Source: https://ailoot.ai/models/id/nvidia-nemotron-3-5-lightning-30b-a3b/
Canonical: https://ailoot.ai/models/id/nvidia-nemotron-3-5-lightning-30b-a3b/
Language: id

# Nemotron 3.5 Lightning 30B A3B

[Markdown](https://ailoot.ai/models/id/nvidia-nemotron-3-5-lightning-30b-a3b/index.md) · [JSON](https://ailoot.ai/models/id/nvidia-nemotron-3-5-lightning-30b-a3b/facts.json)

## [Nemotron 3.5 Lightning 30B A3B](https://ailoot.ai/models/id/nvidia-nemotron-3-5-lightning-30b-a3b/)

Nemotron 3.5 Lightning adalah model teks NVIDIA untuk tugas agen panjang, pemrograman, pencarian dokumen, dan percakapan.

- [**Ailoot · Anthropic Messages** `POST /v1/messages` `nvidia/nemotron-3.5-lightning-30b-a3b`](https://ailoot.ai/models/id/nvidia-nemotron-3-5-lightning-30b-a3b/#method-0)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nvidia/nemotron-3.5-lightning-30b-a3b`](https://ailoot.ai/models/id/nvidia-nemotron-3-5-lightning-30b-a3b/#method-1)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nemotron-lightning`](https://ailoot.ai/models/id/nvidia-nemotron-3-5-lightning-30b-a3b/#method-2)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nemotron-lightning-latest`](https://ailoot.ai/models/id/nvidia-nemotron-3-5-lightning-30b-a3b/#method-3)

Tentang model

Deskripsi ini mencakup kemampuan model. Masukan, keluaran, dan opsi yang tersedia di Ailoot tercantum di bawah untuk metode yang dipilih.

#### Model kerja untuk proses panjang

Nemotron 3.5 Lightning ditujukan untuk agen otonom dan rangkaian tindakan yang berlanjut dalam beberapa langkah. Model juga digunakan pada asisten percakapan, pencarian berdasarkan dokumen, dan pelaksanaan instruksi. Masukan serta keluaran berupa teks.

#### Arsitektur dan konteks

Campuran pakar hibrida memadukan Mamba-2 dan lapisan perhatian tersendiri. Model memiliki keseluruhan 30 miliar parameter, dengan 3 miliar aktif per token. Konteks mencapai satu juta token.

Lapisan prediksi beberapa token berikutnya dilatih lebih lanjut untuk menyelaraskan usulannya dengan distribusi model utama. Rilis ini juga memperkenalkan metode decoding spekulatif. Metode tersebut membantu mengatur generasi, tetapi tidak menetapkan kecepatan permintaan yang dijamin.

#### Lima tahap pelatihan

1. Prapelatihan pada lebih dari 20 triliun token kode, matematika, sains, dan pengetahuan umum dengan pelatihan dalam format NVFP4.
2. Kelanjutan prapelatihan untuk lapisan prediksi beberapa token mendatang: usulannya diselaraskan dengan distribusi model utama.
3. Pembelajaran dari contoh, termasuk instruksi, pemanggilan alat, hasil terstruktur, pengambilan bagian yang berjauhan, dan penggabungan dokumen.
4. Pembelajaran penguatan dalam beberapa lingkungan untuk penalaran, kode, sains, tugas alat bertahap, dan percakapan.
5. Kompresi numerik lanjutan pada varian yang dipublikasikan.

Tahap terakhir mencirikan rilis produsen tertentu dan tidak menetapkan presisi komputasi permintaan yang dilayani. Dalam proses eksternal, model mengusulkan tindakan dan hasil teks; alat dijalankan aplikasi.

#### Bahasa dan versi

Bahasa yang secara resmi dicantumkan adalah Inggris, Spanyol, Prancis, Jerman, Italia, dan Jepang, serta bahasa pemrograman. Batas data prapelatihan dinyatakan hingga September 2025, sedangkan pelatihan selanjutnya hingga Mei 2026.

Karakteristik rilis yang dipublikasikan dengan kompresi numerik secara khusus menjelaskan varian tersebut. Nama model tidak dapat menentukan presisi komputasi pelaksanaan tertentu. Satu juta token merupakan konteks keseluruhan, bukan janji panjang keluaran tersendiri.

