Gemini 3.6 Flash mulohaza yuritish takrorlanuvchi amallar bilan birlashadigan amaliy vazifalar uchun mo‘ljallangan. Google kod yaratish, fazoviy tahlil va bir nechta iteratsiyali tez dasturlash sikllarini ta’kidlaydi. Model Gemini 3.5 Flash’ga asoslangan.
Google kirishda matn, tasvirlar, video, audio va PDF qo‘llab-quvvatlanishini tavsiflaydi. Ailoot API’ning joriy katalogida matnli metodlar uchun kirishda matn va tasvirlar, chiqishda esa matn e’lon qilingan. Video, audio va PDF bu kirishlar to‘plamiga kiritilmagan. Yuborilgan materiallar uchun 1 048 576 tagacha token, matnli javob uchun esa 65 536 tagacha token mavjud. Tasvirlar va video kontekstni tushunish uchun ishlatiladi; o‘z tasviri, videoroligi yoki ovozlashtirishi bu versiyaning chiqishi emas.
Model Thinking, tuzilmali javoblar, funksiya chaqiruvlari, kod bajarish va kontekstni keshlashni qo‘llab-quvvatlaydi. Google tavsiflagan bazaviy model rejimida standart daraja — medium; minimal, low, medium, high mavjud. Bu qiymatlar Google’ning bazaviy modelini tavsiflaydi; Ailoot API orqali boshqarish rejimi va mavjudligi tanlangan metod hamda model variantiga bog‘liq. Bu uni material avval tahlil qilinadigan, keyin vosita tomonidan qayta ishlanadigan va natija keyingi qadamda ishlatiladigan ish sikliga kiritishga imkon beradi. Ishlab chiqaruvchi mos ssenariylarga dasturlash, video bo‘yicha murakkab mulohaza va tashkilotlar ish jarayonlarini kiritadi.
Fayllar bo‘yicha qidiruv, qidiruv natijalari bilan asoslash, Google Maps va berilgan veb-manzillar mazmunidan foydalanish ham ko‘zda tutilgan. Paketli qayta ishlash vazifalar guruhi uchun xizmat qiladi. Kompyuter interfeysini boshqarish dastlabki maqomga ega; modelda bu imkoniyat qo‘llab-quvvatlanishining o‘zi uning har qanday chaqirish metodi orqali mavjudligini anglatmaydi.
Ichki bilimlar uchun ishlab chiqaruvchi ko‘rsatgan chegara — 2026-yil mart. Bunda ayrim sohalardagi ma’lumotlar 2025-yil yanvar darajasida qolishi mumkin. Yuborilgan material va dolzarb ma’lumotli vositalar aniq so‘rov mazmunini kengaytiradi, lekin ichki bilimlarning bu chegarasini o‘zgartirmaydi.
Google to‘qima ma’lumotlar, vaqti-vaqti bilan sekinlashish va kutish vaqti tugashi mumkinligini qayd etadi. Ishlab chiqaruvchi ma’lumotiga ko‘ra, model tez ish iteratsiyalariga yo‘naltirilgan, biroq javobning aniq davomiyligi bajarilayotgan topshiriqqa bog‘liq. Katta kontekst mavjudligi har bir parcha xatosiz qayta ishlanishi kafolatini emas, materiallarning ruxsat etilgan hajmini anglatadi.
gemini-3.6-flash versiyasi barqaror maqomga ega va 2026-yil iyulda e’lon qilingan. Uning yo‘nalishi — multimodal tahlil va qo‘llab-quvvatlanadigan vositalardan foydalanishdan keyingi matnli natija.
