\" scope=\"row\"><span class=\"card-cell-label\">Javob</span>402 · <code>billing_error</code></th><td data-cell-label=\"Shart\"><span class=\"card-cell-label\">Shart</span>Paketli ishlov berish uchun zaxira mavjud emas.</td><td data-cell-label=\"Keyingi qadam\"><span class=\"card-cell-label\">Keyingi qadam</span>Yangi so‘rovdan oldin so‘rovni qabul qilishga ruxsat masalasini hal qiling.</td></tr><tr><th data-cell-label=\"Javob\" scope=\"row\"><span class=\"card-cell-label\">Javob</span>503 · <code>price_unavailable</code></th><td data-cell-label=\"Shart\"><span class=\"card-cell-label\">Shart</span>Paketli ishlov berish usulining narxi yoki tizimning ichki tariflari mavjud emas.</td><td data-cell-label=\"Keyingi qadam\"><span class=\"card-cell-label\">Keyingi qadam</span>Javobni saqlang; narxlarni almashtirmang.</td></tr><tr><th data-cell-label=\"Javob\" scope=\"row\"><span class=\"card-cell-label\">Javob</span>503 · <code>api_error</code></th><td data-cell-label=\"Shart\"><span class=\"card-cell-label\">Shart</span>Ta’minotchining aynan shu yo‘nalishi mavjud emas.</td><td data-cell-label=\"Keyingi qadam\"><span class=\"card-cell-label\">Keyingi qadam</span>Yo‘nalishni tuzatish uchun javobni saqlang.</td></tr><tr><th data-cell-label=\"Javob\" scope=\"row\"><span class=\"card-cell-label\">Javob</span>503 · <code>result_pending_check</code></th><td data-cell-label=\"Shart\"><span class=\"card-cell-label\">Shart</span>Dastlabki natijani tekshirish kerak; X-Should-Retry:false.</td><td data-cell-label=\"Keyingi qadam\"><span class=\"card-cell-label\">Keyingi qadam</span>Dastlabki operation_id/id ni saqlang va uning holatini o‘qing; dastlabki POST ni hech qachon takrorlamang.</td></tr><tr><th data-cell-label=\"Javob\" scope=\"row\"><span class=\"card-cell-label\">Javob</span>404 · <code>not_found</code></th><td data-cell-label=\"Shart\"><span class=\"card-cell-label\">Shart</span>Paket holatini tekshirish operatsiyasi mavjud emas yoki boshqa foydalanuvchi/kalit/guruhga tegishli.</td><td data-cell-label=\"Keyingi qadam\"><span class=\"card-cell-label\">Keyingi qadam</span>Aynan dastlabki id va o‘sha foydalanuvchi/kalit/guruhdan foydalaning.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">Taxalluslar</h3><h4>Model taxalluslari</h4><p class=\"note-s\"><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=moonshotai%2Fkimi-k3%3Abatch&amp;route=Ultra&amp;caller=moonshotai%2Fkimi-k3%3Abatch&amp;fmt=batches\"><code>moonshotai/kimi-k3:batch</code></a></span></p><h4>Usul yo‘llari taxalluslari</h4><p class=\"note-s\">Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.</p><h4>Chaqirish uchun tegishli ID lar</h4><p class=\"note-s\"><a href=\"#m=moonshotai%2Fkimi-k3%3Abatch&amp;route=Ultra&amp;caller=moonshotai%2Fkimi-k3%3Abatch&amp;fmt=batches\"><code>moonshotai/kimi-k3:batch</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "moonshotai/kimi-k3:batch",
        "fmt": "batches",
        "http": "POST",
        "path": "/v1/batches",
        "request_model_id": "moonshotai/kimi-k3:batch",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|batches|/v1/batches|moonshotai%2Fkimi-k3%3Abatch",
      "ordinal": 0,
      "rawMethod": {
        "available": null,
        "cache_read": 0.456,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Preserve full JSON and every result; provider real IDs are only read from actual returned responses.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "Hujjatlarda ko‘rsatilgan, so‘rovga bevosita kiritiladigan tuzilma yaroqsiz, kalitlar takrorlangan, element identifikatori noto‘g‘ri yoki so‘rov modelning sozlangan imkoniyatlariga zid.",
                "http_status": 400,
                "recovery": "Har qanday yangi yuborishdan oldin ko‘rsatilgan maydonlarni tuzating.",
                "type": "invalid_request_error"
              },
              {
                "code": null,
                "condition": "API kaliti yaroqsiz.",
                "http_status": 401,
                "recovery": "Foydalanishga ruxsat berilgan Ailoot kalitidan foydalaning.",
                "type": "authentication_error"
              },
              {
                "code": null,
                "condition": "Paketli ishlov berish guruhi mavjud emas.",
                "http_status": 403,
                "recovery": "Kalit/guruhning foydalanish huquqini tekshiring.",
                "type": "permission_error"
              },
              {
                "code": null,
                "condition": "Paketli ishlov berish to‘lovi balansdan yechiladi; obuna orqali yaratish rad etiladi.",
                "http_status": 422,
                "recovery": "Foydalanishga ruxsat berilgan, to‘lovi balansdan yechiladigan guruhdan foydalaning.",
                "type": "invalid_request_error"
              },
              {
                "code": null,
                "condition": "Paket kirish ma’lumotlari uchun narx hisoblab bo‘lmaydi.",
                "http_status": 422,
                "recovery": "Javobni saqlang; tegishli API oilasi uchun hujjatlarda belgilangan kirish ma’lumotlaridan foydalaning.",
                "type": "price_unavailable"
              },
              {
                "code": null,
                "condition": "Paketli ishlov berish uchun zaxira mavjud emas.",
                "http_status": 402,
                "recovery": "Yangi so‘rovdan oldin so‘rovni qabul qilishga ruxsat masalasini hal qiling.",
                "type": "billing_error"
              },
              {
                "code": null,
                "condition": "Paketli ishlov berish usulining narxi yoki tizimning ichki tariflari mavjud emas.",
                "http_status": 503,
                "recovery": "Javobni saqlang; narxlarni almashtirmang.",
                "type": "price_unavailable"
              },
              {
                "code": null,
                "condition": "Ta’minotchining aynan shu yo‘nalishi mavjud emas.",
                "http_status": 503,
                "recovery": "Yo‘nalishni tuzatish uchun javobni saqlang.",
                "type": "api_error"
              },
              {
                "code": "result_pending_check",
                "condition": "Dastlabki natijani tekshirish kerak; X-Should-Retry:false.",
                "http_status": 503,
                "recovery": "Dastlabki operation_id/id ni saqlang va uning holatini o‘qing; dastlabki POST ni hech qachon takrorlamang.",
                "type": null
              },
              {
                "code": "not_found",
                "condition": "Paket holatini tekshirish operatsiyasi mavjud emas yoki boshqa foydalanuvchi/kalit/guruhga tegishli.",
                "http_status": 404,
                "recovery": "Aynan dastlabki id va o‘sha foydalanuvchi/kalit/guruhdan foydalaning.",
                "type": null
              }
            ],
            "example_body": {
              "endpoint": "/v1/chat/completions",
              "model": "moonshotai/kimi-k3:batch",
              "requests": [
                {
                  "body": {
                    "max_tokens": 16,
                    "messages": [
                      {
                        "content": "Hello!",
                        "role": "user"
                      }
                    ]
                  },
                  "custom_id": "req-0001"
                }
              ]
            },
            "input_constraints": [
              "Use the exact shown :batch model ID.",
              "Each custom_id must be nonempty and unique within the batch.",
              "Keep requests last in the serialized body; duplicate JSON keys are rejected.",
              "Each body.model is omitted or equals the exact batch caller or its documented base ID.",
              "Per-item provider, service_tier and input_type are outside this batch profile.",
              "stream is omitted or false.",
              "Supply text messages for this Chat batch profile; image/audio/file/video objects, hosted tools and cache-control fields are outside this profile.",
              "If body.model is present, use only the exact caller or wire ID listed here; no suffix conversion is needed.",
              "For google/ wire IDs, all items use an identical response_format."