Tugas praktis

### Tugas praktis

Contoh teknis dalam bahasa Inggris

```
Apply a document-grounded procedure

Use these procedure excerpts to draft the next action for case C-09. [Rule 1] Packages with a damaged seal go to inspection. [Rule 2] Only inspection-cleared packages enter stock. [Record] C-09 has a damaged seal and no inspection result. Return the current permitted step, blocked step and supporting rule labels.
```

#### Hasil yang diharapkan

```
Three concise fields covering the permitted inspection step, blocked stocking and source evidence.
```

#### Periksa hasil

```
Check that missing inspection clearance prevents stocking and does not become an assumed failed inspection.
```

**Ailoot · Anthropic Messages** `POST /v1/messages` `nvidia/nemotron-3.5-lightning-30b-a3b`

[`nvidia/nemotron-3.5-lightning-30b-a3b`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&fmt=messages)

NVIDIA /`nvidia/nemotron-3.5-lightning-30b-a3b`

### Mulai

Nemotron 3.5 Lightning adalah model teks NVIDIA untuk tugas agen panjang, pemrograman, pencarian dokumen, dan percakapan.

Masukan yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · masukan & metode

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

Masukan

`text`

Keluaran

`text`

Konteks

262.144 tokens

Keluaran maksimum

32.768 tokens

Format keluaran

json atau SSE

| Kolom | Jenis | Persyaratan | Nilai & batasan | Bawaan |
| --- | --- | --- | --- | --- |
| Kolom`model` | Jenis`string` | PersyaratanWajib | Nilai & batasan nvidia/nemotron-3.5-lightning-30b-a3b | Bawaan— |
| Kolom`messages` | Jenis`message[]` | PersyaratanWajib | Nilai & batasan Item minimum: 1 | Bawaan— |
| Kolom`messages[].role` | Jenis`string` | PersyaratanWajib | Nilai & batasan user, assistant | Bawaan— |
| Kolom`messages[].content` | Jenis`string\|content_block[]` | PersyaratanWajib | Nilai & batasan | Bawaan— |
| Kolom`system` | Jenis`string\|content_block[]` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`max_tokens` | Jenis`integer` | PersyaratanWajib | Nilai & batasan Minimum: 1 Batas berlaku untuk: batas maksimum yang tepat untuk model/kartu yang dipilih | Bawaan— |
| Kolom`stream` | Jenis`boolean` | PersyaratanOpsional | Nilai & batasan | Bawaanfalse |
| Kolom`temperature` | Jenis`number` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`top_p` | Jenis`number` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`stop_sequences` | Jenis`string[]` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`tools` | Jenis`tool[]` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`tools[].name` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Berlaku jika: alat disediakan | Bawaan— |
| Kolom`tools[].description` | Jenis`string` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`tools[].input_schema` | Jenis`JSON_schema` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`tool_choice` | Jenis`object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`thinking.type` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`thinking.budget_tokens` | Jenis`integer` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`output_config.effort` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`metadata` | Jenis`object` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`cache_control` | Jenis`object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |

Kombinasi bahan masukan

**Teks** · Teks UTF8

`messages[].content atau blok type=text`

Parameter metode dan siklus hidup

| Parameter | Kontrak |
| --- | --- |
| Parameter`material_types` | Kontraktext |
| Parameter`required` | Kontrakmodel, messages, max\_tokens |
| Parameter`optional_controls` | Kontraknull |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`text_file_material` | Kontrakkonten UTF-8 aktual dimasukkan sebagai teks; ID file atau alamat URL (URLs) memerlukan dukungan yang tepat dan terpisah |

Siklus hidup: `exact retained published method`

Struktur metode dan ID bersifat eksak; kemampuan pemasok terpisah dari penerimaan permintaan.

### Paket

#### Tarif metode Ailoot

Masukan

US$0,00008 */ 1K*

Keluaran

US$0,0002 */ 1K*

Pembacaan cache

US$0,00008 */ 1K*

Penulisan cache

US$0,00008 */ 1K*

Penulisan cache, 5 menit

US$0,00008 */ 1K tokens*

Ailoot mencadangkan perkiraan dana sebelum permintaan. Setelah hasil diterima, tagihan akhir diselesaikan berdasarkan penggunaan yang terukur. Penyelesaian tagihan streaming menggunakan catatan penggunaan akhir. [Cara kerja cadangan dan penyelesaian tagihan →](https://ailoot.ai/docs/id/billing/reserve/)

### Contoh permintaan

#### Ailoot · Anthropic Messages

Contoh teksPython SDKNode.js SDKAliran Python

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "nvidia/nemotron-3.5-lightning-30b-a3b", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
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/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
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="nvidia/nemotron-3.5-lightning-30b-a3b",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis 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(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "nvidia/nemotron-3.5-lightning-30b-a3b",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,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=anthropic.Anthropic(base_url="https://api.ailoot.ai",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.messages.stream(model='nvidia/nemotron-3.5-lightning-30b-a3b',max_tokens=1024,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_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Terima dan simpan hasil

#### Ailoot · Anthropic Messages

json atau SSE

##### Simpan semua hasil yang selesai

Simpan setiap respons lengkap, berkas, dan bagian konten yang dikembalikan.