Ingliz tilidagi texnik misol
Revise a route after a new constraint\n\nA robot moves one cell north, south, east or west per step. Columns are A–C and rows 1–3. Start at A1 and reach C3; B2 is blocked. A previous route used A1,B1,C1,C2,C3, but C2 is now blocked too. Provide a revised shortest route and verify each move against both obstacles.An ordered cell sequence, step count and a brief validity/minimality check.Every move joins adjacent cells, avoids B2 and C2, and ends at C3.gemini-3.6-flash-mediumDasturlash, fazoviy tahlil va vositalar bilan tez ish sikllari uchun Google’ning multimodal modeli.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Gemini 3.6 Flash mulohaza yuritish takrorlanuvchi amallar bilan birlashadigan amaliy vazifalar uchun mo‘ljallangan. Google kod yaratish, fazoviy tahlil va bir nechta iteratsiyali tez dasturlash sikllarini ta’kidlaydi. Model Gemini 3.5 Flash’ga asoslangan.
Google kirishda matn, tasvirlar, video, audio va PDF qo‘llab-quvvatlanishini tavsiflaydi. Ailoot API’ning joriy katalogida matnli metodlar uchun kirishda matn va tasvirlar, chiqishda esa matn e’lon qilingan. Video, audio va PDF bu kirishlar to‘plamiga kiritilmagan. Yuborilgan materiallar uchun 1 048 576 tagacha token, matnli javob uchun esa 65 536 tagacha token mavjud. Tasvirlar va video kontekstni tushunish uchun ishlatiladi; o‘z tasviri, videoroligi yoki ovozlashtirishi bu versiyaning chiqishi emas.
Model Thinking, tuzilmali javoblar, funksiya chaqiruvlari, kod bajarish va kontekstni keshlashni qo‘llab-quvvatlaydi. Google tavsiflagan bazaviy model rejimida standart daraja — medium; minimal, low, medium, high mavjud. Bu qiymatlar Google’ning bazaviy modelini tavsiflaydi; Ailoot API orqali boshqarish rejimi va mavjudligi tanlangan metod hamda model variantiga bog‘liq. Bu uni material avval tahlil qilinadigan, keyin vosita tomonidan qayta ishlanadigan va natija keyingi qadamda ishlatiladigan ish sikliga kiritishga imkon beradi. Ishlab chiqaruvchi mos ssenariylarga dasturlash, video bo‘yicha murakkab mulohaza va tashkilotlar ish jarayonlarini kiritadi.
Fayllar bo‘yicha qidiruv, qidiruv natijalari bilan asoslash, Google Maps va berilgan veb-manzillar mazmunidan foydalanish ham ko‘zda tutilgan. Paketli qayta ishlash vazifalar guruhi uchun xizmat qiladi. Kompyuter interfeysini boshqarish dastlabki maqomga ega; modelda bu imkoniyat qo‘llab-quvvatlanishining o‘zi uning har qanday chaqirish metodi orqali mavjudligini anglatmaydi.
Ichki bilimlar uchun ishlab chiqaruvchi ko‘rsatgan chegara — 2026-yil mart. Bunda ayrim sohalardagi ma’lumotlar 2025-yil yanvar darajasida qolishi mumkin. Yuborilgan material va dolzarb ma’lumotli vositalar aniq so‘rov mazmunini kengaytiradi, lekin ichki bilimlarning bu chegarasini o‘zgartirmaydi.
Google to‘qima ma’lumotlar, vaqti-vaqti bilan sekinlashish va kutish vaqti tugashi mumkinligini qayd etadi. Ishlab chiqaruvchi ma’lumotiga ko‘ra, model tez ish iteratsiyalariga yo‘naltirilgan, biroq javobning aniq davomiyligi bajarilayotgan topshiriqqa bog‘liq. Katta kontekst mavjudligi har bir parcha xatosiz qayta ishlanishi kafolatini emas, materiallarning ruxsat etilgan hajmini anglatadi.
gemini-3.6-flash versiyasi barqaror maqomga ega va 2026-yil iyulda e’lon qilingan. Uning yo‘nalishi — multimodal tahlil va qo‘llab-quvvatlanadigan vositalardan foydalanishdan keyingi matnli natija.
