Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
", "aboutText": "Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.\n\nArxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.\n\n### Ish jarayonidagi vizual materiallar\n\nModel skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.\n\nUlangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda `json_schema` avtomatik ravishda `json_object` bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.\n\n### Javob berishning ikki usuli\n\nQwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — `xhigh`; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. `low` darajasi oddiy savollar va ma’lumot ajratib olish uchun, `medium` — kundalik dasturlash va hujjat tayyorlash uchun, `xhigh` esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida `reasoning_effort` yoki `thinking_budget` ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.\n\nKontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.\n\nKontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.", "editorialOverlay": { "copy_fields": { "practical_html": "Ingliz tilidagi texnik misol
Reconcile a business table and note\n\nReconcile this table: Team A opened 30 cases and closed 24; Team B opened 20 and closed 25. Manager note: “Both backlogs fell.” Assume no transfers or other adjustments. Calculate each team’s backlog change, assess the note and draft a corrected two-sentence update. Keep calculations separate from proposed explanations.Two net-change calculations, an assessment of the note and a corrected short update.Check the sign convention and avoid inventing a cause for either team’s change.qwen3.8-flashKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/messagestext, imagetext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen3.8-flash | Standart— |
Maydonmessages | Turmessage[] | TalabMajburiy | Qiymatlar va cheklovlar Elementlarning eng kam soni: 1 | Standart— |
Maydonmessages[].role | Turstring | TalabMajburiy | Qiymatlar va cheklovlar user, assistant | Standart— |
Maydonmessages[].content | Turstring|content_block[] | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
Maydonsystem | Turstring|content_block[] | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmax_tokens | Turinteger | TalabMajburiy | Qiymatlar va cheklovlar Eng kam: 1 Cheklov qo‘llanadigan obyekt: Tanlangan model yoki kartaning aniq yuqori chegarasi | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydontemperature | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontop_p | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstop_sequences | Turstring[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools | Turtool[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools[].name | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Vosita taqdim etilgan | Standart— |
Maydontools[].description | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontools[].input_schema | TurJSON_schema | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontool_choice | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonthinking.type | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonthinking.budget_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_config.effort | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmetadata | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydoncache_control | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matn · UTF8 matni
messages[].content yoki type=text bloki
Matn + rasm
{type:image,source:{type:base64,media_type,data}} yoki type=url turidagi manba
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext, image |
Parametrrequired | Parametr talablarimodel, messages, max_tokens |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Parametrtext_file_material | Parametr talablariHaqiqiy UTF-8 kontenti matn sifatida kiritiladi; fayl IDlari/URLs uchun alohida aniq qo‘llab-quvvatlash kerak |
Hayot sikli: exact retained published method
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/messagesAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
Modelning ma’lumot jadvallari usul tanlash, narx hisobi yoki to‘lovlarni o‘zgartirmaydi. Amaldagi to‘lovlar tanlangan Ailoot usuli tariflari bo‘yicha hisoblanadi.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaOpenAI Chat · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaOpenAI Chat · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen3.8-flash", "max_tokens": 1024, "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen3.8-flash", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nimport anthropic\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nmsg = client.messages.create(\n model="qwen3.8-flash",\n max_tokens=1024,\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(msg.to_dict(mode="json"))\nimport Anthropic from "@anthropic-ai/sdk";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n model: "qwen3.8-flash",\n max_tokens: 1024,\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(msg);\nimport anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.messages.stream(model='qwen3.8-flash',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_message()\n save_result(final.to_dict(mode="json"),"stream-result")\njson yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Barcha kontent bloklari, fikrlash imzolari va haqiqiy vosita ishlatish IDlarini saqlang. SSE bloklarining barcha o‘zgarish qismlarini yig‘ing; birinchi matn bloki to‘liq chiqish emas.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonid | Turstring |
Maydonmodel | Turstring |
Maydoncontent[] | Turtext|thinking|tool_use|other content block |
Maydonstop_reason | Turstring|null |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
qwen3.8-flashKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/responsestext, imagetext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen3.8-flash | Standart— |
Maydoninput | Turstring|input_item[] | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
Maydoninstructions | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydoninput[].type | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar message, reasoning, function_call, function_call_output | Standart— |
Maydoninput[].content | Turstring|content_part[] | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydoninput[].call_id | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: function_call_output; haqiqatan qaytarilgan call_id qiymatini saqlang | Standart— |
Maydoninput[].output | Turstring|content_part[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: function_call_output | Standart— |
Maydonmax_output_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydontemperature | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontop_p | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools | Turtool[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontool_choice | Turstring|object | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonparallel_tool_calls | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning.effort | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning.summary | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontext.format | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontext.verbosity | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydoninclude | Turstring[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstore | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprevious_response_id | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar ID talabi: Faqat qo‘llab-quvvatlanadigan davom ettirishdan olingan haqiqiy javob IDsi Modelga bogʻliq | Standart— |
Maydonservice_tier | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprompt_cache_key | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprompt_cache_options | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matn · UTF8 matni
Kirish matni yoki input_text qismi
Matn + rasm
{type:input_image,image_url}
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext, image |
Parametrrequired | Parametr talablarimodel, input |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Parametrtext_file_material | Parametr talablariHaqiqiy UTF-8 kontenti matn sifatida kiritiladi; fayl IDlari/URLs uchun alohida aniq qo‘llab-quvvatlash kerak |