Simpan semua blok konten, tanda tangan penalaran, dan ID penggunaan alat yang sebenarnya. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan keluaran.

##### Jika respons asli perlu diperiksa

Simpan ID permintaan/respons dan header. URL umum untuk pengambilan tugas teks tidak disediakan.

Kolom respons

| Kolom | Jenis |
| --- | --- |
| Kolom`id` | Jenisstring |
| Kolom`model` | Jenisstring |
| Kolom`content[]` | Jenistext\|thinking\|tool\_use\|other content block |
| Kolom`stop_reason` | Jenisstring\|null |
| Kolom`usage` | Jenisobject |

Kesalahan dan langkah berikutnya

| Respons | Kondisi | Langkah berikutnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | KondisiBidang wajib, representasi materi, atau nilai parameter tidak valid | Langkah berikutnyaPerbaiki bidang yang ditunjukkan sebelum permintaan pembuatan baru. |

### Alias

#### Alias model

**Ailoot** [`nvidia/nemotron-3.5-lightning-30b-a3b`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&fmt=messages), [`nemotron-lightning`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning), [`nemotron-lightning-latest`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning-latest)

#### Alias jalur metode

Gunakan jalur metode yang ditampilkan di atas.

#### ID pemanggil terkait

[`nvidia/nemotron-3.5-lightning-30b-a3b`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&fmt=messages), [`nemotron-lightning`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning), [`nemotron-lightning-latest`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning-latest)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nvidia/nemotron-3.5-lightning-30b-a3b`

[`nvidia/nemotron-3.5-lightning-30b-a3b`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&fmt=chat)

NVIDIA /`nvidia/nemotron-3.5-lightning-30b-a3b`

ID model

- `nvidia/nemotron-3.5-lightning-30b-a3b`
- `nemotron-lightning`
- `nemotron-lightning-latest`

### Mulai

Nemotron 3.5 Lightning adalah model teks NVIDIA untuk tugas agen panjang, pemrograman, pencarian dokumen, dan percakapan.

Masukan yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · masukan & metode

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

Masukan

`text`

Keluaran

`text`

Konteks

4.096 tokens

Keluaran maksimum

1.024 tokens

Format keluaran

json atau SSE

| Kolom | Jenis | Persyaratan | Nilai & batasan | Bawaan |
| --- | --- | --- | --- | --- |
| Kolom`model` | Jenis`string` | PersyaratanWajib | Nilai & batasan nvidia/nemotron-3.5-lightning-30b-a3b | Bawaan— |
| Kolom`messages` | Jenis`message[]` | PersyaratanWajib | Nilai & batasan Item minimum: 1 | Bawaan— |
| Kolom`messages[].role` | Jenis`string` | PersyaratanWajib | Nilai & batasan Contoh: system, user, assistant, tool, function Kondisi: Peran ini direpresentasikan secara eksplisit oleh tipe kompatibilitas dalam kode sumber; kumpulan peran model yang tepat tetap khusus untuk tiap model. Bergantung pada model | Bawaan— |
| Kolom`messages[].content` | Jenis`string\|content_part[]\|null` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`messages[].tool_calls` | Jenis`tool_call[]` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`messages[].tool_call_id` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Berlaku jika: role=tool; gunakan ID yang benar-benar dikembalikan | Bawaan— |
| Kolom`messages[].name` | Jenis`string` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`messages[].reasoning_content` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Berlaku jika: Kirim kembali penalaran yang benar-benar dikembalikan jika model ini menggunakannya | Bawaan— |
| Kolom`messages[].reasoning_details` | Jenis`object\|array` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`max_tokens` | Jenis`integer` | PersyaratanOpsional | Nilai & batasan Minimum: 1 Bergantung pada model | Bawaan— |
| Kolom`max_completion_tokens` | Jenis`integer` | PersyaratanOpsional | Nilai & batasan Minimum: 1 Bergantung pada model | Bawaan— |
| Kolom`stream` | Jenis`boolean` | PersyaratanOpsional | Nilai & batasan | Bawaanfalse |
| Kolom`stream_options.include_usage` | Jenis`boolean` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`temperature` | Jenis`number` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`top_p` | Jenis`number` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`stop` | Jenis`string\|string[]` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`tools` | Jenis`function_tool[]` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`tools[].type` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`tools[].function.name` | Jenis`string` | PersyaratanWajib | Nilai & batasan Berlaku jika: alat fungsi disediakan | Bawaan— |
| Kolom`tools[].function.description` | Jenis`string` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`tools[].function.parameters` | Jenis`JSON_schema` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`tool_choice` | Jenis`string\|object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`parallel_tool_calls` | Jenis`boolean` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`response_format` | Jenis`object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`reasoning_effort` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`reasoning` | Jenis`object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`service_tier` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`instructions` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Kolom kompatibilitas | Bawaan— |
| Kolom`functions` | Jenis`function[]` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`function_call` | Jenis`string\|object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`prompt_cache_options` | Jenis`object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |

Kombinasi bahan masukan

**Teks** · Teks UTF8

`messages[].content`

Parameter metode dan siklus hidup

| Parameter | Kontrak |
| --- | --- |
| Parameter`material_types` | Kontraktext |
| Parameter`required` | Kontrakmodel, messages |
| Parameter`optional_controls` | Kontraknull |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`text_file_material` | Kontrakkonten UTF-8 aktual dimasukkan sebagai teks; ID file atau alamat URL (URLs) memerlukan dukungan yang tepat dan terpisah |

Siklus hidup: `exact retained published method`

Struktur metode dan ID bersifat eksak; kemampuan pemasok terpisah dari penerimaan permintaan.

### Paket

#### Tarif metode Ailoot

Masukan

US$0,00008 */ 1K*

Keluaran

US$0,0002 */ 1K*

Pembacaan cache

US$0,00008 */ 1K*

Penulisan cache

US$0,00008 */ 1K*

Penulisan cache, 5 menit

US$0,00008 */ 1K tokens*

Ailoot mencadangkan perkiraan dana sebelum permintaan. Setelah hasil diterima, tagihan akhir diselesaikan berdasarkan penggunaan yang terukur. Penyelesaian tagihan streaming menggunakan catatan penggunaan akhir. [Cara kerja cadangan dan penyelesaian tagihan →](https://ailoot.ai/docs/id/billing/reserve/)

