Source: https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/
Canonical: https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/
Language: ms

# NVIDIA: Nemotron 3 Super

[Markdown](https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/index.md) · [JSON](https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/facts.json)

## [NVIDIA: Nemotron 3 Super](https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/)

Nemotron 3 Super ialah model teks NVIDIA untuk aplikasi ejen kompleks, dengan 12B parameter aktif daripada 120B keseluruhan. Reka bentuk campuran pakar hibrid Mamba–Transformernya menyokong penaakulan, alat fungsi dan kawalan output berstruktur.

- [**Ailoot · Anthropic Messages** `POST /v1/messages` `nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/#method-0)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/#method-1)
- [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/#method-2)
- [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/#method-3)
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `nemotron-3-super`](https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/#method-4)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nemotron-3-super`](https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/#method-5)
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `nemotron-3-super-latest`](https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/#method-6)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nemotron-3-super-latest`](https://ailoot.ai/models/ms/nvidia-nemotron-3-super-120b-a12b/#method-7)

Tentang model

Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.

Nemotron 3 Super ialah model campuran pakar hibrid terbuka NVIDIA untuk aplikasi ejen kompleks. Model ini mempunyai 120 bilion parameter keseluruhan dan mengaktifkan 12 bilion parameter. Seni bina menggabungkan komponen Mamba dan Transformer. Input teks menghasilkan output teks, dengan penaakulan, alat fungsi dan kawalan output berstruktur dalam profil pengehosan yang diterbitkan.

#### Selaraskan tugas berdasarkan buktinya

Kenal pasti hasil yang diperlukan dan maklumat yang menentukan setiap langkah. Tugas pengekodan boleh memberikan kod sumber yang terjejas, tingkah laku yang diperhatikan dan syarat penerimaan. Perbandingan boleh membekalkan alternatif dan kriteria, dengan sumber yang dinamakan untuk fakta yang dinilai. Pastikan objektif kekal kelihatan apabila pemerhatian perantaraan ditambah.

Untuk kerja yang melibatkan beberapa operasi berkaitan, rekodkan tindakan yang menghasilkan setiap pemerhatian supaya kaitannya kekal jelas. Aplikasi melaksanakan operasi alat yang dicadangkan dan mengembalikan hasil sebenarnya kepada model. Hasil itu boleh menyokong keputusan seterusnya atau menunjukkan soalan berikutnya yang perlu diselesaikan.

#### Penaakulan dan artifak berstruktur

Nyatakan kedalaman dan hasil kerja akhir yang diperlukan oleh masalah. Jawapan ringkas masih boleh memerlukan analisis besar terhadap kes yang sukar. Untuk pemprosesan perisian, tetapkan medan dan jenis yang dijangka, kemudian sahkan struktur serta kandungan yang dikembalikan terhadap sumbernya.

Simpan pengecam sumber, andaian dan hasil alat yang berkaitan bersama laporan atau rekod perancangan. Untuk kod, kekalkan perubahan yang dicadangkan atau diterapkan serta semakan yang menilai tingkah laku yang dimaksudkan. Ini menjadikan output berguna di luar perbualan yang menghasilkannya.

#### Konteks untuk kerja berterusan

Profil katalog dihoskan menyenaraikan tetingkap konteks 262,144 token. Rancang mengikut peruntukan kerja sebenar antara muka penyajian, dengan ruang untuk jawapan. Kekalkan keputusan dan bukti yang diperlukan untuk tugas semasa sambil membuang pengulangan yang tidak berkaitan.

Hasil Super yang berguna meninggalkan artifak yang boleh disemak dan keadaan yang diperlukan untuk langkah seterusnya. Model membekalkan teks dan permintaan alat; aplikasi sekeliling membekalkan operasi serta pemerhatian sebenar yang melengkapkan aliran kerja yang lebih besar.