Hayot sikli: exact retained published method
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/responsesAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
Modelning ma’lumot jadvallari usul tanlash, narx hisobi yoki to‘lovlarni o‘zgartirmaydi. Amaldagi to‘lovlar tanlangan Ailoot usuli tariflari bo‘yicha hisoblanadi.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaOpenAI Chat · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaOpenAI Chat · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen3.8-flash", "input": ""}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["input"]="Summarize this material and quote supporting source passages.\\n\\n"+text\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen3.8-flash", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.responses.create(model="qwen3.8-flash", input="Explain the difference between an observation and a hypothesis in three sentences.")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: "qwen3.8-flash", input: "Explain the difference between an observation and a hypothesis in three sentences." });\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nwith client.responses.stream(model="qwen3.8-flash", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_response()\n save_result(final.to_dict(mode="json"),"stream-result")\njson yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Har bir chiqish elementi va kontent qismini, funksiyaning haqiqiy call_id qiymatini, shifrlangan fikrlash ma’lumotlari va sarfni saqlang. Oqimli uzatishda hodisa va elementning to‘liq identifikatsiyasini saqlang.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonid | Turstring |
Maydonstatus | Turstring |
Maydonoutput[] | Turmessage|reasoning|function_call|other item |
Maydonoutput[].content[] | Turcontent part |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
qwen3.8-flashKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/chat/completionstext, imagetext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen3.8-flash | Standart— |
Maydonmessages | Turmessage[] | TalabMajburiy | Qiymatlar va cheklovlar Elementlarning eng kam soni: 1 | Standart— |
Maydonmessages[].role | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Namunalar: system, user, assistant, tool, function Shartlar: Bu rollar manba kodining moslik turlarida ochiq ifodalangan; aniq rollar to‘plami har bir modelga xos bo‘lib qoladi. Modelga bogʻliq | Standart— |
Maydonmessages[].content | Turstring|content_part[]|null | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].tool_calls | Turtool_call[] | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].tool_call_id | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: role=tool; haqiqatan qaytarilgan IDdan foydalaning | Standart— |
Maydonmessages[].name | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].reasoning_content | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Ushbu model foydalanganda, haqiqatan qaytarilgan fikrlash ma’lumotlarini keyingi so‘rovda qayta yuboring | Standart— |
Maydonmessages[].reasoning_details | Turobject|array | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmax_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
Maydonmax_completion_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydonstream_options.include_usage | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontemperature | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontop_p | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstop | Turstring|string[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools | Turfunction_tool[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools[].type | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools[].function.name | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Funksiya vositasi taqdim etilgan | Standart— |
Maydontools[].function.description | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontools[].function.parameters | TurJSON_schema | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontool_choice | Turstring|object | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonparallel_tool_calls | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonresponse_format | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning_effort | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonservice_tier | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydoninstructions | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Moslik maydoni | Standart— |
Maydonfunctions | Turfunction[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonfunction_call | Turstring|object | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprompt_cache_options | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matn · UTF8 matni
messages[].content
Matn + rasm
{type:image_url,image_url:{url,detail}}
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext, image |
Parametrrequired | Parametr talablarimodel, messages |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Parametrtext_file_material | Parametr talablariHaqiqiy UTF-8 kontenti matn sifatida kiritiladi; fayl IDlari/URLs uchun alohida aniq qo‘llab-quvvatlash kerak |
Hayot sikli: exact retained published method
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/chat/completionsAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
Modelning ma’lumot jadvallari usul tanlash, narx hisobi yoki to‘lovlarni o‘zgartirmaydi. Amaldagi to‘lovlar tanlangan Ailoot usuli tariflari bo‘yicha hisoblanadi.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaOpenAI Chat · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaOpenAI Chat · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen3.8-flash", "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen3.8-flash", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.chat.completions.create(\n model="qwen3.8-flash",\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n model: "qwen3.8-flash",\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='qwen3.8-flash',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Har bir javob variantini va uning kontenti, vosita chaqiruvlari hamda fikrlash ma’lumotlarini saqlang. SSEda o‘zgarish qismlarini variant va vosita indeksi bo‘yicha yig‘ing, yakuniy tugash sababi va sarf ma’lumotlarini saqlang.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonchoices[].index | Turinteger |
Maydonchoices[].message.content | Turstring|null |
Maydonchoices[].message.tool_calls | Turtool_call[] |
Maydonchoices[].message.reasoning_content | Turstring |
Maydonchoices[].message.reasoning_details | Turobject|array |
Maydonchoices[].finish_reason | Turstring|null |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
qwen3.8-flashKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/chat/completionstexttext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen3.8-flash | Standart— |
Maydonmessages | Turmessage[] | TalabMajburiy | Qiymatlar va cheklovlar Elementlarning eng kam soni: 1 | Standart— |
Maydonmessages[].role | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmessages[].content | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Matnli suhbat | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Matn · UTF8 matni
messages[].content
| Parametr | Parametr talablari |
|---|---|
Parametrcontent_type | Parametr talablariapplication/json |
Parametrrequired | Parametr talablarimodel, messages |
Parametrmaterial_types | Parametr talablaritext |
Parametrmessages | Parametr talablarirole/content tuzilishidagi xabarlar massivi |
Parametrfile_material | Parametr talablariHaqiqiy UTF-8 hujjati aynan matn sifatida kiritiladi; fayl IDsi faraz qilinmaydi |
Parametroptional_controls | Parametr talablaristream |
Parametrcontrol_scope | Parametr talablariMatnli suhbat; stream mantiqiy qiymat bo‘lib, standart holatda false. |
Parametroutput_modalities | Parametr talablaritext |
Parametrhosted_operations | Parametr talablarifalse |
Parametrmultimodal_input_binding | Parametr talablarinull |
Usul taxalluslari: /chat/completions
Hayot sikli: synchronous_or_streamed
Aniq model IDsini messages bilan yuboring.
Kontekst uzunligi chiqishning yuqori chegarasi emas.