            ],
            "outputs": {
              "all_results": "Dastlabki holat haqidagi to‘liq JSON ni, har bir natija/custom_id ni va to‘liq javob yoki xato tanasini saqlang. Tugallangan results[] ni hech narsani filtrlab tashlamasdan JSONL sifatida saqlang.",
              "enclosing_family": "batch",
              "family": "text",
              "fields": [
                {
                  "name": "results[].custom_id",
                  "type": "string"
                },
                {
                  "name": "results[].response.body.choices[].message.content",
                  "type": "string|null"
                },
                {
                  "name": "results[].error",
                  "type": "object|null"
                },
                {
                  "name": "usage",
                  "type": "object|null"
                },
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "endpoint",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "request_counts",
                  "type": "object"
                },
                {
                  "description": null,
                  "name": "results[].id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "results[].response.status_code",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "results[].response.request_id",
                  "type": "string"
                }
              ],
              "format": "Javobga bevosita kiritilgan results[].response.body JSON ma’lumotlari"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "/v1/chat/completions"
                ],
                "enum_known": true,
                "name": "endpoint",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "moonshotai/kimi-k3:batch"
                ],
                "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": "requests",
                "required": true,
                "type": "batch_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "requests[].custom_id",
                "required": true,
                "type": "string",
                "unique_within_batch": true
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "requests[].body.messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "24h"
                ],
                "enum_known": true,
                "name": "completion_window",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "provider",
                "required": false,
                "type": "object|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "moonshotai/kimi-k3:batch",
                  "moonshotai/kimi-k3"
                ],
                "enum_known": true,
                "name": "requests[].body.model",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  [
                    "deepinfra/bf16"
                  ]
                ],
                "enum_known": true,
                "name": "provider.only",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  false,
                  null
                ],
                "enum_known": true,
                "name": "provider.allow_fallbacks",
                "required": false,
                "type": "boolean|null"
              }
            ],
            "provider_policy": {
              "allow_fallbacks": false,
              "configured_only": [
                "deepinfra/bf16"
              ],
              "per_item_override": false,
              "when_omitted": "Current Source injects the exact persisted declaration before fresh submission."
            },
            "request_schema": {
              "additionalProperties": false,
              "properties": {
                "completion_window": {
                  "enum": [
                    "24h"
                  ],
                  "type": "string"
                },
                "endpoint": {
                  "enum": [
                    "/v1/chat/completions"
                  ],
                  "type": "string"
                },
                "model": {
                  "enum": [
                    "moonshotai/kimi-k3:batch"
                  ],
                  "type": "string"
                },
                "provider": {
                  "additionalProperties": false,
                  "properties": {
                    "allow_fallbacks": {
                      "enum": [
                        false,
                        null
                      ],
                      "type": [
                        "boolean",
                        "null"
                      ]
                    },
                    "only": {
                      "enum": [
                        [
                          "deepinfra/bf16"
                        ]
                      ],
                      "items": {
                        "enum": [
                          "deepinfra/bf16"
                        ],
                        "type": "string"
                      },
                      "maxItems": 1,
                      "minItems": 1,
                      "type": "array"
                    }
                  },
                  "type": [
                    "object",
                    "null"
                  ]
                },
                "requests": {
                  "items": {
                    "additionalProperties": false,
                    "properties": {
                      "body": {
                        "additionalProperties": true,
                        "properties": {
                          "max_tokens": {
                            "minimum": 1,
                            "type": "integer"
                          },
                          "messages": {
                            "items": {
                              "properties": {
                                "content": {
                                  "type": "string"
                                },
                                "role": {
                                  "type": "string"
                                }
                              },
                              "required": [
                                "role",
                                "content"
                              ],
                              "type": "object"
                            },
                            "minItems": 1,
                            "type": "array"
                          },
                          "model": {
                            "enum": [
                              "moonshotai/kimi-k3:batch",
                              "moonshotai/kimi-k3"
                            ],
                            "type": "string"
                          }
                        },
                        "required": [
                          "messages"
                        ],
                        "type": "object"
                      },
                      "custom_id": {
                        "minLength": 1,
                        "type": "string"
                      }
                    },
                    "required": [
                      "custom_id",
                      "body"
                    ],
                    "type": "object"
                  },
                  "minItems": 1,
                  "type": "array"
                }
              },
              "required": [
                "endpoint",
                "model",
                "requests"
              ],
              "type": "object"
            },
            "schema_template": {
              "endpoint": "/v1/chat/completions",
              "model": "moonshotai/kimi-k3:batch",
              "requests": [
                {
                  "body": {
                    "max_tokens": 16,
                    "messages": [
                      {
                        "content": "Hello!",
                        "role": "user"
                      }
                    ]
                  },
                  "custom_id": "req-0001"
                }
              ]
            },
            "unsupported": [
              "Files/input_file_id batch upload workflow",
              "active cancel route",
              "public batch list/delete/result-download route",
              "model-name-derived capability or weights equivalence"
            ]
          },
          "input": {
            "content_type": "application/json",
            "file_material": "Chaqiruvchi haqiqiy UTF-8 JSONL ma’lumotlarini mahalliy tarzda requests[] ichiga o‘qishi mumkin. Yuklash maqsadi, input_file_id yoki faylga havola ishlatilmaydi. Mijoz materiali yo‘q yoki bo‘sh bo‘lsa, tayyorlash POST dan oldin to‘xtaydi.",
            "material_types": [
              "text"
            ],
            "optional_controls": [
              "provider.only",
              "provider.allow_fallbacks",
              "completion_window"
            ],
            "representation": "So‘rovga bevosita kiritilgan requests[] massivi; har bir elementda custom_id va body mavjud.",
            "request_endpoint_profile": "/v1/chat/completions",
            "required": [
              "endpoint",
              "model",
              "requests"
            ],
            "schema_scope": "Hujjatlarda ko‘rsatilgan Batch tuzilmasiga bevosita kiritilgan matnli Chat Completions so‘rovlarining tanalari.",
            "serialization_order": [
              "endpoint",
              "model",
              "provider (agar berilgan bo‘lsa)",
              "completion_window (agar berilgan bo‘lsa)",
              "requests eng oxirida"
            ]
          },
          "lifecycle": {
            "cancel": null,
            "create": {
              "accepted_status": 202,
              "http": "POST",
              "path": "/v1/batches"
            },
            "delete": null,
            "file_upload": null,
            "mode": "asynchronous",
            "observed_status_values": [
              "validating",
              "in_progress",
              "finalizing",
              "completed",
              "failed",
              "expired",
              "cancelling",
              "cancelled"
            ],
            "owned_results": {
              "behavior": "Completed results are saved as owned JSONL, read back byte-for-byte and registered in the existing media library before publication after settlement. Status returns inline results; no separate Batch download route is added.",
              "format": "application/x-ndjson",
              "public_url_field_in_status": null
            },
            "status": {
              "http": "GET",
              "id_source": "Dastlabki yaratish javobida amalda qaytarilgan response.id; aynan o‘sha foydalanuvchi/kalit/guruh",
              "path": "/v1/batches/{operation_id}"
            },
            "terminal": [
              "completed",
              "failed",
              "expired",
              "cancelled"
            ],
            "unknown": "Dastlabki operatsiya ID sini saqlang. 503 result_pending_check javobida X-Should-Retry:false mavjud; natijasi noma’lum bo‘lgan dastlabki paketni hech qachon qayta yubormang."