### Contoh permintaan

#### Ailoot · OpenAI Chat

Contoh teksPython SDKNode.js SDKAliran Python

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "nvidia/nemotron-3.5-lightning-30b-a3b", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
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
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
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)
resp = client.chat.completions.create(
    model="nvidia/nemotron-3.5-lightning-30b-a3b",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis 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(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "nvidia/nemotron-3.5-lightning-30b-a3b",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```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='nvidia/nemotron-3.5-lightning-30b-a3b',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")
```

### Terima dan simpan hasil

#### Ailoot · OpenAI Chat

json atau SSE

##### Simpan semua hasil yang selesai

Simpan setiap respons lengkap, berkas, dan bagian konten yang dikembalikan.

Simpan setiap alternatif jawaban beserta konten, panggilan alat, dan penalarannya. Dalam SSE, gabungkan delta menurut indeks alternatif jawaban/alat, lalu pertahankan alasan penghentian akhir dan data penggunaan.

##### Jika respons asli perlu diperiksa

Simpan ID permintaan/respons dan header. URL umum untuk pengambilan tugas teks tidak disediakan.

Kolom respons

| Kolom | Jenis |
| --- | --- |
| Kolom`choices[].index` | Jenisinteger |
| Kolom`choices[].message.content` | Jenisstring\|null |
| Kolom`choices[].message.tool_calls` | Jenistool\_call\[\] |
| Kolom`choices[].message.reasoning_content` | Jenisstring |
| Kolom`choices[].message.reasoning_details` | Jenisobject\|array |
| Kolom`choices[].finish_reason` | Jenisstring\|null |
| Kolom`usage` | Jenisobject |

Kesalahan dan langkah berikutnya

| Respons | Kondisi | Langkah berikutnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | KondisiBidang wajib, representasi materi, atau nilai parameter tidak valid | Langkah berikutnyaPerbaiki bidang yang ditunjukkan sebelum permintaan pembuatan baru. |

### Alias

#### Alias model

**Ailoot** [`nvidia/nemotron-3.5-lightning-30b-a3b`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&fmt=chat), [`nemotron-lightning`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning&fmt=chat), [`nemotron-lightning-latest`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning-latest&fmt=chat)

#### Alias jalur metode

Gunakan jalur metode yang ditampilkan di atas.

#### ID pemanggil terkait

[`nvidia/nemotron-3.5-lightning-30b-a3b`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&fmt=chat), [`nemotron-lightning`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning&fmt=chat), [`nemotron-lightning-latest`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning-latest&fmt=chat)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nemotron-lightning`

[`nemotron-lightning`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning&fmt=chat)

NVIDIA /`nemotron-lightning`

ID model

- `nvidia/nemotron-3.5-lightning-30b-a3b`
- `nemotron-lightning`
- `nemotron-lightning-latest`

### Mulai

Nemotron 3.5 Lightning adalah model teks NVIDIA untuk tugas agen panjang, pemrograman, pencarian dokumen, dan percakapan.

Masukan yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · masukan & metode

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

Masukan

`text`

Keluaran

`text`

Konteks

4.096 tokens

Keluaran maksimum

1.024 tokens

Format keluaran

json atau SSE

| Kolom | Jenis | Persyaratan | Nilai & batasan | Bawaan |
| --- | --- | --- | --- | --- |
| Kolom`model` | Jenis`string` | PersyaratanWajib | Nilai & batasan nemotron-lightning | Bawaan— |
| Kolom`messages` | Jenis`message[]` | PersyaratanWajib | Nilai & batasan Item minimum: 1 | Bawaan— |
| Kolom`messages[].role` | Jenis`string` | PersyaratanWajib | Nilai & batasan Contoh: system, user, assistant, tool, function Kondisi: Peran ini direpresentasikan secara eksplisit oleh tipe kompatibilitas dalam kode sumber; kumpulan peran model yang tepat tetap khusus untuk tiap model. Bergantung pada model | Bawaan— |
| Kolom`messages[].content` | Jenis`string\|content_part[]\|null` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`messages[].tool_calls` | Jenis`tool_call[]` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`messages[].tool_call_id` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Berlaku jika: role=tool; gunakan ID yang benar-benar dikembalikan | Bawaan— |
| Kolom`messages[].name` | Jenis`string` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`messages[].reasoning_content` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Berlaku jika: Kirim kembali penalaran yang benar-benar dikembalikan jika model ini menggunakannya | Bawaan— |
| Kolom`messages[].reasoning_details` | Jenis`object\|array` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`max_tokens` | Jenis`integer` | PersyaratanOpsional | Nilai & batasan Minimum: 1 Bergantung pada model | Bawaan— |
| Kolom`max_completion_tokens` | Jenis`integer` | PersyaratanOpsional | Nilai & batasan Minimum: 1 Bergantung pada model | Bawaan— |
| Kolom`stream` | Jenis`boolean` | PersyaratanOpsional | Nilai & batasan | Bawaanfalse |
| Kolom`stream_options.include_usage` | Jenis`boolean` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`temperature` | Jenis`number` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`top_p` | Jenis`number` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`stop` | Jenis`string\|string[]` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`tools` | Jenis`function_tool[]` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`tools[].type` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`tools[].function.name` | Jenis`string` | PersyaratanWajib | Nilai & batasan Berlaku jika: alat fungsi disediakan | Bawaan— |
| Kolom`tools[].function.description` | Jenis`string` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`tools[].function.parameters` | Jenis`JSON_schema` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`tool_choice` | Jenis`string\|object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`parallel_tool_calls` | Jenis`boolean` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`response_format` | Jenis`object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`reasoning_effort` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`reasoning` | Jenis`object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`service_tier` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`instructions` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Kolom kompatibilitas | Bawaan— |
| Kolom`functions` | Jenis`function[]` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`function_call` | Jenis`string\|object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`prompt_cache_options` | Jenis`object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |

Kombinasi bahan masukan

**Teks** · Teks UTF8

`messages[].content`

Parameter metode dan siklus hidup

| Parameter | Kontrak |
| --- | --- |
| Parameter`material_types` | Kontraktext |
| Parameter`required` | Kontrakmodel, messages |
| Parameter`optional_controls` | Kontraknull |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`text_file_material` | Kontrakkonten UTF-8 aktual dimasukkan sebagai teks; ID file atau alamat URL (URLs) memerlukan dukungan yang tepat dan terpisah |

Siklus hidup: `exact retained published method`

Struktur metode dan ID bersifat eksak; kemampuan pemasok terpisah dari penerimaan permintaan.

### Paket

#### Tarif metode Ailoot

Masukan

US$0,00008 */ 1K*

Keluaran

US$0,0002 */ 1K*

Pembacaan cache

US$0,00008 */ 1K*

Penulisan cache

US$0,00008 */ 1K*

Penulisan cache, 5 menit

US$0,00008 */ 1K tokens*

Ailoot mencadangkan perkiraan dana sebelum permintaan. Setelah hasil diterima, tagihan akhir diselesaikan berdasarkan penggunaan yang terukur. Penyelesaian tagihan streaming menggunakan catatan penggunaan akhir. [Cara kerja cadangan dan penyelesaian tagihan →](https://ailoot.ai/docs/id/billing/reserve/)

### Contoh permintaan

#### Ailoot · OpenAI Chat

Contoh teksPython SDKNode.js SDKAliran Python

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "nemotron-lightning", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
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
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
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)
resp = client.chat.completions.create(
    model="nemotron-lightning",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis 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(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "nemotron-lightning",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```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='nemotron-lightning',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")
```

### Terima dan simpan hasil

#### Ailoot · OpenAI Chat

json atau SSE

##### Simpan semua hasil yang selesai

Simpan setiap respons lengkap, berkas, dan bagian konten yang dikembalikan.