Matn fayli aynan matnni taqdim etishi mumkin; tasvir, audio va fayl obyekti kirishlari aniq bog‘lashni talab qiladi.
Tarif ma’lumotlari so‘rov imkoniyatlarini qo‘shmaydi. Qo‘llab-quvvatlanadigan parametrlar tanlangan usulda ko‘rsatilgan.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaTokenlar uchun bazaviy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaSo‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
Ailoot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"qwen3.8-flash","messages":[{"role":"user","content":"hello"}],"stream":false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model="qwen3.8-flash", messages=[{"role":"user","content":"hello"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\njson yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Har bir javob variantini va uning kontenti, vosita chaqiruvlari hamda fikrlash ma’lumotlarini saqlang. SSEda o‘zgarish qismlarini variant va vosita indeksi bo‘yicha yig‘ing, yakuniy tugash sababi va sarf ma’lumotlarini saqlang.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonchoices[].index | Turinteger |
Maydonchoices[].message.content | Turstring|null |
Maydonchoices[].message.tool_calls | Turtool_call[] |
Maydonchoices[].message.reasoning_content | Turstring |
Maydonchoices[].message.reasoning_details | Turobject|array |
Maydonchoices[].finish_reason | Turstring|null |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
qwen3.8-flashKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/messagestextjson, sse| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen3.8-flash | Standart— |
Maydonmessages | Turmessage[] | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].role | Turstring | TalabMajburiy | Qiymatlar va cheklovlar user, assistant | Standart— |
Maydonmessages[].content | Turstring | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
Maydonmax_tokens | Turinteger | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Matn · UTF-8 matni
messages[].content satri
| Parametr | Parametr talablari |
|---|---|
Parametrcontent_type | Parametr talablariapplication/json |
Parametrrequired | Parametr talablarimodel, messages, max_tokens |
Parametroptional_controls | Parametr talablaristream |
Parametrmaterial_types | Parametr talablaritext |
Parametrtext_file_material | Parametr talablariHaqiqiy UTF-8 hujjatini o‘qing va uning matnini ko‘rsatilgan kirish yoki xabar kontenti satriga joylashtiring. |
Hayot sikli: synchronous_or_streamed
Tarif ma’lumotlari so‘rov imkoniyatlarini qo‘shmaydi. Qo‘llab-quvvatlanadigan parametrlar tanlangan usulda ko‘rsatilgan.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaTokenlar uchun bazaviy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaSo‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
Ailoot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
{\n "model": "qwen3.8-flash",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'qwen3.8-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'qwen3.8-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Barcha kontent bloklari, fikrlash imzolari va haqiqiy vosita ishlatish IDlarini saqlang. SSE bloklarining barcha o‘zgarish qismlarini yig‘ing; birinchi matn bloki to‘liq chiqish emas.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonid | Turstring |
Maydonmodel | Turstring |
Maydoncontent[] | Turtext|thinking|tool_use|other content block |
Maydonstop_reason | Turstring|null |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
qwen-flashKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/messagestext, imagetext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen-flash | Standart— |
Maydonmessages | Turmessage[] | TalabMajburiy | Qiymatlar va cheklovlar Elementlarning eng kam soni: 1 | Standart— |
Maydonmessages[].role | Turstring | TalabMajburiy | Qiymatlar va cheklovlar user, assistant | Standart— |
Maydonmessages[].content | Turstring|content_block[] | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
Maydonsystem | Turstring|content_block[] | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmax_tokens | Turinteger | TalabMajburiy | Qiymatlar va cheklovlar Eng kam: 1 Cheklov qo‘llanadigan obyekt: Tanlangan model yoki kartaning aniq yuqori chegarasi | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydontemperature | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontop_p | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstop_sequences | Turstring[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools | Turtool[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools[].name | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Vosita taqdim etilgan | Standart— |
Maydontools[].description | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontools[].input_schema | TurJSON_schema | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontool_choice | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonthinking.type | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonthinking.budget_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_config.effort | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmetadata | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydoncache_control | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matn · UTF8 matni
messages[].content yoki type=text bloki
Matn + rasm
{type:image,source:{type:base64,media_type,data}} yoki type=url turidagi manba
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext, image |
Parametrrequired | Parametr talablarimodel, messages, max_tokens |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Parametrtext_file_material | Parametr talablariHaqiqiy UTF-8 kontenti matn sifatida kiritiladi; fayl IDlari/URLs uchun alohida aniq qo‘llab-quvvatlash kerak |
Hayot sikli: exact retained published method
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/messagesAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
Modelning ma’lumot jadvallari usul tanlash, narx hisobi yoki to‘lovlarni o‘zgartirmaydi. Amaldagi to‘lovlar tanlangan Ailoot usuli tariflari bo‘yicha hisoblanadi.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaOpenAI Chat · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaOpenAI Chat · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen-flash", "max_tokens": 1024, "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen-flash", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nimport anthropic\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nmsg = client.messages.create(\n model="qwen-flash",\n max_tokens=1024,\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(msg.to_dict(mode="json"))\nimport Anthropic from "@anthropic-ai/sdk";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n model: "qwen-flash",\n max_tokens: 1024,\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(msg);\nimport anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.messages.stream(model='qwen-flash',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_message()\n save_result(final.to_dict(mode="json"),"stream-result")\njson yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Barcha kontent bloklari, fikrlash imzolari va haqiqiy vosita ishlatish IDlarini saqlang. SSE bloklarining barcha o‘zgarish qismlarini yig‘ing; birinchi matn bloki to‘liq chiqish emas.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonid | Turstring |
Maydonmodel | Turstring |
Maydoncontent[] | Turtext|thinking|tool_use|other content block |
Maydonstop_reason | Turstring|null |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
qwen-flashKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/responsestext, imagetext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen-flash | Standart— |
Maydoninput | Turstring|input_item[] | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
Maydoninstructions | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydoninput[].type | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar message, reasoning, function_call, function_call_output | Standart— |
Maydoninput[].content | Turstring|content_part[] | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydoninput[].call_id | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: function_call_output; haqiqatan qaytarilgan call_id qiymatini saqlang | Standart— |
Maydoninput[].output | Turstring|content_part[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: function_call_output | Standart— |