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/batches"
          },
          "output": {
            "all_results": "Preserve the full original status JSON, every result/custom_id and complete response or error body. Save completed results[] as JSONL without filtering.",
            "family": "batch",
            "format": "JSON; completed results[] are returned inline and can be saved as JSONL."
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Tokenlar uchun bazaviy tariflar",
            "units": [
              {
                "amount": "0.00456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.00000456",
                "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": "0.0228000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000228",
                "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": "0.000456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.000000456",
                "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": "So‘rov uzunligi bo‘yicha 1-daraja",
            "units": [
              {
                "amount": "0.00456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.00000456",
                "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": "0.0228000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000228",
                "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": "0.000456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.000000456",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json\nfrom pathlib import Path\nbody=json.loads('{\"endpoint\":\"/v1/chat/completions\",\"model\":\"moonshotai/kimi-k3:batch\",\"requests\":[{\"custom_id\":\"req-0001\",\"body\":{\"messages\":[{\"role\":\"user\",\"content\":\"Hello!\"}],\"max_tokens\":16}}]}')\nPath(\"batch-request.json\").write_text(json.dumps(body,ensure_ascii=False),encoding=\"utf-8\")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @batch-request.json -D batch-response-headers.txt -o batch-create-response.json\n",
            "label": "curl · retained fixture",
            "language": "bash"
          },
          {
            "code": "import json, os\nfrom pathlib import Path\nfrom urllib.request import Request, urlopen\n\ndef prepare_requests(customer_path):\n    path = Path(customer_path)\n    if not path.is_file(): raise ValueError(\"Customer JSONL file is missing\")\n    items = [json.loads(line) for line in path.read_text(encoding=\"utf-8\").splitlines() if line.strip()]\n    if not items: raise ValueError(\"Customer JSONL contains no requests\")\n    ids = set()\n    for item in items:\n        if set(item) != {\"custom_id\", \"body\"}: raise ValueError(\"Each item needs custom_id and body\")\n        cid = item[\"custom_id\"]\n        if not isinstance(cid, str) or not cid.strip() or cid in ids: raise ValueError(\"custom_id must be nonempty and unique\")\n        ids.add(cid)\n        if not isinstance(item[\"body\"], dict) or not item[\"body\"].get(\"messages\"): raise ValueError(\"Supply actual text messages\")\n        supplied_model = item[\"body\"].get(\"model\")\n        if supplied_model is not None and supplied_model not in ['moonshotai/kimi-k3:batch', 'moonshotai/kimi-k3']: raise ValueError(\"body.model must be an exact documented caller or wire ID\")\n    return {\"endpoint\":\"/v1/chat/completions\", \"model\":\"moonshotai/kimi-k3:batch\", \"requests\":items}\n\nif __name__ == \"__main__\":\n    material = os.environ.get(\"AILOOT_BATCH_REQUESTS_JSONL\", \"\")\n    if not material: raise SystemExit(\"Set AILOOT_BATCH_REQUESTS_JSONL to your actual customer file\")\n    body = prepare_requests(material)\n    key = os.environ.get(\"AILOOT_API_KEY\", \"\")\n    if not key: raise SystemExit(\"Set AILOOT_API_KEY\")\n    request = Request(\"https://api.ailoot.ai/v1/batches\", data=json.dumps(body, ensure_ascii=False).encode(\"utf-8\"), headers={\"Authorization\":\"Bearer \" + key, \"Content-Type\":\"application/json\"}, method=\"POST\")\n    with urlopen(request) as response:\n        raw = response.read()\n        Path(\"batch-create-response.json\").write_bytes(raw)\n        print(raw.decode(\"utf-8\"))\n",
            "label": "Python HTTP · actual customer JSONL",
            "language": "python"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nBATCH_OPERATION_ID=\"$(python3 - <<'PY_ID'\nimport json\nfrom pathlib import Path\nfrom urllib.parse import quote\nresponse = json.loads(Path(\"batch-create-response.json\").read_text(encoding=\"utf-8\"))\noperation = response.get(\"id\")\nif not isinstance(operation, str) or not operation: raise SystemExit(\"No actual original operation ID; preserve the response and do not resubmit\")\nprint(quote(operation, safe=\"\"))\nPY_ID\n)\"\ncurl --fail-with-body --silent --show-error \"https://api.ailoot.ai/v1/batches/$BATCH_OPERATION_ID\" \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -o batch-status-response.json\n",
            "label": "curl · original operation status",
            "language": "bash"
          },
          {
            "code": "import json\nfrom pathlib import Path\nraw = Path(\"batch-status-response.json\").read_bytes()\nresponse = json.loads(raw)\nif response.get(\"status\") != \"completed\":\n    raise SystemExit(\"Keep the original operation; read its status without resubmitting\")\nresults = response.get(\"results\")\nif not isinstance(results, list) or not results:\n    raise SystemExit(\"Preserve the original response; completed results are missing\")\nPath(\"batch-results.jsonl\").write_text(\"\".join(json.dumps(item, ensure_ascii=False) + \"\\n\" for item in results), encoding=\"utf-8\")\n# Preserve batch-status-response.json with aggregate usage and every result/error.\n",
            "label": "Python · save every completed result",
            "language": "python"
          }
        ],
        "family": "batch",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "batches",
        "hints": [
          "Read your actual request items before submission; inline requests are required.",
          "Keep the returned operation ID and every result. Never replay an unknown submission."