Simpan setiap alternatif jawaban beserta konten, panggilan alat, dan penalarannya. Dalam SSE, gabungkan delta menurut indeks alternatif jawaban/alat, lalu pertahankan alasan penghentian akhir dan data penggunaan.

##### Jika respons asli perlu diperiksa

Simpan ID permintaan/respons dan header. URL umum untuk pengambilan tugas teks tidak disediakan.

Kolom respons

| Kolom | Jenis |
| --- | --- |
| Kolom`choices[].index` | Jenisinteger |
| Kolom`choices[].message.content` | Jenisstring\|null |
| Kolom`choices[].message.tool_calls` | Jenistool\_call\[\] |
| Kolom`choices[].message.reasoning_content` | Jenisstring |
| Kolom`choices[].message.reasoning_details` | Jenisobject\|array |
| Kolom`choices[].finish_reason` | Jenisstring\|null |
| Kolom`usage` | Jenisobject |

Kesalahan dan langkah berikutnya

| Respons | Kondisi | Langkah berikutnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | KondisiBidang wajib, representasi materi, atau nilai parameter tidak valid | Langkah berikutnyaPerbaiki bidang yang ditunjukkan sebelum permintaan pembuatan baru. |

### Alias

#### Alias model

**Ailoot** [`nvidia/nemotron-3.5-lightning-30b-a3b`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&fmt=chat), [`nemotron-lightning`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning&fmt=chat), [`nemotron-lightning-latest`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning-latest&fmt=chat)

#### Alias jalur metode

Gunakan jalur metode yang ditampilkan di atas.

#### ID pemanggil terkait

[`nvidia/nemotron-3.5-lightning-30b-a3b`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&fmt=chat), [`nemotron-lightning`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning&fmt=chat), [`nemotron-lightning-latest`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning-latest&fmt=chat)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nemotron-lightning-latest`

[`nemotron-lightning-latest`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning-latest&fmt=chat)

NVIDIA /`nemotron-lightning-latest`

ID model

- `nvidia/nemotron-3.5-lightning-30b-a3b`
- `nemotron-lightning`
- `nemotron-lightning-latest`

### Mulai

Nemotron 3.5 Lightning adalah model teks NVIDIA untuk tugas agen panjang, pemrograman, pencarian dokumen, dan percakapan.

Masukan yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · masukan & metode

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

Masukan

`text`

Keluaran

`text`

Konteks

4.096 tokens

Keluaran maksimum

1.024 tokens

Format keluaran

json atau SSE

| Kolom | Jenis | Persyaratan | Nilai & batasan | Bawaan |
| --- | --- | --- | --- | --- |
| Kolom`model` | Jenis`string` | PersyaratanWajib | Nilai & batasan nemotron-lightning-latest | Bawaan— |
| Kolom`messages` | Jenis`message[]` | PersyaratanWajib | Nilai & batasan Item minimum: 1 | Bawaan— |
| Kolom`messages[].role` | Jenis`string` | PersyaratanWajib | Nilai & batasan Contoh: system, user, assistant, tool, function Kondisi: Peran ini direpresentasikan secara eksplisit oleh tipe kompatibilitas dalam kode sumber; kumpulan peran model yang tepat tetap khusus untuk tiap model. Bergantung pada model | Bawaan— |
| Kolom`messages[].content` | Jenis`string\|content_part[]\|null` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`messages[].tool_calls` | Jenis`tool_call[]` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`messages[].tool_call_id` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Berlaku jika: role=tool; gunakan ID yang benar-benar dikembalikan | Bawaan— |
| Kolom`messages[].name` | Jenis`string` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`messages[].reasoning_content` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Berlaku jika: Kirim kembali penalaran yang benar-benar dikembalikan jika model ini menggunakannya | Bawaan— |
| Kolom`messages[].reasoning_details` | Jenis`object\|array` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`max_tokens` | Jenis`integer` | PersyaratanOpsional | Nilai & batasan Minimum: 1 Bergantung pada model | Bawaan— |
| Kolom`max_completion_tokens` | Jenis`integer` | PersyaratanOpsional | Nilai & batasan Minimum: 1 Bergantung pada model | Bawaan— |
| Kolom`stream` | Jenis`boolean` | PersyaratanOpsional | Nilai & batasan | Bawaanfalse |
| Kolom`stream_options.include_usage` | Jenis`boolean` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`temperature` | Jenis`number` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`top_p` | Jenis`number` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`stop` | Jenis`string\|string[]` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`tools` | Jenis`function_tool[]` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`tools[].type` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`tools[].function.name` | Jenis`string` | PersyaratanWajib | Nilai & batasan Berlaku jika: alat fungsi disediakan | Bawaan— |
| Kolom`tools[].function.description` | Jenis`string` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`tools[].function.parameters` | Jenis`JSON_schema` | PersyaratanOpsional | Nilai & batasan | Bawaan— |
| Kolom`tool_choice` | Jenis`string\|object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`parallel_tool_calls` | Jenis`boolean` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`response_format` | Jenis`object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`reasoning_effort` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`reasoning` | Jenis`object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`service_tier` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`instructions` | Jenis`string` | PersyaratanOpsional | Nilai & batasan Kolom kompatibilitas | Bawaan— |
| Kolom`functions` | Jenis`function[]` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`function_call` | Jenis`string\|object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |
| Kolom`prompt_cache_options` | Jenis`object` | PersyaratanOpsional | Nilai & batasan Bergantung pada model | Bawaan— |