Maydonmax_output_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydontemperature | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontop_p | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools | Turtool[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontool_choice | Turstring|object | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonparallel_tool_calls | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning.effort | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning.summary | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontext.format | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontext.verbosity | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydoninclude | Turstring[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstore | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprevious_response_id | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar ID talabi: Faqat qo‘llab-quvvatlanadigan davom ettirishdan olingan haqiqiy javob IDsi Modelga bogʻliq | Standart— |
Maydonservice_tier | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprompt_cache_key | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprompt_cache_options | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matn · UTF8 matni
Kirish matni yoki input_text qismi
Matn + rasm
{type:input_image,image_url}
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext, image |
Parametrrequired | Parametr talablarimodel, input |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Parametrtext_file_material | Parametr talablariHaqiqiy UTF-8 kontenti matn sifatida kiritiladi; fayl IDlari/URLs uchun alohida aniq qo‘llab-quvvatlash kerak |
Hayot sikli: exact retained published method
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/responsesAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
Modelning ma’lumot jadvallari usul tanlash, narx hisobi yoki to‘lovlarni o‘zgartirmaydi. Amaldagi to‘lovlar tanlangan Ailoot usuli tariflari bo‘yicha hisoblanadi.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaOpenAI Chat · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaOpenAI Chat · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen-flash", "input": ""}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["input"]="Summarize this material and quote supporting source passages.\\n\\n"+text\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen-flash", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.responses.create(model="qwen-flash", input="Explain the difference between an observation and a hypothesis in three sentences.")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: "qwen-flash", input: "Explain the difference between an observation and a hypothesis in three sentences." });\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nwith client.responses.stream(model="qwen-flash", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_response()\n save_result(final.to_dict(mode="json"),"stream-result")\njson yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Har bir chiqish elementi va kontent qismini, funksiyaning haqiqiy call_id qiymatini, shifrlangan fikrlash ma’lumotlari va sarfni saqlang. Oqimli uzatishda hodisa va elementning to‘liq identifikatsiyasini saqlang.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonid | Turstring |
Maydonstatus | Turstring |
Maydonoutput[] | Turmessage|reasoning|function_call|other item |
Maydonoutput[].content[] | Turcontent part |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
qwen-flashKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/chat/completionstext, imagetext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen-flash | Standart— |
Maydonmessages | Turmessage[] | TalabMajburiy | Qiymatlar va cheklovlar Elementlarning eng kam soni: 1 | Standart— |
Maydonmessages[].role | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Namunalar: system, user, assistant, tool, function Shartlar: Bu rollar manba kodining moslik turlarida ochiq ifodalangan; aniq rollar to‘plami har bir modelga xos bo‘lib qoladi. Modelga bogʻliq | Standart— |
Maydonmessages[].content | Turstring|content_part[]|null | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].tool_calls | Turtool_call[] | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].tool_call_id | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: role=tool; haqiqatan qaytarilgan IDdan foydalaning | Standart— |
Maydonmessages[].name | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].reasoning_content | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Ushbu model foydalanganda, haqiqatan qaytarilgan fikrlash ma’lumotlarini keyingi so‘rovda qayta yuboring | Standart— |
Maydonmessages[].reasoning_details | Turobject|array | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmax_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
Maydonmax_completion_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydonstream_options.include_usage | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontemperature | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontop_p | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstop | Turstring|string[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools | Turfunction_tool[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools[].type | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools[].function.name | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Funksiya vositasi taqdim etilgan | Standart— |
Maydontools[].function.description | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontools[].function.parameters | TurJSON_schema | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontool_choice | Turstring|object | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonparallel_tool_calls | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonresponse_format | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning_effort | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonservice_tier | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydoninstructions | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Moslik maydoni | Standart— |
Maydonfunctions | Turfunction[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonfunction_call | Turstring|object | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprompt_cache_options | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matn · UTF8 matni
messages[].content
Matn + rasm
{type:image_url,image_url:{url,detail}}
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext, image |
Parametrrequired | Parametr talablarimodel, messages |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Parametrtext_file_material | Parametr talablariHaqiqiy UTF-8 kontenti matn sifatida kiritiladi; fayl IDlari/URLs uchun alohida aniq qo‘llab-quvvatlash kerak |
Hayot sikli: exact retained published method
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/chat/completionsAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
Modelning ma’lumot jadvallari usul tanlash, narx hisobi yoki to‘lovlarni o‘zgartirmaydi. Amaldagi to‘lovlar tanlangan Ailoot usuli tariflari bo‘yicha hisoblanadi.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaOpenAI Chat · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaOpenAI Chat · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen-flash", "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen-flash", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.chat.completions.create(\n model="qwen-flash",\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n model: "qwen-flash",\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='qwen-flash',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Har bir javob variantini va uning kontenti, vosita chaqiruvlari hamda fikrlash ma’lumotlarini saqlang. SSEda o‘zgarish qismlarini variant va vosita indeksi bo‘yicha yig‘ing, yakuniy tugash sababi va sarf ma’lumotlarini saqlang.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonchoices[].index | Turinteger |
Maydonchoices[].message.content | Turstring|null |
Maydonchoices[].message.tool_calls | Turtool_call[] |
Maydonchoices[].message.reasoning_content | Turstring |
Maydonchoices[].message.reasoning_details | Turobject|array |
Maydonchoices[].finish_reason | Turstring|null |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
qwen-flash-latestKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/messagestext, imagetext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen-flash-latest | Standart— |
Maydonmessages | Turmessage[] | TalabMajburiy | Qiymatlar va cheklovlar Elementlarning eng kam soni: 1 | Standart— |
Maydonmessages[].role | Turstring | TalabMajburiy | Qiymatlar va cheklovlar user, assistant | Standart— |
Maydonmessages[].content | Turstring|content_block[] | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