        ],
        "http": "POST",
        "in": 4.56,
        "input": [
          "text"
        ],
        "label": "Paketli ishlov berish",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "out": 22.8,
        "output": [
          "text"
        ],
        "path": "/v1/batches",
        "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"
          },
          {
            "label": "Explicit cache pricing",
            "value": "Not enabled",
            "when": "When explicit cache is requested"
          }
        ],
        "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": "0.00456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.00000456",
                "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": "0.0228000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000228",
                "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": "0.000456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.000000456",
                "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": "0.00456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.00000456",
                "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": "0.0228000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000228",
                "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": "0.000456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.000000456",
                "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": "moonshotai/kimi-k3:batch",
        "route_label": "Ultra",
        "status_reads": [
          "GET /v1/batches/{operation_id}"
        ],
        "tiers": [
          {
            "cache_read": 0.456,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 4.56,
            "input_multiplier": null,
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "out": 22.8,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.00456000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.00000456",
            "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": "0.0228000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.0000228",
            "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": "0.000456000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.000000456",
            "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": "moonshotai/kimi-k3:batch",
  "nativeProvenance": {
    "input_facts_canonical_sha256": "3e6bb5fec0723dc239db1a177077b041361aeac3b95df3319ff694f2f13d0c9d",
    "input_html_sha256": "917a2823c907f6a0c27f59beef9436a968cac434cbd37025ad42ebc952fa874e",
    "private_audit_sha256": "0667d031a4cbcbb0d27a9d324dd7275323a06855f98a1511a3a091c48ef93f94",
    "role": "historical-normalized-input-audit-hashes",
    "schema": "ailoot-native-model-provenance-v2"
  },
  "page": {
    "canonical": "https://ailoot.ai/models/uz/moonshotai-kimi-k3-u003a-batch/",
    "description": "Kimi K3 — Moonshot AI kompaniyasining uzun dasturlash vazifalari va bilim ishi uchun boshidan multimodal yaratilgan mulohaza modeli. U matn, tasvir va videoni o‘qiydi, matn yaratadi hamda 1 048 576 tokenli kontekst va qadamlar bo‘ylab saqlanadigan fikrlash tarixi bilan vositalarga tayangan jarayonlarni qo‘llab-quvvatlaydi.",
    "locale": "uz",
    "md_url": "https://ailoot.ai/models/uz/moonshotai-kimi-k3-u003a-batch/index.md",
    "title": "MoonshotAI: Kimi K3 (batch) — Ailoot",
    "url": "https://ailoot.ai/models/uz/moonshotai-kimi-k3-u003a-batch/"
  },
  "rawModel": {
    "about": "Kimi K3 — Moonshot AI kompaniyasining uzoq davom etadigan dasturlash, bilim ishi va mulohaza uchun ochiq vaznli multimodal agent modeli. U matnni tasvir va videoni bevosita vizual tushunish bilan birlashtirib, matnli javob yoki vosita so‘rovini yaratadi. Ishlab chiqaruvchi uzun muhandislik seanslari, katta repozitoriylar hamda kod bilan birga skrinshot yoki vizual qayta aloqadan foydalanadigan vazifalarni ta’kidlaydi. Foydali topshiriq kerakli material, foydalaniladigan dalillar va ish tugallanganini belgilaydigan shartni aniqlaydi.\n\n### Arxitektura va uzun kontekst\n\nModel kartasi jami 2,8 trillion parametr va 104 milliard faollashtirilgan parametrli siyrak Mixture of Expertsni ta’riflaydi. Uning Stable LatentMoE dizayni har bir token uchun 896 ekspertdan 16 tasini tanlaydi, bunda Kimi Delta Attention va Attention Residualsdan darvozali diqqat bilan birga foydalanadi. Aniq kontekst uzunligi 1 048 576 token. Bu katta vazifa konteksti uchun joy, manba chegaralarini yoki natija uchun kerakli joyni e’tiborsiz qoldirishga sabab emas.\n\nE’lon qilingan asl material MXFP4 vaznlari va MXFP8 faollashuvlari bilan kvantlashni hisobga olgan o‘qitishdan foydalanadi. Bu ishlab chiqaruvchining reliz formati bo‘lib, alohida taqdim etilgan kvantlangan nashrdan yoki muayyan yo‘nalish modelga qanday xizmat ko‘rsatishi haqidagi da’vodan farq qiladi. Ochiq vaznlar va katta parametrlar soni faol parametrlar sonini umumiy saqlash yoki apparat talabiga aylantirmaydi.\n\n### Katta dasturlash vazifasini tayyorlang\n\nTegishli repozitoriy materiali, mavjud xatti-harakat, so‘ralgan o‘zgarish va moslik cheklovlarini bering. Natija ta’sir qilishi shart bo‘lgan fayllar yoki interfeysni, muvaffaqiyatni belgilaydigan tekshiruvlarni hamda muammoni ko‘rsatadigan berilgan xato yoki kirishni belgilang. Foydali natija hech qachon bajarilmagan harakatlar tavsifi emas, tushuntirish va haqiqatan ishlagan tekshiruvlardan dalil bilan aniq yo‘naltirilgan kod o‘zgarishi bo‘lishi mumkin.\n\nVizual ishlab chiqish vazifasida tegishli kod va aniq nomuvofiqlik bilan birga skrinshot yoki kerakli natijaning ravshan ko‘rinishini kiriting. Ishlab chiqaruvchi frontend ishi, o‘yinlar va CADni qamrab oladigan, vizual qayta aloqadan foydalanadigan jarayonlarni ta’riflaydi. Kodni kuzatilgan natijaga bog‘laydigan o‘zgarishni so‘rang va yetkazilgan materialni u bilan tekshirish uchun tayanch manbani saqlang.\n\n### Tasvirlar, video va bilim ishini tayyorlash\n\nIshlab chiqaruvchining tezkor boshlash yo‘riqnomasi vizual xabarlar uchun turi belgilangan mazmun obyektlaridan foydalanadi; content massiv bo‘lib, ushbu massivning ketma-ket yozilgan matnli ifodasi emas. Uning tasvir jarayoni ommaviy tasvir manzili o‘rniga kodlangan tasvir ma’lumoti yoki qo‘llanadigan fayl havolasidan foydalanadi. Video misoli video faylini yuklaydi va hosil bo‘lgan havolani uning mazmuni haqidagi savol bilan beradi. O‘qiladigan manbani bering hamda muhim kuzatuv, oraliq yoki bog‘lanishni belgilang. Ishlab chiqaruvchining vizual jarayoni JPEG, PNG, GIF, WebP, BMP, HEIC va HEIF tasvirlarini hamda MP4, MPEG, MOV, AVI, FLV, MPG, WebM, WMV va 3GPP videolarini qabul qiladi. Animatsiyalangan GIF yoki WebP video sifatida dekodlanishi mumkin. SVG manbasini matn sifatida bering. Ishlab chiqaruvchi tasvirlar uchun 4096 × 2160 gacha, video uchun 1920 × 1080 gacha o‘lchamlarni tavsiya qiladi; bular rad etish chegaralari emas, aniqlik tavsiyalaridir. So‘rov tanasini hujjatlashtirilgan 100M hajm chegarasi ichida saqlang va katta yoki qayta-qayta ishlatiladigan mediani fayl sifatida yuklang.