Tugas praktikal

### Tugas praktikal

Contoh teknikal dalam bahasa Inggeris

```
Assemble an evidence-based incident handoff

Prepare an incident handoff from three observations. Monitor M: checkout error rate rose at 10:05. Deployment D: release 6.4 finished at 10:00. Database B: connection pool was exhausted at 10:06. Separate the timeline, plausible investigation leads and facts still needed. Keep observation labels beside claims and do not assert that deployment caused the errors.
```

#### Hasil yang dijangka

```
A labelled timeline, bounded investigation leads and a short list of evidence needed to distinguish causes.
```

#### Semak hasil

```
Temporal proximity is not presented as established causality, and all times and labels remain intact.
```

**Ailoot · Anthropic Messages** `POST /v1/messages` `nvidia/nemotron-3-super-120b-a12b`

[`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages)

NVIDIA /`nvidia/nemotron-3-super-120b-a12b`

ID model

- `nvidia/nemotron-3-super-120b-a12b`
- `nemotron-3-super`
- `nemotron-3-super-latest`

### Pengenalan

Nemotron 3 Super ialah model teks NVIDIA untuk aplikasi ejen kompleks, dengan 12B parameter aktif daripada 120B keseluruhan. Reka bentuk campuran pakar hibrid Mamba–Transformernya menyokong penaakulan, alat fungsi dan kawalan output berstruktur.

Input yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · input & kaedah

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

Input

`text`

Output

`text`

Konteks

262,144 tokens

Output maksimum

32,768 tokens

Format output

json atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had nvidia/nemotron-3-super-120b-a12b | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
| Medan`messages[].content` | Jenis`string\|content_block[]` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`system` | Jenis`string\|content_block[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanDiperlukan | Nilai & had Minimum: 1 Had terpakai pada: had maksimum tepat bagi model/kad yang dipilih | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`stop_sequences` | Jenis`string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].name` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: alat dibekalkan | Lalai— |
| Medan`tools[].description` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tools[].input_schema` | Jenis`JSON_schema` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tool_choice` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`thinking.type` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`thinking.budget_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`output_config.effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`metadata` | Jenis`object` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`cache_control` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |

Gabungan bahan input

**Teks** · Teks UTF8

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

Parameter kaedah dan kitar hayat

| 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` | Kontrakkandungan UTF-8 sebenar dimasukkan sebagai teks; ID fail atau alamat URL (URLs) memerlukan sokongan tepat yang berasingan |

Kitar hayat: `exact retained published method`

Struktur kaedah dan ID adalah tepat; keupayaan pembekal berasingan daripada penerimaan permintaan.

### Pelan harga

#### Kadar kaedah Ailoot

Input

USD 0.00008 */ 1K*

Output

USD 0.00045 */ 1K*

Bacaan cache

USD 0.00008 */ 1K*

Penulisan cache

USD 0.00008 */ 1K*

Penulisan cache, 5 minit

USD 0.00008 */ 1K tokens*

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

#### Butiran tarif rujukan

Jadual rujukan peringkat model tidak mengubah pemilihan kaedah, sebut harga atau caj. Caj aktif menggunakan kadar kaedah Ailoot yang dipilih.

Jadual rujukan model

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiOpenAI Chat · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiOpenAI Chat · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

### Contoh permintaan

#### Ailoot · Anthropic Messages

Contoh teksPython SDKNode.js SDKPenstriman 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-super-120b-a12b", "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-super-120b-a12b",
    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-super-120b-a12b",
  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-super-120b-a12b',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, fail dan bahagian kandungan yang dikembalikan.

Kekalkan semua blok kandungan, tandatangan penaakulan dan ID penggunaan alat sebenar. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan output.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

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

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=messages), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=messages)
**Ailoot Ultra** [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages)

#### Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

#### ID pemanggil berkaitan

[`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages), [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=messages), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=messages)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nvidia/nemotron-3-super-120b-a12b`

[`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat)

NVIDIA /`nvidia/nemotron-3-super-120b-a12b`

ID model

- `nvidia/nemotron-3-super-120b-a12b`
- `nemotron-3-super`
- `nemotron-3-super-latest`

### Pengenalan

Nemotron 3 Super ialah model teks NVIDIA untuk aplikasi ejen kompleks, dengan 12B parameter aktif daripada 120B keseluruhan. Reka bentuk campuran pakar hibrid Mamba–Transformernya menyokong penaakulan, alat fungsi dan kawalan output berstruktur.