Maydonsystem | Turstring|content_block[] | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmax_tokens | Turinteger | TalabMajburiy | Qiymatlar va cheklovlar Eng kam: 1 Cheklov qo‘llanadigan obyekt: Tanlangan model yoki kartaning aniq yuqori chegarasi | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydontemperature | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontop_p | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstop_sequences | Turstring[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools | Turtool[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools[].name | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Vosita taqdim etilgan | Standart— |
Maydontools[].description | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontools[].input_schema | TurJSON_schema | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontool_choice | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonthinking.type | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonthinking.budget_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_config.effort | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmetadata | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydoncache_control | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matn · UTF8 matni
messages[].content yoki type=text bloki
Matn + rasm
{type:image,source:{type:base64,media_type,data}} yoki type=url turidagi manba
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext, image |
Parametrrequired | Parametr talablarimodel, messages, max_tokens |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Parametrtext_file_material | Parametr talablariHaqiqiy UTF-8 kontenti matn sifatida kiritiladi; fayl IDlari/URLs uchun alohida aniq qo‘llab-quvvatlash kerak |
Hayot sikli: exact retained published method
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/messagesAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
Modelning ma’lumot jadvallari usul tanlash, narx hisobi yoki to‘lovlarni o‘zgartirmaydi. Amaldagi to‘lovlar tanlangan Ailoot usuli tariflari bo‘yicha hisoblanadi.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaOpenAI Chat · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaOpenAI Chat · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen-flash-latest", "max_tokens": 1024, "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen-flash-latest", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nimport anthropic\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nmsg = client.messages.create(\n model="qwen-flash-latest",\n max_tokens=1024,\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(msg.to_dict(mode="json"))\nimport Anthropic from "@anthropic-ai/sdk";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n model: "qwen-flash-latest",\n max_tokens: 1024,\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(msg);\nimport anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.messages.stream(model='qwen-flash-latest',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_message()\n save_result(final.to_dict(mode="json"),"stream-result")\njson yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Barcha kontent bloklari, fikrlash imzolari va haqiqiy vosita ishlatish IDlarini saqlang. SSE bloklarining barcha o‘zgarish qismlarini yig‘ing; birinchi matn bloki to‘liq chiqish emas.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonid | Turstring |
Maydonmodel | Turstring |
Maydoncontent[] | Turtext|thinking|tool_use|other content block |
Maydonstop_reason | Turstring|null |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
qwen-flash-latestKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/responsestext, imagetext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen-flash-latest | Standart— |
Maydoninput | Turstring|input_item[] | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
Maydoninstructions | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydoninput[].type | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar message, reasoning, function_call, function_call_output | Standart— |
Maydoninput[].content | Turstring|content_part[] | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydoninput[].call_id | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: function_call_output; haqiqatan qaytarilgan call_id qiymatini saqlang | Standart— |
Maydoninput[].output | Turstring|content_part[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: function_call_output | Standart— |
Maydonmax_output_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydontemperature | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontop_p | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools | Turtool[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontool_choice | Turstring|object | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonparallel_tool_calls | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning.effort | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning.summary | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontext.format | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontext.verbosity | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydoninclude | Turstring[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstore | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprevious_response_id | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar ID talabi: Faqat qo‘llab-quvvatlanadigan davom ettirishdan olingan haqiqiy javob IDsi Modelga bogʻliq | Standart— |
Maydonservice_tier | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprompt_cache_key | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprompt_cache_options | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matn · UTF8 matni
Kirish matni yoki input_text qismi
Matn + rasm
{type:input_image,image_url}
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext, image |
Parametrrequired | Parametr talablarimodel, input |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Parametrtext_file_material | Parametr talablariHaqiqiy UTF-8 kontenti matn sifatida kiritiladi; fayl IDlari/URLs uchun alohida aniq qo‘llab-quvvatlash kerak |
Hayot sikli: exact retained published method
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/responsesAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
Modelning ma’lumot jadvallari usul tanlash, narx hisobi yoki to‘lovlarni o‘zgartirmaydi. Amaldagi to‘lovlar tanlangan Ailoot usuli tariflari bo‘yicha hisoblanadi.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaOpenAI Chat · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaOpenAI Chat · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen-flash-latest", "input": ""}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["input"]="Summarize this material and quote supporting source passages.\\n\\n"+text\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen-flash-latest", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.responses.create(model="qwen-flash-latest", input="Explain the difference between an observation and a hypothesis in three sentences.")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: "qwen-flash-latest", input: "Explain the difference between an observation and a hypothesis in three sentences." });\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nwith client.responses.stream(model="qwen-flash-latest", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_response()\n save_result(final.to_dict(mode="json"),"stream-result")\njson yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Har bir chiqish elementi va kontent qismini, funksiyaning haqiqiy call_id qiymatini, shifrlangan fikrlash ma’lumotlari va sarfni saqlang. Oqimli uzatishda hodisa va elementning to‘liq identifikatsiyasini saqlang.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonid | Turstring |
Maydonstatus | Turstring |
Maydonoutput[] | Turmessage|reasoning|function_call|other item |
Maydonoutput[].content[] | Turcontent part |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
qwen-flash-latestKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/chat/completionstext, imagetext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen-flash-latest | Standart— |
Maydonmessages | Turmessage[] | TalabMajburiy | Qiymatlar va cheklovlar Elementlarning eng kam soni: 1 | Standart— |
Maydonmessages[].role | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Namunalar: system, user, assistant, tool, function Shartlar: Bu rollar manba kodining moslik turlarida ochiq ifodalangan; aniq rollar to‘plami har bir modelga xos bo‘lib qoladi. Modelga bogʻliq | Standart— |
Maydonmessages[].content | Turstring|content_part[]|null | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].tool_calls | Turtool_call[] | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].tool_call_id | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: role=tool; haqiqatan qaytarilgan IDdan foydalaning | Standart— |