\n\nHujjatlarga boy tadqiqotda manbalarni belgilang va yakuniy hisobot javob berishi kerak bo‘lgan savollarni ayting. Video tushuntirishida cheklanmagan izoh so‘rash o‘rniga tahlil qilinadigan hodisalar yoki ketma-ketlikni ko‘rsating. K3 vizual mazmundan mulohaza uchun dalil sifatida foydalanib, matn yoki vosita so‘rovlarini qaytaradi. Ilova alohida tasvir yoki video materiallari yaratish uchun ushbu so‘rovlarni media vositalariga uzatishi mumkin.\n\n### Fikrlash doimo yoqilgan\n\nK3ning ishlab chiqaruvchi interfeysida fikrlash doimo yoqilgan. Yuqori darajadagi reasoning_effort sozlamasi low, high va max qiymatlarini qabul qiladi, standart qiymat max. Bu tanlovlar modelga xos; fikrlamaslik sozlamasi yoki boshqa oilaning daraja qiymatini taxmin qilmaslik kerak. Ishlab chiqaruvchining ko‘chirish yo‘riqnomasi eski thinking konfiguratsiyasini ko‘chirish o‘rniga reasoning_effort dan foydalanish bilan K3ni K2.xdan farqlaydi.\n\nIshlab chiqaruvchi oqimli natijalarda reasoning_content va yakuniy javob content qismlarini alohida hujjatlashtiradi. Ko‘p navbatli suhbat yoki vosita jarayoni uchun qaytgan yordamchi xabari to‘liq, jumladan reasoning_content va tool_calls bilan o‘zgartirilmay qayta berilishini talab qiladi. Faqat ko‘rinadigan yakuniy javobni saqlash modelning saqlangan fikrlash jarayoni keyingi qadamda kutadigan ma’lumotni yo‘qotadi.\n\n### Tuzilmali yakuniy javoblar va qisman davom ettirish\n\nTezkor boshlash yo‘riqnomasi yakuniy xabar mazmuni uchun qat’iy JSON-schema natijasini hujjatlashtiradi. Maydonlar va ularning ma’nolarini ilovaga kerakli material atrofida belgilang hamda yakuniy mazmunni mulohaza maydoni bilan birlashtirmasdan tahlil qiling. Tuzilmali natija berilgan materialdan ajratilgan ma’lumot yoki belgilangan hisobot shaklini ifodalashi mumkin; sxema uning shaklini cheklaydi, qiymatlar to‘g‘riligini esa manba dalillari belgilaydi.\n\nPartial rejimi berilgan matn prefiksini davom ettirishi mumkin. Ishlab chiqaruvchi misoli tarix oxiriga qisman yordamchi xabarini joylashtiradi va ko‘rsatish uchun shu prefiksni qaytgan davom bilan birlashtiradi. Zarur material mazmunli qat’iy boshlanishga ega bo‘lsa, prefiksni yaratilgan qolgan qismdan farqlagan holda bundan foydalaning.\n\n### Vositalar va ularning natijalari uzluksizligi\n\nK3 maxsus funksiya vositalarini qo‘llab-quvvatlaydi. Ishlab chiqaruvchi misoli birinchi navbatda vositani talab qiladi, yordamchining to‘liq xabarini saqlaydi, har bir qaytgan chaqiruvni bajaradi va yakuniy javobni so‘rashdan oldin mos vosita natijasini qo‘shadi. Taklif etilgan chaqiruv amal muvaffaqiyatli bo‘lganining dalili emas; haqiqiy qaytgan natija keyingi qadam uchun dalilga aylanadi.\n\nUning dinamik yuklash jarayoni xabar tarixining muayyan joyida to‘liq vosita ta’rifini kiritadi. Ta’rifga uning nomi, maqsadi va parametrlari kerak; server bu e’lonni mustaqil saqlamagani uchun u keyingi tarixda ham qolishi shart. Uzun vazifa allaqachon tugallangan ishdan davom etishi uchun vosita imkoniyatlari, berilgan argumentlar va haqiqiy kuzatuvlarni bog‘liq saqlang.\n\n### Chiqish boshqaruvlari va takroriy kontekst\n\nIshlab chiqaruvchi 131 072 tokenli standart yaratish limitini hujjatlashtiradi; u modelning umumiy kontekst cheklovlari ichida 1 048 576 gacha sozlanadi. Uning joriy K3 API qiymatlari qat’iy: temperature 1.0, top_p 0.95, bitta natija, presence va frequency jarimalari nol; chaqiruvchilarga ushbu namuna olish boshqaruvlarini yubormaslik aytiladi. Bular boshqa joyga ko‘chiriladigan sozlanadigan boshqaruvlar ro‘yxati emas, aynan ishlab chiqaruvchi katalog variantining sozlamalari.\n\nMos takroriy prefikslar uchun kontekst keshlash avtomatik; hujjatlashtirilgan TTL tanlovlari 5 daqiqa va 1 soat, standart esa 5 daqiqa. Qisman kesh bloklari keshga tushmagan bo‘lib qoladi. Qayta ishlatiladigan kontekstni barqaror saqlang va faqat takrorlangan matnga qarab keshga tushganini da’vo qilish o‘rniga haqiqiy sarfni tekshiring. Yakuniy material uchun berilgan manbalar, haqiqiy vosita dalillari va zarur chiqish tuzilmasini saqlang hamda uzun javob yoki muhandislik natijasi aytilgan tugallanish mezonlariga mosligini tekshiring.",
    "alias_of": null,
    "aliases": [],
    "author": "MoonshotAI",
    "capabilities": {
      "context_length": 1048576,
      "manufacturer_input": [
        "text",
        "image",
        "video"
      ],
      "manufacturer_output": [
        "text"
      ]
    },
    "card_routes": [
      {
        "label": "Ultra",
        "rates": [
          {
            "amount": "0.00456000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.00000456",
            "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": "0.0228000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.0000228",
            "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": [
      "batches"
    ],
    "id": "moonshotai/kimi-k3:batch",
    "input": [
      "text"
    ],
    "kind": "text",
    "max_out": null,
    "methods": [
      {
        "available": null,
        "cache_read": 0.456,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Preserve full JSON and every result; provider real IDs are only read from actual returned responses.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "Hujjatlarda ko‘rsatilgan, so‘rovga bevosita kiritiladigan tuzilma yaroqsiz, kalitlar takrorlangan, element identifikatori noto‘g‘ri yoki so‘rov modelning sozlangan imkoniyatlariga zid.",
                "http_status": 400,
                "recovery": "Har qanday yangi yuborishdan oldin ko‘rsatilgan maydonlarni tuzating.",
                "type": "invalid_request_error"
              },
              {
                "code": null,
                "condition": "API kaliti yaroqsiz.",
                "http_status": 401,
                "recovery": "Foydalanishga ruxsat berilgan Ailoot kalitidan foydalaning.",
                "type": "authentication_error"
              },
              {
                "code": null,
                "condition": "Paketli ishlov berish guruhi mavjud emas.",
                "http_status": 403,
                "recovery": "Kalit/guruhning foydalanish huquqini tekshiring.",
                "type": "permission_error"
              },
              {
                "code": null,
                "condition": "Paketli ishlov berish to‘lovi balansdan yechiladi; obuna orqali yaratish rad etiladi.",
                "http_status": 422,
                "recovery": "Foydalanishga ruxsat berilgan, to‘lovi balansdan yechiladigan guruhdan foydalaning.",
                "type": "invalid_request_error"
              },
              {
                "code": null,
                "condition": "Paket kirish ma’lumotlari uchun narx hisoblab bo‘lmaydi.",