POST /v1/messagestext, imagetext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar gemini-3.6-flash-medium | 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 →
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": "gemini-3.6-flash-medium", "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": "gemini-3.6-flash-medium", "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="gemini-3.6-flash-medium",\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: "gemini-3.6-flash-medium",\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='gemini-3.6-flash-medium',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 gemini-3.6-flash-medium
Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.
gemini-3.6-flash-mediumDasturlash, fazoviy tahlil va vositalar bilan tez ish sikllari uchun Google’ning multimodal modeli.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
Gemini 3.6 Flash mulohaza yuritish takrorlanuvchi amallar bilan birlashadigan amaliy vazifalar uchun mo‘ljallangan. Google kod yaratish, fazoviy tahlil va bir nechta iteratsiyali tez dasturlash sikllarini ta’kidlaydi. Model Gemini 3.5 Flash’ga asoslangan.
Google kirishda matn, tasvirlar, video, audio va PDF qo‘llab-quvvatlanishini tavsiflaydi. Ailoot API’ning joriy katalogida matnli metodlar uchun kirishda matn va tasvirlar, chiqishda esa matn e’lon qilingan. Video, audio va PDF bu kirishlar to‘plamiga kiritilmagan. Yuborilgan materiallar uchun 1 048 576 tagacha token, matnli javob uchun esa 65 536 tagacha token mavjud. Tasvirlar va video kontekstni tushunish uchun ishlatiladi; o‘z tasviri, videoroligi yoki ovozlashtirishi bu versiyaning chiqishi emas.
Model Thinking, tuzilmali javoblar, funksiya chaqiruvlari, kod bajarish va kontekstni keshlashni qo‘llab-quvvatlaydi. Google tavsiflagan bazaviy model rejimida standart daraja — medium; minimal, low, medium, high mavjud. Bu qiymatlar Google’ning bazaviy modelini tavsiflaydi; Ailoot API orqali boshqarish rejimi va mavjudligi tanlangan metod hamda model variantiga bog‘liq. Bu uni material avval tahlil qilinadigan, keyin vosita tomonidan qayta ishlanadigan va natija keyingi qadamda ishlatiladigan ish sikliga kiritishga imkon beradi. Ishlab chiqaruvchi mos ssenariylarga dasturlash, video bo‘yicha murakkab mulohaza va tashkilotlar ish jarayonlarini kiritadi.
Fayllar bo‘yicha qidiruv, qidiruv natijalari bilan asoslash, Google Maps va berilgan veb-manzillar mazmunidan foydalanish ham ko‘zda tutilgan. Paketli qayta ishlash vazifalar guruhi uchun xizmat qiladi. Kompyuter interfeysini boshqarish dastlabki maqomga ega; modelda bu imkoniyat qo‘llab-quvvatlanishining o‘zi uning har qanday chaqirish metodi orqali mavjudligini anglatmaydi.
Ichki bilimlar uchun ishlab chiqaruvchi ko‘rsatgan chegara — 2026-yil mart. Bunda ayrim sohalardagi ma’lumotlar 2025-yil yanvar darajasida qolishi mumkin. Yuborilgan material va dolzarb ma’lumotli vositalar aniq so‘rov mazmunini kengaytiradi, lekin ichki bilimlarning bu chegarasini o‘zgartirmaydi.
Google to‘qima ma’lumotlar, vaqti-vaqti bilan sekinlashish va kutish vaqti tugashi mumkinligini qayd etadi. Ishlab chiqaruvchi ma’lumotiga ko‘ra, model tez ish iteratsiyalariga yo‘naltirilgan, biroq javobning aniq davomiyligi bajarilayotgan topshiriqqa bog‘liq. Katta kontekst mavjudligi har bir parcha xatosiz qayta ishlanishi kafolatini emas, materiallarning ruxsat etilgan hajmini anglatadi.
gemini-3.6-flash versiyasi barqaror maqomga ega va 2026-yil iyulda e’lon qilingan. Uning yo‘nalishi — multimodal tahlil va qo‘llab-quvvatlanadigan vositalardan foydalanishdan keyingi matnli natija.
