Source: https://ailoot.ai/models/uz/thinkingmachines-inkling-small/
Canonical: https://ailoot.ai/models/uz/thinkingmachines-inkling-small/
Language: uz

# Thinking Machines: Inkling Small

[Markdown](https://ailoot.ai/models/uz/thinkingmachines-inkling-small/index.md) · [JSON](https://ailoot.ai/models/uz/thinkingmachines-inkling-small/facts.json)

## [Thinking Machines: Inkling Small](https://ailoot.ai/models/uz/thinkingmachines-inkling-small/)

Thinking Machines Lab’ning Inkling-Small modeli — matn, tasvir va audio ustida mulohaza yuritish uchun 12B faol parametrli 276B MoE model. U matn yaratadi, vositalarga qaratilgan ilovalarni qo‘llab-quvvatlaydi va 1M model kontekstiga ega; ishlab chiqaruvchi xizmatining qisqaroq kontekstlari alohida hisobga olinadi.

- [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `thinkingmachines/inkling-small`](https://ailoot.ai/models/uz/thinkingmachines-inkling-small/#method-0)
- [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `thinkingmachines/inkling-small`](https://ailoot.ai/models/uz/thinkingmachines-inkling-small/#method-1)

Model haqida

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

Inkling-Small — Thinking Machines Lab’ning kichikroq umumiy maqsadli multimodal modeli. Uning rasmiy kartochkasida jami 276 milliard parametr va 12B faol parametr ko‘rsatilgan. U matn, tasvir va audioni qabul qiladi hamda suhbat, dasturlash, mulohaza yuritish, topilgan ma’lumot bilan boyitilgan va vositalarga qaratilgan ilovalar uchun matn yaratadi. U kattaroq Inkling modelidan alohida nashrdir.

Arxitekturada 42 dekoder qatlami va siyrak ekspertlar tarmog‘i ishlatiladi. Token 256 yo‘naltiriladigan ekspertdan oltitasini va yana ikkita umumiy ekspertni tanlaydi; mahalliy va global diqqat aralashmasi qo‘llanadi. Tasvir bo‘laklari va diskret audio tokenlari dekoderning umumiy ifodasiga proyeksiya qilinadi. Alohida BF16 va NVFP4 artefaktlari o‘z aniqlik identifikatoriga ega.

Ishlab chiqaruvchi 1M model kontekstini ta’riflaydi, uning o‘qitish xizmati esa 64K va 256K konfiguratsiyalarini taklif qiladi. Bular o‘zaro almashtiriladigan oyna o‘lchamlari emas, alohida qamrovlardir. Uzun materialda topshiriq ishlatayotgan haqiqiy kontekstni aniqlang va model fikrlashi hamda yakuniy javob uchun joy qoldiring. Ishlab chiqaruvchining umumiy Inkling rendereri 0.0 dan boshlab, 1.0 ni kiritmagan holda chekli daraja qiymatini qabul qiladi; qiymat berilmasa, 0.9 ishlatadi. Nol mulohazani qat’iy taqiqlamasdan, bevosita javobga undaydi.

Kirishni tayyorlash aniq talablarga ega. Kartochka o‘lchamlari imkon qadar 40 dan 4096 pikselgacha bo‘lgan tasvirlarni tavsiya qiladi. Audio 16 kHz chastotali WAV bo‘lishi va ushbu Small nashri uchun imkon qadar ikki daqiqadan qisqa bo‘lishi kerak. Bular optimal kirish tavsiyalari; model ularning tashqarisidagi har bir kirishni rad etishi haqidagi va’dalar emas. Natija generatsiya qilingan nutq yoki video emas, UTF-8 matn.

Tasvirga oid savolda tekshiriladigan xususiyat va uning yozma topshiriqqa aloqasini belgilang. Audio uchun foydali natija mazmun izohi, xulosa yoki boshqa matnli tahlil bo‘lishini ko‘rsating. Materialni talqin qilish uchun zarur lug‘at va fon ma’lumotini bering. Kod yoki ma’lumot izlash topshirig‘i tegishli manba yoki topilgan parchalar va istalgan materialni taqdim etishi kerak.