                "http_status": 422,
                "recovery": "Javobni saqlang; tegishli API oilasi uchun hujjatlarda belgilangan kirish ma’lumotlaridan foydalaning.",
                "type": "price_unavailable"
              },
              {
                "code": null,
                "condition": "Paketli ishlov berish uchun zaxira mavjud emas.",
                "http_status": 402,
                "recovery": "Yangi so‘rovdan oldin so‘rovni qabul qilishga ruxsat masalasini hal qiling.",
                "type": "billing_error"
              },
              {
                "code": null,
                "condition": "Paketli ishlov berish usulining narxi yoki tizimning ichki tariflari mavjud emas.",
                "http_status": 503,
                "recovery": "Javobni saqlang; narxlarni almashtirmang.",
                "type": "price_unavailable"
              },
              {
                "code": null,
                "condition": "Ta’minotchining aynan shu yo‘nalishi mavjud emas.",
                "http_status": 503,
                "recovery": "Yo‘nalishni tuzatish uchun javobni saqlang.",
                "type": "api_error"
              },
              {
                "code": "result_pending_check",
                "condition": "Dastlabki natijani tekshirish kerak; X-Should-Retry:false.",
                "http_status": 503,
                "recovery": "Dastlabki operation_id/id ni saqlang va uning holatini o‘qing; dastlabki POST ni hech qachon takrorlamang.",
                "type": null
              },
              {
                "code": "not_found",
                "condition": "Paket holatini tekshirish operatsiyasi mavjud emas yoki boshqa foydalanuvchi/kalit/guruhga tegishli.",
                "http_status": 404,
                "recovery": "Aynan dastlabki id va o‘sha foydalanuvchi/kalit/guruhdan foydalaning.",
                "type": null
              }
            ],
            "example_body": {
              "endpoint": "/v1/chat/completions",
              "model": "moonshotai/kimi-k3:batch",
              "requests": [
                {
                  "body": {
                    "max_tokens": 16,
                    "messages": [
                      {
                        "content": "Hello!",
                        "role": "user"
                      }
                    ]
                  },
                  "custom_id": "req-0001"
                }
              ]
            },
            "input_constraints": [
              "Use the exact shown :batch model ID.",
              "Each custom_id must be nonempty and unique within the batch.",
              "Keep requests last in the serialized body; duplicate JSON keys are rejected.",
              "Each body.model is omitted or equals the exact batch caller or its documented base ID.",
              "Per-item provider, service_tier and input_type are outside this batch profile.",
              "stream is omitted or false.",
              "Supply text messages for this Chat batch profile; image/audio/file/video objects, hosted tools and cache-control fields are outside this profile.",
              "If body.model is present, use only the exact caller or wire ID listed here; no suffix conversion is needed.",
              "For google/ wire IDs, all items use an identical response_format."
            ],
            "outputs": {
              "all_results": "Dastlabki holat haqidagi to‘liq JSON ni, har bir natija/custom_id ni va to‘liq javob yoki xato tanasini saqlang. Tugallangan results[] ni hech narsani filtrlab tashlamasdan JSONL sifatida saqlang.",
              "enclosing_family": "batch",
              "family": "text",
              "fields": [
                {
                  "name": "results[].custom_id",
                  "type": "string"
                },
                {
                  "name": "results[].response.body.choices[].message.content",
                  "type": "string|null"
                },
                {
                  "name": "results[].error",
                  "type": "object|null"
                },
                {
                  "name": "usage",
                  "type": "object|null"
                },
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "endpoint",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "request_counts",
                  "type": "object"
                },
                {
                  "description": null,
                  "name": "results[].id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "results[].response.status_code",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "results[].response.request_id",
                  "type": "string"
                }
              ],
              "format": "Javobga bevosita kiritilgan results[].response.body JSON ma’lumotlari"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "/v1/chat/completions"
                ],
                "enum_known": true,
                "name": "endpoint",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "moonshotai/kimi-k3:batch"
                ],
                "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": "requests",
                "required": true,
                "type": "batch_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "requests[].custom_id",
                "required": true,
                "type": "string",
                "unique_within_batch": true
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "requests[].body.messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "24h"
                ],
                "enum_known": true,
                "name": "completion_window",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "provider",
                "required": false,
                "type": "object|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "moonshotai/kimi-k3:batch",
                  "moonshotai/kimi-k3"
                ],
                "enum_known": true,
                "name": "requests[].body.model",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  [
                    "deepinfra/bf16"
                  ]
                ],
                "enum_known": true,
                "name": "provider.only",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  false,
                  null
                ],
                "enum_known": true,
                "name": "provider.allow_fallbacks",
                "required": false,
                "type": "boolean|null"
              }
            ],
            "provider_policy": {
              "allow_fallbacks": false,
              "configured_only": [
                "deepinfra/bf16"
              ],
              "per_item_override": false,
              "when_omitted": "Current Source injects the exact persisted declaration before fresh submission."