POST /v1beta/models/{model}:generateContenttext, imagetext| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonpath.model | Turstring | TalabMajburiy | Qiymatlar va cheklovlar gemini-3.6-flash-medium | Standart— |
Maydoncontents | Turcontent[] | TalabMajburiy | Qiymatlar va cheklovlar Elementlarning eng kam soni: 1 | Standart— |
Maydoncontents[].role | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar user, model | Standart— |
Maydoncontents[].parts | Turpart[] | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
MaydonsystemInstruction | Turcontent | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
MaydongenerationConfig.maxOutputTokens | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
MaydongenerationConfig.temperature | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
MaydongenerationConfig.topP | Turnumber | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
MaydongenerationConfig.topK | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
MaydongenerationConfig.stopSequences | Turstring[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
MaydongenerationConfig.thinkingConfig.includeThoughts | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
MaydongenerationConfig.thinkingConfig.thinkingBudget | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydontools[].functionDeclarations | Turfunction_declaration[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
MaydontoolConfig.functionCallingConfig.mode | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
MaydonsafetySettings | Turobject[] | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
MaydonsessionId | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
Matn · UTF8 matni
contents[].parts[].text
Matn + rasm
parts[].inlineData={mimeType,data}
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext, image |
Parametrrequired | Parametr talablaricontents |
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 /v1beta/models/{model}:generateContentAiloot 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}"\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('{"contents": []}')\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["contents"]=[{"role":"user","parts":[{"text":"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/v1beta/models/gemini-3.6-flash-medium:generateContent \\\n -H "x-goog-api-key: $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('{"contents": [{"role": "user", "parts": [{"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["contents"][0]["parts"].append({"inlineData":{"mimeType":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/v1beta/models/gemini-3.6-flash-medium:generateContent \\\n -H "x-goog-api-key: $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 google import genai\nfrom google.genai import types\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = genai.Client(\n api_key=os.environ["AILOOT_API_KEY"],\n http_options=types.HttpOptions(base_url="https://api.ailoot.ai"),\n)\nresp = client.models.generate_content(model="gemini-3.6-flash-medium", contents="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_json_dict())\nimport { GoogleGenAI } from "@google/genai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst ai = new GoogleGenAI({ apiKey: process.env.AILOOT_API_KEY, httpOptions: { baseUrl: "https://api.ailoot.ai" } });\nconst resp = await ai.models.generateContent({ model: "gemini-3.6-flash-medium", contents: "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 google import genai\nfrom google.genai import types\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=genai.Client(api_key=os.environ["AILOOT_API_KEY"],http_options=types.HttpOptions(base_url="https://api.ailoot.ai"))\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\ncount=0\nwith Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for chunk in client.models.generate_content_stream(model='gemini-3.6-flash-medium',contents="Explain observations and hypotheses in three sentences."):\n payload=chunk.to_json_dict()\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n save_result(payload,"stream-chunk-"+str(count))\n count+=1\njson yoki qo‘llab-quvvatlanadigan oqimli uzatish
Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.
Funksiya chaqiruvlari, fikrlash imzolari va sarf ma’lumotlari bilan birga barcha nomzod javoblar va qismlarni saqlang; oqim qismlarini tartib bilan yig‘ing.
So‘rov va javob IDlari hamda sarlavhalarini saqlang. Matn vazifasini olish uchun umumiy URL taqdim etilmagan.
| Maydon | Tur |
|---|---|
MaydonresponseId | Turstring |
MaydonmodelVersion | Turstring |
Maydoncandidates[].content.parts[] | Turtext|inlineData|functionCall|other part |
Maydoncandidates[].finishReason | Turstring |
MaydonusageMetadata | 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 gemini-3.6-flash-medium
Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.
Ingliz tilidagi texnik misol
Revise a route after a new constraint\n\nA robot moves one cell north, south, east or west per step. Columns are A–C and rows 1–3. Start at A1 and reach C3; B2 is blocked. A previous route used A1,B1,C1,C2,C3, but C2 is now blocked too. Provide a revised shortest route and verify each move against both obstacles.An ordered cell sequence, step count and a brief validity/minimality check.Every move joins adjacent cells, avoids B2 and C2, and ends at C3.