Vosita bilan bog‘langan ilovada model o‘zaro amallarni taklif qiladi, ilova esa ularning natijalarini qaytaradi. Keyingi qadam yuz bergan voqeadan foydalanishi uchun shu kuzatuvlarni keyingi savollarda saqlang. Ishlab chiqaruvchi modelni moslashtirish va qo‘shimcha o‘qitish uchun chiqaradi; alohida moslashtirilgan nazorat nuqtasi esa asl Small modelidan alohida qoladi.

Ishlab chiqaruvchi ba’zan ko‘rsatmaga amal qilmaslik, asossiz faktik bayonotlar va uzun suhbatlarda sifat pasayishini, kamroq namoyish etilgan tillar va sohalarda esa notekis natijani ko‘rsatadi. U multimodal xavfsizlik baholashi va ayrim bilvosita shakllantirilgan promptlarga qolgan sezgirlikni ham ta’riflaydi. Model natijasini jarayonda ishlatganda manba dalillari va ilovaga xos chiqish nazoratlarini saqlang.

Amaliy vazifa

### Amaliy vazifa

Ingliz tilidagi texnik misol

```
Answer from retrieved training material

Answer a new employee using only these retrieved passages. [DOC1] Draft reports may be edited by their author. [DOC2] Approved reports are locked; corrections create a new version. Question: 'I found a typo in an approved report. Can I edit it directly?' Give a concise answer, the supporting document label and one appropriate next step without claiming a change occurred.
```

#### Kutiladigan natija

```
A short source-grounded answer with DOC2 support and a proposed version-based correction step.
```

#### Natijani tekshirish

```
Check the approved/draft distinction is preserved and no lock is bypassed in the suggestion.
```

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `thinkingmachines/inkling-small`

[`thinkingmachines/inkling-small`](https://ailoot.ai/models/uz/#m=thinkingmachines%2Finkling-small&route=Ultra&caller=thinkingmachines%2Finkling-small&fmt=chat)

Thinking Machines /`thinkingmachines/inkling-small`

### Boshlash

Thinking Machines Lab’ning Inkling-Small modeli — matn, tasvir va audio ustida mulohaza yuritish uchun 12B faol parametrli 276B MoE model. U matn yaratadi, vositalarga qaratilgan ilovalarni qo‘llab-quvvatlaydi va 1M model kontekstiga ega; ishlab chiqaruvchi xizmatining qisqaroq kontekstlari alohida hisobga olinadi.