Input yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · input & kaedah

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

Input

`text`

Output

`text`

Konteks

4,096 tokens

Output maksimum

1,024 tokens

Format output

json atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had nvidia/nemotron-3-super-120b-a12b | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had Contoh: system, user, assistant, tool, function Syarat: Peranan ini diwakili secara eksplisit oleh jenis keserasian dalam kod sumber; set peranan model yang tepat kekal khusus untuk setiap model. Bergantung pada model | Lalai— |
| Medan`messages[].content` | Jenis`string\|content_part[]\|null` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_calls` | Jenis`tool_call[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_call_id` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: role=tool; gunakan ID sebenar yang dipulangkan | Lalai— |
| Medan`messages[].name` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].reasoning_content` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: Hantar semula penaakulan sebenar yang dipulangkan apabila model ini menggunakannya | Lalai— |
| Medan`messages[].reasoning_details` | Jenis`object\|array` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`max_completion_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`stream_options.include_usage` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`stop` | Jenis`string\|string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`function_tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].type` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].function.name` | Jenis`string` | KeperluanDiperlukan | Nilai & had Terpakai apabila: alat fungsi dibekalkan | Lalai— |
| Medan`tools[].function.description` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tools[].function.parameters` | Jenis`JSON_schema` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tool_choice` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`parallel_tool_calls` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`response_format` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning_effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`service_tier` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`instructions` | Jenis`string` | KeperluanPilihan | Nilai & had Medan keserasian | Lalai— |
| Medan`functions` | Jenis`function[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`function_call` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`prompt_cache_options` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |

Gabungan bahan input

**Teks** · Teks UTF8

`messages[].content`

Parameter kaedah dan kitar hayat

| Parameter | Kontrak |
| --- | --- |
| Parameter`material_types` | Kontraktext |
| Parameter`required` | Kontrakmodel, messages |
| Parameter`optional_controls` | Kontraknull |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`text_file_material` | Kontrakkandungan UTF-8 sebenar dimasukkan sebagai teks; ID fail atau alamat URL (URLs) memerlukan sokongan tepat yang berasingan |

Kitar hayat: `exact retained published method`

Struktur kaedah dan ID adalah tepat; keupayaan pembekal berasingan daripada penerimaan permintaan.

### Pelan harga

#### Kadar kaedah Ailoot

Input

USD 0.00008 */ 1K*

Output

USD 0.00045 */ 1K*

Bacaan cache

USD 0.00008 */ 1K*

Penulisan cache

USD 0.00008 */ 1K*

Penulisan cache, 5 minit

USD 0.00008 */ 1K tokens*

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

#### Butiran tarif rujukan

Jadual rujukan peringkat model tidak mengubah pemilihan kaedah, sebut harga atau caj. Caj aktif menggunakan kadar kaedah Ailoot yang dipilih.

Jadual rujukan model

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiOpenAI Chat · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiOpenAI Chat · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

### Contoh permintaan

#### Ailoot · OpenAI Chat

Contoh teksPython SDKNode.js SDKPenstriman 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-super-120b-a12b", "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-super-120b-a12b",
    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-super-120b-a12b",
  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-super-120b-a12b',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, fail dan bahagian kandungan yang dikembalikan.

Kekalkan setiap pilihan jawapan bersama kandungan, panggilan alat dan penaakulannya. Dalam SSE, gabungkan delta mengikut indeks pilihan jawapan/alat dan kekalkan sebab penamatan akhir serta data penggunaan.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

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

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=chat), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=chat)
**Ailoot Ultra** [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat)

#### Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

#### ID pemanggil berkaitan

[`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat), [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=chat), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=chat)

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `nvidia/nemotron-3-super-120b-a12b`

[`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat)

NVIDIA /`nvidia/nemotron-3-super-120b-a12b`

### Pengenalan

Nemotron 3 Super ialah model teks NVIDIA untuk aplikasi ejen kompleks, dengan 12B parameter aktif daripada 120B keseluruhan. Reka bentuk campuran pakar hibrid Mamba–Transformernya menyokong penaakulan, alat fungsi dan kawalan output berstruktur.