Kombinasi bahan masukan

**Teks** · Teks UTF8

`messages[].content`

Parameter metode dan siklus hidup

| Parameter | Kontrak |
| --- | --- |
| Parameter`material_types` | Kontraktext |
| Parameter`required` | Kontrakmodel, messages |
| Parameter`optional_controls` | Kontraknull |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`text_file_material` | Kontrakkonten UTF-8 aktual dimasukkan sebagai teks; ID file atau alamat URL (URLs) memerlukan dukungan yang tepat dan terpisah |

Siklus hidup: `exact retained published method`

Struktur metode dan ID bersifat eksak; kemampuan pemasok terpisah dari penerimaan permintaan.

### Paket

#### Tarif metode Ailoot

Masukan

US$0,00008 */ 1K*

Keluaran

US$0,0002 */ 1K*

Pembacaan cache

US$0,00008 */ 1K*

Penulisan cache

US$0,00008 */ 1K*

Penulisan cache, 5 menit

US$0,00008 */ 1K tokens*

Ailoot mencadangkan perkiraan dana sebelum permintaan. Setelah hasil diterima, tagihan akhir diselesaikan berdasarkan penggunaan yang terukur. Penyelesaian tagihan streaming menggunakan catatan penggunaan akhir. [Cara kerja cadangan dan penyelesaian tagihan →](https://ailoot.ai/docs/id/billing/reserve/)