Qabul qilinadigan kirish ma’lumotlari

Matn

Natijalar

Matn

### Ailoot da mavjud · kirish ma’lumotlari va usullar

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions`

Kirish

`text`

Chiqish

`text`

Chiqish formati

json yoki SSE

| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
| --- | --- | --- | --- | --- |
| Maydon`model` | Tur`string` | TalabMajburiy | Qiymatlar va cheklovlar thinkingmachines/inkling-small | Standart— |
| Maydon`messages` | Tur`message[]` | TalabMajburiy | Qiymatlar va cheklovlar Elementlarning eng kam soni: 1 | Standart— |
| Maydon`messages[].role` | Tur`string` | 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— |
| Maydon`messages[].content` | Tur`string\|content_part[]\|null` | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
| Maydon`messages[].tool_calls` | Tur`tool_call[]` | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
| Maydon`messages[].tool_call_id` | Tur`string` | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: role=tool; haqiqatan qaytarilgan IDdan foydalaning | Standart— |
| Maydon`messages[].name` | Tur`string` | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
| Maydon`messages[].reasoning_content` | Tur`string` | TalabIxtiyoriy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Ushbu model foydalanganda, haqiqatan qaytarilgan fikrlash ma’lumotlarini keyingi so‘rovda qayta yuboring | Standart— |
| Maydon`messages[].reasoning_details` | Tur`object\|array` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`max_tokens` | Tur`integer` | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
| Maydon`max_completion_tokens` | Tur`integer` | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 Modelga bogʻliq | Standart— |
| Maydon`stream` | Tur`boolean` | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
| Maydon`stream_options.include_usage` | Tur`boolean` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`temperature` | Tur`number` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`top_p` | Tur`number` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`stop` | Tur`string\|string[]` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`tools` | Tur`function_tool[]` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`tools[].type` | Tur`string` | TalabIxtiyoriy | Qiymatlar va cheklovlar function Modelga bogʻliq | Standart— |
| Maydon`tools[].function.name` | Tur`string` | TalabMajburiy | Qiymatlar va cheklovlar Quyidagi holatda qo‘llanadi: Funksiya vositasi taqdim etilgan | Standart— |
| Maydon`tools[].function.description` | Tur`string` | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
| Maydon`tools[].function.parameters` | Tur`JSON_schema` | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standart— |
| Maydon`tool_choice` | Tur`string\|object` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`parallel_tool_calls` | Tur`boolean` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`response_format` | Tur`object` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`reasoning_effort` | Tur`string` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`reasoning` | Tur`object` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`service_tier` | Tur`string` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`instructions` | Tur`string` | TalabIxtiyoriy | Qiymatlar va cheklovlar Moslik maydoni | Standart— |
| Maydon`functions` | Tur`function[]` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`function_call` | Tur`string\|object` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`prompt_cache_options` | Tur`object` | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
| Maydon`modalities` | Tur`string[]` | TalabIxtiyoriy | Qiymatlar va cheklovlar text | Standart— |
| Maydon`provider` | Tur`object` | TalabIxtiyoriy | Qiymatlar va cheklovlar Shartlar: Ushbu Ultra matn marshrutida provider.options rad etiladi | Standart— |
| Maydon`cache_control.ttl` | Tur`string` | TalabIxtiyoriy | Qiymatlar va cheklovlar Shartlar: Haqiqiy prompt-kesh joylarida 1h rad etiladi | Standart— |

Kirish materiallari birikmalari

**Matn** · UTF8 matni

`messages[].content`

Usul parametrlari va hayot sikli

| Parametr | Parametr talablari |
| --- | --- |
| Parametr`content_type` | Parametr talablariapplication/json |
| Parametr`required` | Parametr talablarimodel, messages |
| Parametr`material_types` | Parametr talablaritext |
| Parametr`messages` | Parametr talablarirole/content tuzilishidagi xabarlar massivi |
| Parametr`file_material` | Parametr talablariHaqiqiy UTF-8 hujjati aynan matn sifatida kiritiladi; fayl IDsi faraz qilinmaydi |
| Parametr`optional_controls` | Parametr talablaristream, temperature, top\_p, stop, max\_tokens, max\_completion\_tokens, reasoning, response\_format, tools, tool\_choice |
| Parametr`control_scope` | Parametr talablariModelga xos; foydalanuvchi funksiya vositalari hostingdagi vositalardan farq qiladi |
| Parametr`output_modalities` | Parametr talablaritext |
| Parametr`hosted_operations` | Parametr talablarifalse |
| Parametr`multimodal_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.

### Tariflar

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

Tezkor rejim

Standart tarif Tezkor rejim tanlanganda

Flex rejimi

Standart tarif flex rejimi tanlanganda

Maksimal fikrlash darajasi

Standart tarif Maksimal fikrlash darajasi uchun standart (default) tuzatish qo‘llanganda