Input yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · input & kaedah

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

Input

`text`

Output

`text`

Format output

json atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had nvidia/nemotron-3-super-120b-a12b | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had Contoh: system, user, assistant, tool, function Syarat: Peranan ini diwakili secara eksplisit oleh jenis keserasian dalam kod sumber; set peranan model yang tepat kekal khusus untuk setiap model. Bergantung pada model | Lalai— |
| Medan`messages[].content` | Jenis`string\|content_part[]\|null` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_calls` | Jenis`tool_call[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_call_id` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: role=tool; gunakan ID sebenar yang dipulangkan | Lalai— |
| Medan`messages[].name` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].reasoning_content` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: Hantar semula penaakulan sebenar yang dipulangkan apabila model ini menggunakannya | Lalai— |
| Medan`messages[].reasoning_details` | Jenis`object\|array` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`max_completion_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`stream_options.include_usage` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`stop` | Jenis`string\|string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`function_tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].type` | Jenis`string` | KeperluanPilihan | Nilai & had function Bergantung pada model | Lalai— |
| Medan`tools[].function.name` | Jenis`string` | KeperluanDiperlukan | Nilai & had Terpakai apabila: alat fungsi dibekalkan | Lalai— |
| Medan`tools[].function.description` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tools[].function.parameters` | Jenis`JSON_schema` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tool_choice` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`parallel_tool_calls` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`response_format` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning_effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`service_tier` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`instructions` | Jenis`string` | KeperluanPilihan | Nilai & had Medan keserasian | Lalai— |
| Medan`functions` | Jenis`function[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`function_call` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`prompt_cache_options` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`modalities` | Jenis`string[]` | KeperluanPilihan | Nilai & had text | Lalai— |
| Medan`provider` | Jenis`object` | KeperluanPilihan | Nilai & had Syarat: provider.options ditolak pada laluan teks Ultra ini | Lalai— |
| Medan`cache_control.ttl` | Jenis`string` | KeperluanPilihan | Nilai & had Syarat: 1h ditolak pada lokasi cache prompt yang digunakan | Lalai— |

Gabungan bahan input

**Teks** · Teks UTF8

`messages[].content`

Parameter kaedah dan kitar hayat

| Parameter | Kontrak |
| --- | --- |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`required` | Kontrakmodel, messages |
| Parameter`material_types` | Kontraktext |
| Parameter`messages` | Kontraktatasusunan mesej dengan struktur role/content |
| Parameter`file_material` | Kontrakdokumen UTF-8 sebenar dimasukkan sebagai teks literal; ID fail tidak diandaikan |
| Parameter`optional_controls` | Kontrakstream, temperature, top\_p, stop, max\_tokens, max\_completion\_tokens, reasoning, response\_format, tools, tool\_choice |
| Parameter`control_scope` | Kontrakkhusus model; alat fungsi pengguna berbeza daripada alat yang dihoskan |
| Parameter`output_modalities` | Kontraktext |
| Parameter`hosted_operations` | Kontrakfalse |
| Parameter`multimodal_input_binding` | Kontraknull |

Kitar hayat: `synchronous_or_streamed`

Hantar ID model yang tepat bersama messages.

Panjang konteks bukan had output.

Fail teks boleh membekalkan teks literal; input imej/audio/objek fail memerlukan pengikatan tepat.

### Pelan harga

Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.

Mod pantas

Kadar standard Apabila mod pantas dipilih

Mod flex

Kadar standard Apabila mod flex dipilih

Usaha penaakulan maksimum

Kadar standard Apabila usaha penaakulan maksimum menggunakan pelarasan default

Usaha penaakulan · low

Kadar standard Apabila usaha penaakulan ditetapkan kepada low

Usaha penaakulan · medium

Kadar standard Apabila usaha penaakulan ditetapkan kepada medium

#### Kadar Ailoot

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiKadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiTahap panjang permintaan 1 | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