### Contoh permintaan

#### Ailoot · OpenAI Chat

Contoh teksPython SDKNode.js SDKAliran Python

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "nemotron-lightning-latest", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
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
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
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)
resp = client.chat.completions.create(
    model="nemotron-lightning-latest",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis 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(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "nemotron-lightning-latest",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```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='nemotron-lightning-latest',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")
```

### Terima dan simpan hasil

#### Ailoot · OpenAI Chat

json atau SSE

##### Simpan semua hasil yang selesai

Simpan setiap respons lengkap, berkas, dan bagian konten yang dikembalikan.

Simpan setiap alternatif jawaban beserta konten, panggilan alat, dan penalarannya. Dalam SSE, gabungkan delta menurut indeks alternatif jawaban/alat, lalu pertahankan alasan penghentian akhir dan data penggunaan.

##### Jika respons asli perlu diperiksa

Simpan ID permintaan/respons dan header. URL umum untuk pengambilan tugas teks tidak disediakan.

Kolom respons

| Kolom | Jenis |
| --- | --- |
| Kolom`choices[].index` | Jenisinteger |
| Kolom`choices[].message.content` | Jenisstring\|null |
| Kolom`choices[].message.tool_calls` | Jenistool\_call\[\] |
| Kolom`choices[].message.reasoning_content` | Jenisstring |
| Kolom`choices[].message.reasoning_details` | Jenisobject\|array |
| Kolom`choices[].finish_reason` | Jenisstring\|null |
| Kolom`usage` | Jenisobject |

Kesalahan dan langkah berikutnya

| Respons | Kondisi | Langkah berikutnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | KondisiBidang wajib, representasi materi, atau nilai parameter tidak valid | Langkah berikutnyaPerbaiki bidang yang ditunjukkan sebelum permintaan pembuatan baru. |

### Alias

#### Alias model

**Ailoot** [`nvidia/nemotron-3.5-lightning-30b-a3b`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&fmt=chat), [`nemotron-lightning`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning&fmt=chat), [`nemotron-lightning-latest`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning-latest&fmt=chat)

#### Alias jalur metode

Gunakan jalur metode yang ditampilkan di atas.

#### ID pemanggil terkait

[`nvidia/nemotron-3.5-lightning-30b-a3b`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nvidia%2Fnemotron-3.5-lightning-30b-a3b&fmt=chat), [`nemotron-lightning`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning&fmt=chat), [`nemotron-lightning-latest`](https://ailoot.ai/models/id/#m=nvidia%2Fnemotron-3.5-lightning-30b-a3b&route=Core&caller=nemotron-lightning-latest&fmt=chat)

FAQ · nvidia/nemotron-3.5-lightning-30b-a3b

Input dan hasil apa yang tersedia?

`POST /v1/messages` · `nvidia/nemotron-3.5-lightning-30b-a3b`: `text` → `text` `POST /v1/chat/completions` · `nvidia/nemotron-3.5-lightning-30b-a3b`: `text` → `text` `POST /v1/chat/completions` · `nemotron-lightning`: `text` → `text` `POST /v1/chat/completions` · `nemotron-lightning-latest`: `text` → `text`

Kolom apa yang digunakan permintaan?

`POST /v1/messages` · `nvidia/nemotron-3.5-lightning-30b-a3b`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/chat/completions` · `nvidia/nemotron-3.5-lightning-30b-a3b`: `model`, `messages`, `stream` `POST /v1/chat/completions` · `nemotron-lightning`: `model`, `messages`, `stream` `POST /v1/chat/completions` · `nemotron-lightning-latest`: `model`, `messages`, `stream`

Batasan apa yang berlaku?

`POST /v1/messages` · `nvidia/nemotron-3.5-lightning-30b-a3b`: `ctx`: `262144`; `max_out`: `32768`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/chat/completions` · `nvidia/nemotron-3.5-lightning-30b-a3b`: `ctx`: `4096`; `max_out`: `1024`; `messages.min_items`: `1` `POST /v1/chat/completions` · `nemotron-lightning`: `ctx`: `4096`; `max_out`: `1024`; `messages.min_items`: `1` `POST /v1/chat/completions` · `nemotron-lightning-latest`: `ctx`: `4096`; `max_out`: `1024`; `messages.min_items`: `1`

Hubungkan Ailoot ke Claude Code, OpenCode, Hermes, atau aplikasi Anda.

## Perusahaan dan portofolio proyeknya

Perusahaan dan portofolio proyeknya: jutaan pelanggan; penjualan miliaran setiap bulan.

## Beli token dengan diskon.

Diskon langganan untuk pekerjaan rutin. Kode promo — hingga 50% untuk pembelian token.

Langganan

Pilih paket dengan diskon untuk permintaan rutin Anda.

Kode promo hingga 50%

Masukkan kode saat membeli. Harga dihitung ulang sesuai promosi aktif.

Biaya dalam riwayat

Model, token, dan jumlah tagihan disimpan untuk setiap permintaan.

[Pilih langganan](https://ailoot.ai/docs/id/billing/subscriptions/) · [Lihat harga model](https://ailoot.ai/models/id/)

## Hubungkan API ke produk yang Anda jual.

SaaS, aplikasi, dan bot — sesuai penawaran dan perjanjian lisensi Ailoot. Untuk penjualan kembali, mintalah lisensi reseller.

Aplikasi komersial

Integrasikan pembuatan teks, gambar, video, dan suara dalam fitur berbayar layanan Anda.

Lisensi reseller

Kirim deskripsi proyek dan skema akses. Mintalah ketentuan penggunaan dan penjualan kembali secara tertulis.

Dokumen di situs

Penawaran, perjanjian lisensi, dan kebijakan pemrosesan data tersedia sebelum koneksi.

[Minta lisensi reseller](mailto:support@ailoot.ai) · [Penawaran dan perjanjian lisensi](https://ailoot.ai/legal/offer?lang=id)

## Ailoot · Perusahaan dan portofolio proyeknya





Ailoot bertumpu pada pengalaman operasional yang teruji, basis pelanggan yang besar, layanan yang stabil, dan pemantauan KPI berkelanjutan.





Perusahaan dan portofolio proyeknya: jutaan pelanggan; penjualan miliaran setiap bulan.





Ailoot memanfaatkan pengalaman operasional ini untuk akses API ke fitur AI dalam produk pelanggan, agen, aplikasi, dan otomatisasi.