Maydonmessages[].name | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].reasoning_content | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Ushbu model foydalanganda, haqiqatan qaytarilgan fikrlash ma’lumotlarini keyingi so‘rovda qayta yuboring | Standart— |
Maydonmessages[].reasoning_details | Turobject|array | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmax_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
Maydonmax_completion_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydonstream_options.include_usage | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontemperature | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontop_p | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstop | Turstring|string[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools | Turfunction_tool[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools[].type | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools[].function.name | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Funksiya vositasi taqdim etilgan | Standart— |
Maydontools[].function.description | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontools[].function.parameters | TurJSON_schema | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontool_choice | Turstring|object | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonparallel_tool_calls | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonresponse_format | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning_effort | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonservice_tier | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydoninstructions | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Moslik maydoni | Standart— |
Maydonfunctions | Turfunction[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonfunction_call | Turstring|object | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprompt_cache_options | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matn · UTF8 matni
messages[].content
Matn + rasm
{type:image_url,image_url:{url,detail}}
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext, image |
Parametrrequired | Parametr talablarimodel, messages |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Parametrtext_file_material | Parametr talablariHaqiqiy UTF-8 kontenti matn sifatida kiritiladi; fayl IDlari/URLs uchun alohida aniq qo‘llab-quvvatlash kerak |
Hayot sikli: exact retained published method
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/chat/completionsAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
Modelning ma’lumot jadvallari usul tanlash, narx hisobi yoki to‘lovlarni o‘zgartirmaydi. Amaldagi to‘lovlar tanlangan Ailoot usuli tariflari bo‘yicha hisoblanadi.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaOpenAI Chat · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaOpenAI Chat · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · Tokenlar uchun asosiy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaAnthropic Messages · So‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen-flash-latest", "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen-flash-latest", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="image/png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "image/jpeg" if raw.startswith(b"\\xff\\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.chat.completions.create(\n model="qwen-flash-latest",\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n model: "qwen-flash-latest",\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='qwen-flash-latest',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Har bir javob variantini va uning kontenti, vosita chaqiruvlari hamda fikrlash ma’lumotlarini saqlang. SSEda o‘zgarish qismlarini variant va vosita indeksi bo‘yicha yig‘ing, yakuniy tugash sababi va sarf ma’lumotlarini saqlang.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonchoices[].index | Turinteger |
Maydonchoices[].message.content | Turstring|null |
Maydonchoices[].message.tool_calls | Turtool_call[] |
Maydonchoices[].message.reasoning_content | Turstring |
Maydonchoices[].message.reasoning_details | Turobject|array |
Maydonchoices[].finish_reason | Turstring|null |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
qwen/qwen3.8-flashKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/chat/completionstexttext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen/qwen3.8-flash | Standart— |
Maydonmessages | Turmessage[] | TalabMajburiy | Qiymatlar va cheklovlar Elementlarning eng kam soni: 1 | Standart— |
Maydonmessages[].role | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Namunalar: system, user, assistant, tool, function Shartlar: Bu rollar manba kodining moslik turlarida ochiq ifodalangan; aniq rollar to‘plami har bir modelga xos bo‘lib qoladi. Modelga bogʻliq | Standart— |
Maydonmessages[].content | Turstring|content_part[]|null | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].tool_calls | Turtool_call[] | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].tool_call_id | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: role=tool; haqiqatan qaytarilgan IDdan foydalaning | Standart— |
Maydonmessages[].name | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].reasoning_content | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Ushbu model foydalanganda, haqiqatan qaytarilgan fikrlash ma’lumotlarini keyingi so‘rovda qayta yuboring | Standart— |
Maydonmessages[].reasoning_details | Turobject|array | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmax_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
Maydonmax_completion_tokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydonstream_options.include_usage | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontemperature | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontop_p | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstop | Turstring|string[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools | Turfunction_tool[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools[].type | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar function Modelga bogʻliq | Standart— |
Maydontools[].function.name | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Funksiya vositasi taqdim etilgan | Standart— |
Maydontools[].function.description | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontools[].function.parameters | TurJSON_schema | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Maydontool_choice | Turstring|object | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonparallel_tool_calls | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonresponse_format | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning_effort | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonreasoning | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonservice_tier | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydoninstructions | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Moslik maydoni | Standart— |
Maydonfunctions | Turfunction[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonfunction_call | Turstring|object | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonprompt_cache_options | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmodalities | Turstring[] | TalabIxtiyoriy | Qiymatlar va cheklovlar text | Standart— |
Maydonprovider | Turobject | TalabIxtiyoriy | Qiymatlar va cheklovlar Shartlar: Ushbu Ultra matn marshrutida provider.options rad etiladi | Standart— |
Maydoncache_control.ttl | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Shartlar: Haqiqiy prompt-kesh joylarida 1h rad etiladi | Standart— |
Matn · UTF8 matni
messages[].content
| Parametr | Parametr talablari |
|---|---|
Parametrcontent_type | Parametr talablariapplication/json |
Parametrrequired | Parametr talablarimodel, messages |
Parametrmaterial_types | Parametr talablaritext |
Parametrmessages | Parametr talablarirole/content tuzilishidagi xabarlar massivi |
Parametrfile_material | Parametr talablariHaqiqiy UTF-8 hujjati aynan matn sifatida kiritiladi; fayl IDsi faraz qilinmaydi |
Parametroptional_controls | Parametr talablaristream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametrcontrol_scope | Parametr talablariModelga xos; foydalanuvchi funksiya vositalari hostingdagi vositalardan farq qiladi |
Parametroutput_modalities | Parametr talablaritext |
Parametrhosted_operations | Parametr talablarifalse |
Parametrmultimodal_input_binding | Parametr talablarinull |
Hayot sikli: synchronous_or_streamed
Aniq model IDsini messages bilan yuboring.