Fikrlash darajasi · yuqori

Standart tarif Fikrlash darajasi yuqori bo‘lganda

Fikrlash darajasi · past

Standart tarif Fikrlash darajasi past bo‘lganda

Fikrlash darajasi · maksimal

Standart tarif Fikrlash darajasi maksimal bo‘lganda

Fikrlash darajasi · o‘rtacha

Standart tarif Fikrlash darajasi o‘rtacha bo‘lganda

Fikrlash darajasi · minimal

Standart tarif Fikrlash darajasi minimal bo‘lganda

Fikrlash darajasi · yo‘q

Standart tarif Fikrlash darajasi yo‘q bo‘lganda

#### Ailoot tariflari

#### Sozlamalar bo‘yicha narxlar

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 **$0.0009** / 1K token Chiqish · Chiqish tokenlari **$0.0024** / 1K token Kirish · Keshdan o‘qish **$0.0002** / 1K token Kirish · Keshga yozish **—** / 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 **$0.0009** / 1K token Chiqish · Chiqish tokenlari **$0.0024** / 1K token Kirish · Keshdan o‘qish **$0.0002** / 1K token Kirish · Keshga yozish **—** / 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 →](https://ailoot.ai/docs/uz/billing/reserve/)

### So‘rov namunalari

#### Ailoot Ultra · OpenAI Chat

curlPython SDKPython oqimi

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "thinkingmachines/inkling-small", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')

Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("choices",[]):
    if x.get("message",{}).get("content"): print(x["message"]["content"])
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.chat.completions.create(model='thinkingmachines/inkling-small',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(result.to_dict(mode="json"))
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='thinkingmachines/inkling-small',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Natijalarni olish va saqlash

#### Ailoot Ultra · OpenAI Chat

json yoki SSE

##### Barcha tayyor natijalarni saqlash

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

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

##### Asl javobni tekshirish kerak bo‘lsa

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

Javob maydonlari

| Maydon | Tur |
| --- | --- |
| Maydon`choices[].index` | Turinteger |
| Maydon`choices[].message.content` | Turstring\|null |
| Maydon`choices[].message.tool_calls` | Turtool\_call\[\] |
| Maydon`choices[].message.reasoning_content` | Turstring |
| Maydon`choices[].message.reasoning_details` | Turobject\|array |
| Maydon`choices[].finish_reason` | Turstring\|null |
| Maydon`usage` | Turobject |

Xatolar va keyingi qadamlar

| 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. |

### Taxalluslar

#### Model taxalluslari

**Ailoot Ultra** [`thinkingmachines/inkling-small`](https://ailoot.ai/models/uz/#m=thinkingmachines%2Finkling-small&route=Ultra&caller=thinkingmachines%2Finkling-small&fmt=chat)

#### Usul yo‘llari taxalluslari

Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.

#### Chaqirish uchun tegishli ID lar

[`thinkingmachines/inkling-small`](https://ailoot.ai/models/uz/#m=thinkingmachines%2Finkling-small&route=Ultra&caller=thinkingmachines%2Finkling-small&fmt=chat)

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `thinkingmachines/inkling-small`

[`thinkingmachines/inkling-small`](https://ailoot.ai/models/uz/#m=thinkingmachines%2Finkling-small&route=Ultra&caller=thinkingmachines%2Finkling-small&fmt=messages)

Thinking Machines /`thinkingmachines/inkling-small`

### Boshlash

Thinking Machines Lab’ning Inkling-Small modeli — matn, tasvir va audio ustida mulohaza yuritish uchun 12B faol parametrli 276B MoE model. U matn yaratadi, vositalarga qaratilgan ilovalarni qo‘llab-quvvatlaydi va 1M model kontekstiga ega; ishlab chiqaruvchi xizmatining qisqaroq kontekstlari alohida hisobga olinadi.