            },
            "request_schema": {
              "additionalProperties": false,
              "properties": {
                "completion_window": {
                  "enum": [
                    "24h"
                  ],
                  "type": "string"
                },
                "endpoint": {
                  "enum": [
                    "/v1/chat/completions"
                  ],
                  "type": "string"
                },
                "model": {
                  "enum": [
                    "moonshotai/kimi-k3:batch"
                  ],
                  "type": "string"
                },
                "provider": {
                  "additionalProperties": false,
                  "properties": {
                    "allow_fallbacks": {
                      "enum": [
                        false,
                        null
                      ],
                      "type": [
                        "boolean",
                        "null"
                      ]
                    },
                    "only": {
                      "enum": [
                        [
                          "deepinfra/bf16"
                        ]
                      ],
                      "items": {
                        "enum": [
                          "deepinfra/bf16"
                        ],
                        "type": "string"
                      },
                      "maxItems": 1,
                      "minItems": 1,
                      "type": "array"
                    }
                  },
                  "type": [
                    "object",
                    "null"
                  ]
                },
                "requests": {
                  "items": {
                    "additionalProperties": false,
                    "properties": {
                      "body": {
                        "additionalProperties": true,
                        "properties": {
                          "max_tokens": {
                            "minimum": 1,
                            "type": "integer"
                          },
                          "messages": {
                            "items": {
                              "properties": {
                                "content": {
                                  "type": "string"
                                },
                                "role": {
                                  "type": "string"
                                }
                              },
                              "required": [
                                "role",
                                "content"
                              ],
                              "type": "object"
                            },
                            "minItems": 1,
                            "type": "array"
                          },
                          "model": {
                            "enum": [
                              "moonshotai/kimi-k3:batch",
                              "moonshotai/kimi-k3"
                            ],
                            "type": "string"
                          }
                        },
                        "required": [
                          "messages"
                        ],
                        "type": "object"
                      },
                      "custom_id": {
                        "minLength": 1,
                        "type": "string"
                      }
                    },
                    "required": [
                      "custom_id",
                      "body"
                    ],
                    "type": "object"
                  },
                  "minItems": 1,
                  "type": "array"
                }
              },
              "required": [
                "endpoint",
                "model",
                "requests"
              ],
              "type": "object"
            },
            "schema_template": {
              "endpoint": "/v1/chat/completions",
              "model": "moonshotai/kimi-k3:batch",
              "requests": [
                {
                  "body": {
                    "max_tokens": 16,
                    "messages": [
                      {
                        "content": "Hello!",
                        "role": "user"
                      }
                    ]
                  },
                  "custom_id": "req-0001"
                }
              ]
            },
            "unsupported": [
              "Files/input_file_id batch upload workflow",
              "active cancel route",
              "public batch list/delete/result-download route",
              "model-name-derived capability or weights equivalence"
            ]
          },
          "input": {
            "content_type": "application/json",
            "file_material": "Chaqiruvchi haqiqiy UTF-8 JSONL ma’lumotlarini mahalliy tarzda requests[] ichiga o‘qishi mumkin. Yuklash maqsadi, input_file_id yoki faylga havola ishlatilmaydi. Mijoz materiali yo‘q yoki bo‘sh bo‘lsa, tayyorlash POST dan oldin to‘xtaydi.",
            "material_types": [
              "text"
            ],
            "optional_controls": [
              "provider.only",
              "provider.allow_fallbacks",
              "completion_window"
            ],
            "representation": "So‘rovga bevosita kiritilgan requests[] massivi; har bir elementda custom_id va body mavjud.",
            "request_endpoint_profile": "/v1/chat/completions",
            "required": [
              "endpoint",
              "model",
              "requests"
            ],
            "schema_scope": "Hujjatlarda ko‘rsatilgan Batch tuzilmasiga bevosita kiritilgan matnli Chat Completions so‘rovlarining tanalari.",
            "serialization_order": [
              "endpoint",
              "model",
              "provider (agar berilgan bo‘lsa)",
              "completion_window (agar berilgan bo‘lsa)",
              "requests eng oxirida"
            ]
          },
          "lifecycle": {
            "cancel": null,
            "create": {
              "accepted_status": 202,
              "http": "POST",
              "path": "/v1/batches"
            },
            "delete": null,
            "file_upload": null,
            "mode": "asynchronous",
            "observed_status_values": [
              "validating",
              "in_progress",
              "finalizing",
              "completed",
              "failed",
              "expired",
              "cancelling",
              "cancelled"
            ],
            "owned_results": {
              "behavior": "Completed results are saved as owned JSONL, read back byte-for-byte and registered in the existing media library before publication after settlement. Status returns inline results; no separate Batch download route is added.",
              "format": "application/x-ndjson",
              "public_url_field_in_status": null
            },
            "status": {
              "http": "GET",
              "id_source": "Dastlabki yaratish javobida amalda qaytarilgan response.id; aynan o‘sha foydalanuvchi/kalit/guruh",
              "path": "/v1/batches/{operation_id}"
            },
            "terminal": [
              "completed",
              "failed",
              "expired",
              "cancelled"
            ],
            "unknown": "Dastlabki operatsiya ID sini saqlang. 503 result_pending_check javobida X-Should-Retry:false mavjud; natijasi noma’lum bo‘lgan dastlabki paketni hech qachon qayta yubormang."
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/batches"
          },
          "output": {
            "all_results": "Preserve the full original status JSON, every result/custom_id and complete response or error body. Save completed results[] as JSONL without filtering.",
            "family": "batch",
            "format": "JSON; completed results[] are returned inline and can be saved as JSONL."