Kontekst uzunligi chiqishning yuqori chegarasi emas.
Matn fayli aynan matnni taqdim etishi mumkin; tasvir, audio va fayl obyekti kirishlari aniq bog‘lashni talab qiladi.
Tarif ma’lumotlari so‘rov imkoniyatlarini qo‘shmaydi. Qo‘llab-quvvatlanadigan parametrlar tanlangan usulda ko‘rsatilgan.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaTokenlar uchun bazaviy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaSo‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
Ailoot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen/qwen3.8-flash", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='qwen/qwen3.8-flash',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='qwen/qwen3.8-flash',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Har bir javob variantini va uning kontenti, vosita chaqiruvlari hamda fikrlash ma’lumotlarini saqlang. SSEda o‘zgarish qismlarini variant va vosita indeksi bo‘yicha yig‘ing, yakuniy tugash sababi va sarf ma’lumotlarini saqlang.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonchoices[].index | Turinteger |
Maydonchoices[].message.content | Turstring|null |
Maydonchoices[].message.tool_calls | Turtool_call[] |
Maydonchoices[].message.reasoning_content | Turstring |
Maydonchoices[].message.reasoning_details | Turobject|array |
Maydonchoices[].finish_reason | Turstring|null |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
qwen/qwen3.8-flashKatta kontekstli dasturiy agentlar va ofis vazifalari uchun multimodal model. Ailoot’da matn va tasvirlarni tahlil qilib, matnli javob shakllantiradi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Qwen3.8-Flash dastur yaratish, ketma-ket ofis ishlari va vizual materiallarni tushunishni birlashtiradi. Alibaba uni amallarni rejalashtiradigan, qayta aloqa oladigan va keyingi qadamlarni aniqlashtiradigan agent uchun model sifatida tavsiflaydi. E’lon qilingan yo‘nalishlar orasida dasturiy vositalarni yaratish va rivojlantirish, ish hujjatlari bilan ishlash hamda yechimi ekran yoki hujjat mazmuniga bog‘liq vazifalar bor.
Arxitekturada 125 mlrd parametr mavjud, ulardan bitta token uchun 6 mlrd parametr faollashadi. Gibrid diqqat mexanizmi uzun ketma-ketlikni saqlash va kerakli ma’lumotlarni ajratib olish uchun GDN va QSA’ni birlashtiradi. Qoldiq bog‘lanishlar mexanizmi axborot oqimini to‘rtta parallel tarmoqqa ajratadi, N-gram Embedding mexanizmi esa 51 mlrd parametr qo‘shadi; o‘qitishda Muon optimizatori ishlatiladi. Bunday tuzilish modelning ichki qurilishiga tegishli. Joriy Ailoot kartasida kirishda matn va tasvirlar, chiqishda esa matn taqdim etilgan. Alibaba videoni birgalikda qayta ishlashni ham tavsiflaydi; video kirishi alohida qo‘llab-quvvatlashni talab qiladi va kartaning joriy metodlarida taqdim etilmagan.
Model skrinshotlarni tahlil qilishi, hujjatlardan matn ajratib olishi va kod tayyorlashda tasvirdan yo‘nalish sifatida foydalanishi mumkin. Alibaba tavsiflagan variantda video kadrlar orqali tahlil qilinadi: bu sodir bo‘layotgan voqealarni tavsiflash, o‘quv roligi mazmunini ajratib olish va vizual tafsilotlarni tekshirishga imkon beradi. Modelning o‘z chiqishi matnli — tushuntirish, dastur kodi, vosita chaqiruvi yoki tuzilmali ma’lumotlar.
Ulangan ilova bajaradigan funksiyalar qo‘llab-quvvatlanadi. Mulohaza yuritish rejimida model avval qaysi amallar kerakligi va ularning natijasidan qanday foydalanishni aniqlaydi, so‘ng javobni davom ettiradi. Oldingi mulohazani saqlash vositalar bilan uzoq ishlashga yordam beradi. Tuzilmali chiqish keyinchalik dastur qayta ishlaydigan ma’lumotlarni ajratib olishga mos keladi; kerakli tuzilma va maydon turlarini belgilash mumkin. Ishlab chiqaruvchida qat’iy sxema matnli so‘rovlarga tegishli. Tasvirlar va boshqa multimodal ma’lumotlarda json_schema avtomatik ravishda json_object bilan almashtiriladi: natija JSON ko‘rinishida bo‘ladi, lekin belgilangan sxema cheklovlari qo‘llanilmaydi. Bu sozlamalar mavjudligi tanlangan Ailoot metodiga bog‘liq.