### Contoh permintaan

#### Ailoot Ultra · OpenAI Chat

curlPython SDKPenstriman Python

```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": "nvidia/nemotron-3-super-120b-a12b", "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='nvidia/nemotron-3-super-120b-a12b',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='nvidia/nemotron-3-super-120b-a12b',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 Ultra · OpenAI Chat

json atau SSE

##### Simpan semua hasil yang selesai

Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.

Kekalkan setiap pilihan jawapan bersama kandungan, panggilan alat dan penaakulannya. Dalam SSE, gabungkan delta mengikut indeks pilihan jawapan/alat dan kekalkan sebab penamatan akhir serta data penggunaan.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

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

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=chat), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=chat)
**Ailoot Ultra** [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat)

#### Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

#### ID pemanggil berkaitan

[`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat), [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=chat), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=chat)

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `nvidia/nemotron-3-super-120b-a12b`

[`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages)

NVIDIA /`nvidia/nemotron-3-super-120b-a12b`

### Pengenalan

Nemotron 3 Super ialah model teks NVIDIA untuk aplikasi ejen kompleks, dengan 12B parameter aktif daripada 120B keseluruhan. Reka bentuk campuran pakar hibrid Mamba–Transformernya menyokong penaakulan, alat fungsi dan kawalan output berstruktur.

Input yang diterima

Teks

Hasil

json · sse

### Tersedia di Ailoot · input & kaedah

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

Input

`text`

Output

`json`, `sse`

Format output

JSON atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had nvidia/nemotron-3-super-120b-a12b | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
| Medan`messages[].content` | Jenis`string` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |

Gabungan bahan input

**Teks** · Teks UTF-8

`rentetan messages[].content`

Parameter kaedah dan kitar hayat

| Parameter | Kontrak |
| --- | --- |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`required` | Kontrakmodel, messages, max\_tokens |
| Parameter`optional_controls` | Kontrakstream |
| Parameter`material_types` | Kontraktext |
| Parameter`text_file_material` | KontrakBaca dokumen UTF-8 sebenar dan letakkan teksnya dalam rentetan input atau kandungan mesej yang ditunjukkan. |

Kitar hayat: `synchronous_or_streamed`

### Pelan harga

Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.

Mod pantas

Kadar standard Apabila mod pantas dipilih

Mod flex

Kadar standard Apabila mod flex dipilih

Usaha penaakulan maksimum

Kadar standard Apabila usaha penaakulan maksimum menggunakan pelarasan default

Usaha penaakulan · low

Kadar standard Apabila usaha penaakulan ditetapkan kepada low

Usaha penaakulan · medium

Kadar standard Apabila usaha penaakulan ditetapkan kepada medium

#### Kadar Ailoot

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiKadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiTahap panjang permintaan 1 | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

### Contoh permintaan

#### Ailoot Ultra · Anthropic Messages

Badan JSON minimum yang lengkapcurl · gunakan dokumen UTF-8 andaPython · simpan hasil lengkap