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Tokenlar uchun bazaviy tariflar",
            "units": [
              {
                "amount": "0.00456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.00000456",
                "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": "0.0228000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000228",
                "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": "0.000456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.000000456",
                "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": "So‘rov uzunligi bo‘yicha 1-daraja",
            "units": [
              {
                "amount": "0.00456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.00000456",
                "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": "0.0228000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000228",
                "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": "0.000456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.000000456",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json\nfrom pathlib import Path\nbody=json.loads('{\"endpoint\":\"/v1/chat/completions\",\"model\":\"moonshotai/kimi-k3:batch\",\"requests\":[{\"custom_id\":\"req-0001\",\"body\":{\"messages\":[{\"role\":\"user\",\"content\":\"Hello!\"}],\"max_tokens\":16}}]}')\nPath(\"batch-request.json\").write_text(json.dumps(body,ensure_ascii=False),encoding=\"utf-8\")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @batch-request.json -D batch-response-headers.txt -o batch-create-response.json\n",
            "label": "curl · retained fixture",
            "language": "bash"
          },
          {
            "code": "import json, os\nfrom pathlib import Path\nfrom urllib.request import Request, urlopen\n\ndef prepare_requests(customer_path):\n    path = Path(customer_path)\n    if not path.is_file(): raise ValueError(\"Customer JSONL file is missing\")\n    items = [json.loads(line) for line in path.read_text(encoding=\"utf-8\").splitlines() if line.strip()]\n    if not items: raise ValueError(\"Customer JSONL contains no requests\")\n    ids = set()\n    for item in items:\n        if set(item) != {\"custom_id\", \"body\"}: raise ValueError(\"Each item needs custom_id and body\")\n        cid = item[\"custom_id\"]\n        if not isinstance(cid, str) or not cid.strip() or cid in ids: raise ValueError(\"custom_id must be nonempty and unique\")\n        ids.add(cid)\n        if not isinstance(item[\"body\"], dict) or not item[\"body\"].get(\"messages\"): raise ValueError(\"Supply actual text messages\")\n        supplied_model = item[\"body\"].get(\"model\")\n        if supplied_model is not None and supplied_model not in ['moonshotai/kimi-k3:batch', 'moonshotai/kimi-k3']: raise ValueError(\"body.model must be an exact documented caller or wire ID\")\n    return {\"endpoint\":\"/v1/chat/completions\", \"model\":\"moonshotai/kimi-k3:batch\", \"requests\":items}\n\nif __name__ == \"__main__\":\n    material = os.environ.get(\"AILOOT_BATCH_REQUESTS_JSONL\", \"\")\n    if not material: raise SystemExit(\"Set AILOOT_BATCH_REQUESTS_JSONL to your actual customer file\")\n    body = prepare_requests(material)\n    key = os.environ.get(\"AILOOT_API_KEY\", \"\")\n    if not key: raise SystemExit(\"Set AILOOT_API_KEY\")\n    request = Request(\"https://api.ailoot.ai/v1/batches\", data=json.dumps(body, ensure_ascii=False).encode(\"utf-8\"), headers={\"Authorization\":\"Bearer \" + key, \"Content-Type\":\"application/json\"}, method=\"POST\")\n    with urlopen(request) as response:\n        raw = response.read()\n        Path(\"batch-create-response.json\").write_bytes(raw)\n        print(raw.decode(\"utf-8\"))\n",
            "label": "Python HTTP · actual customer JSONL",
            "language": "python"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nBATCH_OPERATION_ID=\"$(python3 - <<'PY_ID'\nimport json\nfrom pathlib import Path\nfrom urllib.parse import quote\nresponse = json.loads(Path(\"batch-create-response.json\").read_text(encoding=\"utf-8\"))\noperation = response.get(\"id\")\nif not isinstance(operation, str) or not operation: raise SystemExit(\"No actual original operation ID; preserve the response and do not resubmit\")\nprint(quote(operation, safe=\"\"))\nPY_ID\n)\"\ncurl --fail-with-body --silent --show-error \"https://api.ailoot.ai/v1/batches/$BATCH_OPERATION_ID\" \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -o batch-status-response.json\n",
            "label": "curl · original operation status",
            "language": "bash"
          },
          {
            "code": "import json\nfrom pathlib import Path\nraw = Path(\"batch-status-response.json\").read_bytes()\nresponse = json.loads(raw)\nif response.get(\"status\") != \"completed\":\n    raise SystemExit(\"Keep the original operation; read its status without resubmitting\")\nresults = response.get(\"results\")\nif not isinstance(results, list) or not results:\n    raise SystemExit(\"Preserve the original response; completed results are missing\")\nPath(\"batch-results.jsonl\").write_text(\"\".join(json.dumps(item, ensure_ascii=False) + \"\\n\" for item in results), encoding=\"utf-8\")\n# Preserve batch-status-response.json with aggregate usage and every result/error.\n",
            "label": "Python · save every completed result",
            "language": "python"
          }
        ],
        "family": "batch",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "batches",
        "hints": [
          "Read your actual request items before submission; inline requests are required.",
          "Keep the returned operation ID and every result. Never replay an unknown submission."
        ],
        "http": "POST",
        "in": 4.56,
        "input": [
          "text"
        ],
        "label": "Paketli ishlov berish",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "out": 22.8,
        "output": [
          "text"
        ],
        "path": "/v1/batches",
        "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"
          },
          {
            "label": "Explicit cache pricing",
            "value": "Not enabled",
            "when": "When explicit cache is requested"
          }
        ],
        "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": "0.00456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.00000456",
                "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": "0.0228000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000228",
                "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": "0.000456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.000000456",
                "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": "0.00456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.00000456",
                "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": "0.0228000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.0000228",
                "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": "0.000456000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.000000456",
                "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": "moonshotai/kimi-k3:batch",
        "route_label": "Ultra",
        "status_reads": [
          "GET /v1/batches/{operation_id}"
        ],
        "tiers": [
          {
            "cache_read": 0.456,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 4.56,
            "input_multiplier": null,
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "out": 22.8,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.00456000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.00000456",
            "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": "0.0228000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.0000228",
            "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": "0.000456000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.000000456",
            "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": "moonshotai/kimi-k3:batch",
        "request_model_id": "moonshotai/kimi-k3:batch",
        "route_label": "Ultra"
      }
    ],
    "name": "MoonshotAI: Kimi K3 (batch)",
    "price": {
      "in": 4.56,
      "in_label": null,
      "out": 22.8,
      "out_label": null,
      "scope_label": "Token rates",
      "sort_in": 4.56,
      "sort_out": 22.8,
      "varies": true
    },
    "short": "Kimi K3 — Moonshot AI kompaniyasining uzun dasturlash vazifalari va bilim ishi uchun boshidan multimodal yaratilgan mulohaza modeli. U matn, tasvir va videoni o‘qiydi, matn yaratadi hamda 1 048 576 tokenli kontekst va qadamlar bo‘ylab saqlanadigan fikrlash tarixi bilan vositalarga tayangan jarayonlarni qo‘llab-quvvatlaydi."
  },
  "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": "Kimi K3 — Moonshot AI kompaniyasining uzun dasturlash vazifalari va bilim ishi uchun boshidan multimodal yaratilgan mulohaza modeli. U matn, tasvir va videoni o‘qiydi, matn yaratadi hamda 1 048 576 tokenli kontekst va qadamlar bo‘ylab saqlanadigan fikrlash tarixi bilan vositalarga tayangan jarayonlarni qo‘llab-quvvatlaydi.",
  "source": {
    "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1",
    "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036",
    "raw_model_json_sha256": "6b80012ad8e1428bdbe4a29486e2f710359eef05e766e62afcf28ac62e307e81",
    "renderer_sha256": "aa8a0fca1bd770c042b64987512b6187fca2067aea3ddc877f68b163d80e7df6"
  },
  "sourceRevision": "ec75fced39ea4a979e2f6af623320903b617279a63ac0ced9949657c76f6e91a"
}