Qabul qilinadigan kirish ma’lumotlari

Matn

Natijalar

json · sse

### Ailoot da mavjud · kirish ma’lumotlari va usullar

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages`

Kirish

`text`

Chiqish

`json`, `sse`

Chiqish formati

JSON yoki SSE

| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
| --- | --- | --- | --- | --- |
| Maydon`model` | Tur`string` | TalabMajburiy | Qiymatlar va cheklovlar thinkingmachines/inkling-small | Standart— |
| Maydon`messages` | Tur`message[]` | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
| Maydon`messages[].role` | Tur`string` | TalabMajburiy | Qiymatlar va cheklovlar user, assistant | Standart— |
| Maydon`messages[].content` | Tur`string` | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
| Maydon`max_tokens` | Tur`integer` | TalabMajburiy | Qiymatlar va cheklovlar | Standart— |
| Maydon`stream` | Tur`boolean` | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |

Kirish materiallari birikmalari

**Matn** · UTF-8 matni

`messages[].content satri`

Usul parametrlari va hayot sikli

| Parametr | Parametr talablari |
| --- | --- |
| Parametr`content_type` | Parametr talablariapplication/json |
| Parametr`required` | Parametr talablarimodel, messages, max\_tokens |
| Parametr`optional_controls` | Parametr talablaristream |
| Parametr`material_types` | Parametr talablaritext |
| Parametr`text_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`

### Tariflar

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

Tezkor rejim

Standart tarif Tezkor rejim tanlanganda

Flex rejimi

Standart tarif flex rejimi tanlanganda

Maksimal fikrlash darajasi

Standart tarif Maksimal fikrlash darajasi uchun standart (default) tuzatish qo‘llanganda

Fikrlash darajasi · yuqori

Standart tarif Fikrlash darajasi yuqori bo‘lganda

Fikrlash darajasi · past

Standart tarif Fikrlash darajasi past bo‘lganda

Fikrlash darajasi · maksimal

Standart tarif Fikrlash darajasi maksimal bo‘lganda

Fikrlash darajasi · o‘rtacha

Standart tarif Fikrlash darajasi o‘rtacha bo‘lganda

Fikrlash darajasi · minimal

Standart tarif Fikrlash darajasi minimal bo‘lganda

Fikrlash darajasi · yo‘q

Standart tarif Fikrlash darajasi yo‘q bo‘lganda

#### Ailoot tariflari

#### Sozlamalar bo‘yicha narxlar

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 **$0.0009** / 1K token Chiqish · Chiqish tokenlari **$0.0024** / 1K token Kirish · Keshdan o‘qish **$0.0002** / 1K token Kirish · Keshga yozish **—** / 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 **$0.0009** / 1K token Chiqish · Chiqish tokenlari **$0.0024** / 1K token Kirish · Keshdan o‘qish **$0.0002** / 1K token Kirish · Keshga yozish **—** / 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 →](https://ailoot.ai/docs/uz/billing/reserve/)

### So‘rov namunalari

#### Ailoot Ultra · Anthropic Messages

To‘liq minimal JSON so‘rov tanasicurl · O‘zingizning UTF-8 hujjatingizdan foydalaningPython · Natijani to‘liq saqlang

```json
{
  "model": "thinkingmachines/inkling-small",
  "max_tokens": 128,
  "messages": [
    {
      "role": "user",
      "content": "Summarize the incident report."
    }
  ],
  "stream": false
}
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'thinkingmachines/inkling-small', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
PY_RESULT
```

```python
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'thinkingmachines/inkling-small', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
from urllib.request import Request, urlopen
from urllib.error import HTTPError

api_key = os.environ['AILOOT_API_KEY']
if not api_key.strip():
    raise SystemExit('Set AILOOT_API_KEY before making a request')
headers = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}
headers['x-api-key'] = api_key
request = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')
try:
    with urlopen(request, timeout=120) as response:
        raw = response.read()
        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')
except HTTPError as error:
    Path('result.json').write_bytes(error.read())
    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')
    raise
Path('result.json').write_bytes(raw)
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
```

### Natijalarni olish va saqlash

#### Ailoot Ultra · Anthropic Messages

JSON yoki SSE

##### Barcha tayyor natijalarni saqlash

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.