Qwen3.8-Flash mulohaza yuritish va bevosita javob berishni qo‘llab-quvvatlaydi. Ishlab chiqaruvchida mulohaza yuritish standart holatda yoqilgan, odatiy intensivlik — xhigh; sozlamalarning qo‘llab-quvvatlanishi tanlangan metodga bog‘liq. low darajasi oddiy savollar va ma’lumot ajratib olish uchun, medium — kundalik dasturlash va hujjat tayyorlash uchun, xhigh esa murakkab kod, matematik isbotlar va arxitektura vazifalari uchun mo‘ljallangan. Tanlangan chuqurlik dastlabki tahlil hajmiga ta’sir qiladi. Agar tanlangan metod bu sozlamalarni taqdim etsa, ishlab chiqaruvchida reasoning_effort yoki thinking_budget ishlatiladi; bu ikki boshqaruv parametrini birga yuborish xatoga olib keladi. Mulohaza yuritish o‘chirilsa, model darhol javobni shakllantiradi.
Kontekstga 1 000 000 token sig‘adi. Kirishning maksimal uzunligi — 991 808 token, mulohaza yuritish rejimida — 983 616. Maksimal chiqish 131 072 tokenni, mulohaza yuritishning alohida chegarasi esa 262 144 tokenni tashkil etadi. Alibaba’ning vizual spetsifikatsiyasida 16 mln pikselgacha tasvirlar va hajmi 2 GB gacha bo‘lgan ikki soatgacha videolar ko‘rsatilgan. Ishlab chiqaruvchi bir so‘rovda manzil orqali 2048 tagacha yoki Base64’da 250 tagacha tasvir va 64 tagacha videoni ko‘zda tutadi. Bu chegaralar umumiy kontekst bilan birga amal qiladi va ishlab chiqaruvchi variantini tavsiflaydi; Ailoot’ning joriy metodlari video kirishi yoki shu miqdoriy limitlarni emas, matn va tasvirli kirishni e’lon qiladi.
Kontekstning takrorlanuvchi qismini keyingi so‘rovlar uchun keshlash mumkin. Mexanizm kiruvchi materiallarning umumiy boshlanishi bilan ishlaydi; uning mavjudligi topshiriq mazmunini o‘zgartirmaydi va har bir so‘rov albatta oldin saqlangan kontekstdan foydalanishini anglatmaydi.
POST /v1/messagestextjson, sse| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar qwen/qwen3.8-flash | Standart— |
Maydonmessages | Turmessage[] | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
Maydonmessages[].role | Turstring | TalabMajburiy | Qiymatlar va cheklovlar user, assistant | Standart— |
Maydonmessages[].content | Turstring | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
Maydonmax_tokens | Turinteger | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Matn · UTF-8 matni
messages[].content satri
| Parametr | Parametr talablari |
|---|---|
Parametrcontent_type | Parametr talablariapplication/json |
Parametrrequired | Parametr talablarimodel, messages, max_tokens |
Parametroptional_controls | Parametr talablaristream |
Parametrmaterial_types | Parametr talablaritext |
Parametrtext_file_material | Parametr talablariHaqiqiy UTF-8 hujjatini o‘qing va uning matnini ko‘rsatilgan kirish yoki xabar kontenti satriga joylashtiring. |
Hayot sikli: synchronous_or_streamed
Tarif ma’lumotlari so‘rov imkoniyatlarini qo‘shmaydi. Qo‘llab-quvvatlanadigan parametrlar tanlangan usulda ko‘rsatilgan.
Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.
| Sozlama | Tariflar jadvali | Kontekst tokenlari soni bundan ko‘p | Kontekst tokenlari soni bundan oshmaydi, chegara kiradi | To‘lov |
|---|---|---|---|---|
| SozlamaTokenlar uchun bazaviy tariflar | Tariflar jadvaliAsosiy tarif | Kontekst tokenlari soni bundan ko‘p— | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
| SozlamaSo‘rov uzunligi bo‘yicha 1-daraja | Tariflar jadvali— | Kontekst tokenlari soni bundan ko‘p0 | Kontekst tokenlari soni bundan oshmaydi, chegara kiradiYuqori chegara yo‘q | To‘lov Kirish · Kirish tokenlari $0.0003 / 1K token Chiqish · Chiqish tokenlari $0.00094 / 1K token Kirish · Keshdan o‘qish $0.000032 / 1K token Kirish · Keshga yozish $0.0004 / 1K token Kirish · Keshga yozish, 1 soat — / 1K token |
Ailoot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
{\n "model": "qwen/qwen3.8-flash",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'qwen/qwen3.8-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'qwen/qwen3.8-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON yoki SSE
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Barcha kontent bloklari, fikrlash imzolari va haqiqiy vosita ishlatish IDlarini saqlang. SSE bloklarining barcha o‘zgarish qismlarini yig‘ing; birinchi matn bloki to‘liq chiqish emas.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
Maydonid | Turstring |
Maydonmodel | Turstring |
Maydoncontent[] | Turtext|thinking|tool_use|other content block |
Maydonstop_reason | Turstring|null |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Ailoot qwen3.8-flash, qwen-flash, qwen-flash-latest
Ailoot Ultra qwen3.8-flash, qwen/qwen3.8-flash
/chat/completions
qwen/qwen3.8-flash, qwen-flash, qwen-flash-latest, qwen3.8-flash, qwen3.8-flash
Ingliz tilidagi texnik misol
Reconcile a business table and note\n\nReconcile this table: Team A opened 30 cases and closed 24; Team B opened 20 and closed 25. Manager note: “Both backlogs fell.” Assume no transfers or other adjustments. Calculate each team’s backlog change, assess the note and draft a corrected two-sentence update. Keep calculations separate from proposed explanations.Two net-change calculations, an assessment of the note and a corrected short update.Check the sign convention and avoid inventing a cause for either team’s change.