##### Asl javobni tekshirish kerak bo‘lsa

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

Javob maydonlari

| Maydon | Tur |
| --- | --- |
| Maydon`id` | Turstring |
| Maydon`model` | Turstring |
| Maydon`content[]` | Turtext\|thinking\|tool\_use\|other content block |
| Maydon`stop_reason` | Turstring\|null |
| Maydon`usage` | Turobject |

Xatolar va keyingi qadamlar

| 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. |

### Taxalluslar

#### Model taxalluslari

**Ailoot Ultra** [`thinkingmachines/inkling-small`](https://ailoot.ai/models/uz/#m=thinkingmachines%2Finkling-small&route=Ultra&caller=thinkingmachines%2Finkling-small&fmt=messages)

#### Usul yo‘llari taxalluslari

Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.

#### Chaqirish uchun tegishli ID lar

[`thinkingmachines/inkling-small`](https://ailoot.ai/models/uz/#m=thinkingmachines%2Finkling-small&route=Ultra&caller=thinkingmachines%2Finkling-small&fmt=messages)

FAQ · Thinking Machines: Inkling Small

Qanday kirish ma’lumotlari va natijalar mavjud?

`POST /v1/chat/completions` · `thinkingmachines/inkling-small`: `text` → `text` `POST /v1/messages` · `thinkingmachines/inkling-small`: `text` → `json`, `sse`

So‘rov qaysi maydonlardan foydalanadi?

`POST /v1/chat/completions` · `thinkingmachines/inkling-small`: `model`, `messages`, `stream`, `modalities`, `provider` `POST /v1/messages` · `thinkingmachines/inkling-small`: `model`, `messages`, `max_tokens`, `stream`

Qanday cheklovlar amal qiladi?

`POST /v1/chat/completions` · `thinkingmachines/inkling-small`: `messages.min_items`: `1`

Ailoot’ni Claude Code, OpenCode, Hermes yoki ilovangizga ulang.

## Kompaniya va uning loyihalar portfeli

Kompaniya va uning loyihalar portfeli: millionlab mijozlar; oylik sotuvlar hajmi milliardlarda.

## Tokenlarni chegirma bilan xarid qiling.

Muntazam ish uchun obuna chegirmasi. Token xaridiga promokodlar — 50% gacha.

Obuna

Muntazam so‘rovlaringiz uchun chegirmali tarif tanlang.

50% gacha promokod

Xaridda kod kiriting. Narx amaldagi aksiya bilan qayta hisoblanadi.

Tarixdagi xarajatlar

Har so‘rov uchun model, token va summa saqlanadi.

[Obuna tanlash](https://ailoot.ai/docs/uz/billing/subscriptions/) · [Model narxlarini ko‘rish](https://ailoot.ai/models/uz/)

## API’ni sotadigan mahsulotingizga ulang.

SaaS, ilova va botlar Ailoot ofertasi hamda litsenziya shartnomasiga muvofiq. Qayta sotishga reseller litsenziyasi so‘rang.

Tijorat ilovasi

Xizmatingizning pullik funksiyalariga matn, rasm, video va ovoz yaratishni qo‘shing.

Reseller litsenziyasi

Loyiha tavsifi va kirish sxemasini yuboring. Foydalanish va qayta sotishga yozma shartlarni so‘rang.

Saytdagi hujjatlar

Oferta, litsenziya shartnomasi va ma’lumotlar siyosati ulashdan oldin ochiq.

[Reseller litsenziyasini so‘rash](mailto:support@ailoot.ai) · [Oferta va litsenziya shartnomasi](https://ailoot.ai/legal/offer?lang=uz)

## Ailoot · Kompaniya va uning loyihalar portfeli





Ailoot to‘plangan faoliyat tajribasi, keng mijozlar bazasi, barqaror xizmat va doimiy KPI nazoratiga tayanadi.





Kompaniya va uning loyihalar portfeli: millionlab mijozlar; oylik sotuvlar hajmi milliardlarda.





Ailoot bu faoliyat tajribasini mijozlar mahsulotlari, agentlar, ilovalar va avtomatlashtirishlarda AI imkoniyatlariga API orqali kirishni ta’minlashda qo‘llaydi.