```json
{
  "model": "nvidia/nemotron-3-super-120b-a12b",
  "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': 'nvidia/nemotron-3-super-120b-a12b', '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': 'nvidia/nemotron-3-super-120b-a12b', '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))
```

### Terima dan simpan hasil

#### Ailoot Ultra · Anthropic Messages

JSON atau SSE

##### Simpan semua hasil yang selesai

Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.

Kekalkan semua blok kandungan, tandatangan penaakulan dan ID penggunaan alat sebenar. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan output.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

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

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=messages), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=messages)
**Ailoot Ultra** [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages)

#### Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

#### ID pemanggil berkaitan

[`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages), [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=messages), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=messages)

**Ailoot · Anthropic Messages** `POST /v1/messages` `nemotron-3-super`

[`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=messages)

NVIDIA /`nemotron-3-super`

ID model

- `nvidia/nemotron-3-super-120b-a12b`
- `nemotron-3-super`
- `nemotron-3-super-latest`

### Pengenalan

Nemotron 3 Super ialah model teks NVIDIA untuk aplikasi ejen kompleks, dengan 12B parameter aktif daripada 120B keseluruhan. Reka bentuk campuran pakar hibrid Mamba–Transformernya menyokong penaakulan, alat fungsi dan kawalan output berstruktur.

Input yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · input & kaedah

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

Input

`text`

Output

`text`

Konteks

262,144 tokens

Output maksimum

32,768 tokens

Format output

json atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had nemotron-3-super | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
| Medan`messages[].content` | Jenis`string\|content_block[]` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`system` | Jenis`string\|content_block[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanDiperlukan | Nilai & had Minimum: 1 Had terpakai pada: had maksimum tepat bagi model/kad yang dipilih | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`stop_sequences` | Jenis`string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].name` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: alat dibekalkan | Lalai— |
| Medan`tools[].description` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tools[].input_schema` | Jenis`JSON_schema` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tool_choice` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`thinking.type` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`thinking.budget_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`output_config.effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`metadata` | Jenis`object` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`cache_control` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |

Gabungan bahan input

**Teks** · Teks UTF8

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

Parameter kaedah dan kitar hayat

| 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` | Kontrakkandungan UTF-8 sebenar dimasukkan sebagai teks; ID fail atau alamat URL (URLs) memerlukan sokongan tepat yang berasingan |

Kitar hayat: `exact retained published method`

Struktur kaedah dan ID adalah tepat; keupayaan pembekal berasingan daripada penerimaan permintaan.

### Pelan harga

#### Kadar kaedah Ailoot

Input

USD 0.00008 */ 1K*

Output

USD 0.00045 */ 1K*

Bacaan cache

USD 0.00008 */ 1K*

Penulisan cache

USD 0.00008 */ 1K*

Penulisan cache, 5 minit

USD 0.00008 */ 1K tokens*

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

#### Butiran tarif rujukan

Jadual rujukan peringkat model tidak mengubah pemilihan kaedah, sebut harga atau caj. Caj aktif menggunakan kadar kaedah Ailoot yang dipilih.

Jadual rujukan model

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiOpenAI Chat · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiOpenAI Chat · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

### Contoh permintaan

#### Ailoot · Anthropic Messages

Contoh teksPython SDKNode.js SDKPenstriman 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-3-super", "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="nemotron-3-super",
    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: "nemotron-3-super",
  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='nemotron-3-super',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, fail dan bahagian kandungan yang dikembalikan.

Kekalkan semua blok kandungan, tandatangan penaakulan dan ID penggunaan alat sebenar. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan output.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

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

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=messages), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=messages)
**Ailoot Ultra** [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages)

#### Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

#### ID pemanggil berkaitan

[`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages), [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=messages), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=messages)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nemotron-3-super`

[`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=chat)

NVIDIA /`nemotron-3-super`

ID model

- `nvidia/nemotron-3-super-120b-a12b`
- `nemotron-3-super`
- `nemotron-3-super-latest`

### Pengenalan

Nemotron 3 Super ialah model teks NVIDIA untuk aplikasi ejen kompleks, dengan 12B parameter aktif daripada 120B keseluruhan. Reka bentuk campuran pakar hibrid Mamba–Transformernya menyokong penaakulan, alat fungsi dan kawalan output berstruktur.

Input yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · input & kaedah

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

Input

`text`

Output

`text`

Konteks

4,096 tokens

Output maksimum

1,024 tokens

Format output

json atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had nemotron-3-super | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had Contoh: system, user, assistant, tool, function Syarat: Peranan ini diwakili secara eksplisit oleh jenis keserasian dalam kod sumber; set peranan model yang tepat kekal khusus untuk setiap model. Bergantung pada model | Lalai— |
| Medan`messages[].content` | Jenis`string\|content_part[]\|null` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_calls` | Jenis`tool_call[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_call_id` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: role=tool; gunakan ID sebenar yang dipulangkan | Lalai— |
| Medan`messages[].name` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].reasoning_content` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: Hantar semula penaakulan sebenar yang dipulangkan apabila model ini menggunakannya | Lalai— |
| Medan`messages[].reasoning_details` | Jenis`object\|array` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`max_completion_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`stream_options.include_usage` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`stop` | Jenis`string\|string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`function_tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].type` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].function.name` | Jenis`string` | KeperluanDiperlukan | Nilai & had Terpakai apabila: alat fungsi dibekalkan | Lalai— |
| Medan`tools[].function.description` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tools[].function.parameters` | Jenis`JSON_schema` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tool_choice` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`parallel_tool_calls` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`response_format` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning_effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`service_tier` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`instructions` | Jenis`string` | KeperluanPilihan | Nilai & had Medan keserasian | Lalai— |
| Medan`functions` | Jenis`function[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`function_call` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`prompt_cache_options` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |

Gabungan bahan input

**Teks** · Teks UTF8

`messages[].content`

Parameter kaedah dan kitar hayat

| Parameter | Kontrak |
| --- | --- |
| Parameter`material_types` | Kontraktext |
| Parameter`required` | Kontrakmodel, messages |
| Parameter`optional_controls` | Kontraknull |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`text_file_material` | Kontrakkandungan UTF-8 sebenar dimasukkan sebagai teks; ID fail atau alamat URL (URLs) memerlukan sokongan tepat yang berasingan |

Kitar hayat: `exact retained published method`

Struktur kaedah dan ID adalah tepat; keupayaan pembekal berasingan daripada penerimaan permintaan.

### Pelan harga

#### Kadar kaedah Ailoot

Input

USD 0.00008 */ 1K*

Output

USD 0.00045 */ 1K*

Bacaan cache

USD 0.00008 */ 1K*

Penulisan cache

USD 0.00008 */ 1K*

Penulisan cache, 5 minit

USD 0.00008 */ 1K tokens*

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

#### Butiran tarif rujukan

Jadual rujukan peringkat model tidak mengubah pemilihan kaedah, sebut harga atau caj. Caj aktif menggunakan kadar kaedah Ailoot yang dipilih.

Jadual rujukan model

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiOpenAI Chat · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiOpenAI Chat · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

### Contoh permintaan

#### Ailoot · OpenAI Chat

Contoh teksPython SDKNode.js SDKPenstriman 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-3-super", "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-3-super",
    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-3-super",
  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-3-super',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, fail dan bahagian kandungan yang dikembalikan.

Kekalkan setiap pilihan jawapan bersama kandungan, panggilan alat dan penaakulannya. Dalam SSE, gabungkan delta mengikut indeks pilihan jawapan/alat dan kekalkan sebab penamatan akhir serta data penggunaan.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

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

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=chat), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=chat)
**Ailoot Ultra** [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat)

#### Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

#### ID pemanggil berkaitan

[`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat), [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=chat), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=chat)

**Ailoot · Anthropic Messages** `POST /v1/messages` `nemotron-3-super-latest`

[`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=messages)

NVIDIA /`nemotron-3-super-latest`

ID model

- `nvidia/nemotron-3-super-120b-a12b`
- `nemotron-3-super`
- `nemotron-3-super-latest`

### Pengenalan

Nemotron 3 Super ialah model teks NVIDIA untuk aplikasi ejen kompleks, dengan 12B parameter aktif daripada 120B keseluruhan. Reka bentuk campuran pakar hibrid Mamba–Transformernya menyokong penaakulan, alat fungsi dan kawalan output berstruktur.

Input yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · input & kaedah

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

Input

`text`

Output

`text`

Konteks

262,144 tokens

Output maksimum

32,768 tokens

Format output

json atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had nemotron-3-super-latest | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
| Medan`messages[].content` | Jenis`string\|content_block[]` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`system` | Jenis`string\|content_block[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanDiperlukan | Nilai & had Minimum: 1 Had terpakai pada: had maksimum tepat bagi model/kad yang dipilih | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`stop_sequences` | Jenis`string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].name` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: alat dibekalkan | Lalai— |
| Medan`tools[].description` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tools[].input_schema` | Jenis`JSON_schema` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tool_choice` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`thinking.type` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`thinking.budget_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`output_config.effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`metadata` | Jenis`object` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`cache_control` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |

Gabungan bahan input

**Teks** · Teks UTF8

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

Parameter kaedah dan kitar hayat

| 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` | Kontrakkandungan UTF-8 sebenar dimasukkan sebagai teks; ID fail atau alamat URL (URLs) memerlukan sokongan tepat yang berasingan |

Kitar hayat: `exact retained published method`

Struktur kaedah dan ID adalah tepat; keupayaan pembekal berasingan daripada penerimaan permintaan.

### Pelan harga

#### Kadar kaedah Ailoot

Input

USD 0.00008 */ 1K*

Output

USD 0.00045 */ 1K*

Bacaan cache

USD 0.00008 */ 1K*

Penulisan cache

USD 0.00008 */ 1K*

Penulisan cache, 5 minit

USD 0.00008 */ 1K tokens*

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

#### Butiran tarif rujukan

Jadual rujukan peringkat model tidak mengubah pemilihan kaedah, sebut harga atau caj. Caj aktif menggunakan kadar kaedah Ailoot yang dipilih.

Jadual rujukan model

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiOpenAI Chat · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiOpenAI Chat · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

### Contoh permintaan

#### Ailoot · Anthropic Messages

Contoh teksPython SDKNode.js SDKPenstriman 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-3-super-latest", "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="nemotron-3-super-latest",
    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: "nemotron-3-super-latest",
  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='nemotron-3-super-latest',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, fail dan bahagian kandungan yang dikembalikan.

Kekalkan semua blok kandungan, tandatangan penaakulan dan ID penggunaan alat sebenar. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan output.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

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

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=messages), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=messages)
**Ailoot Ultra** [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages)

#### Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

#### ID pemanggil berkaitan

[`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages), [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=messages), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=messages), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=messages)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nemotron-3-super-latest`

[`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=chat)

NVIDIA /`nemotron-3-super-latest`

ID model

- `nvidia/nemotron-3-super-120b-a12b`
- `nemotron-3-super`
- `nemotron-3-super-latest`

### Pengenalan

Nemotron 3 Super ialah model teks NVIDIA untuk aplikasi ejen kompleks, dengan 12B parameter aktif daripada 120B keseluruhan. Reka bentuk campuran pakar hibrid Mamba–Transformernya menyokong penaakulan, alat fungsi dan kawalan output berstruktur.

Input yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · input & kaedah

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

Input

`text`

Output

`text`

Konteks

4,096 tokens

Output maksimum

1,024 tokens

Format output

json atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had nemotron-3-super-latest | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had Contoh: system, user, assistant, tool, function Syarat: Peranan ini diwakili secara eksplisit oleh jenis keserasian dalam kod sumber; set peranan model yang tepat kekal khusus untuk setiap model. Bergantung pada model | Lalai— |
| Medan`messages[].content` | Jenis`string\|content_part[]\|null` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_calls` | Jenis`tool_call[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_call_id` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: role=tool; gunakan ID sebenar yang dipulangkan | Lalai— |
| Medan`messages[].name` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].reasoning_content` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: Hantar semula penaakulan sebenar yang dipulangkan apabila model ini menggunakannya | Lalai— |
| Medan`messages[].reasoning_details` | Jenis`object\|array` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`max_completion_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`stream_options.include_usage` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`stop` | Jenis`string\|string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`function_tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].type` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].function.name` | Jenis`string` | KeperluanDiperlukan | Nilai & had Terpakai apabila: alat fungsi dibekalkan | Lalai— |
| Medan`tools[].function.description` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tools[].function.parameters` | Jenis`JSON_schema` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tool_choice` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`parallel_tool_calls` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`response_format` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning_effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`service_tier` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`instructions` | Jenis`string` | KeperluanPilihan | Nilai & had Medan keserasian | Lalai— |
| Medan`functions` | Jenis`function[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`function_call` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`prompt_cache_options` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |

Gabungan bahan input

**Teks** · Teks UTF8

`messages[].content`

Parameter kaedah dan kitar hayat

| Parameter | Kontrak |
| --- | --- |
| Parameter`material_types` | Kontraktext |
| Parameter`required` | Kontrakmodel, messages |
| Parameter`optional_controls` | Kontraknull |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`text_file_material` | Kontrakkandungan UTF-8 sebenar dimasukkan sebagai teks; ID fail atau alamat URL (URLs) memerlukan sokongan tepat yang berasingan |

Kitar hayat: `exact retained published method`

Struktur kaedah dan ID adalah tepat; keupayaan pembekal berasingan daripada penerimaan permintaan.

### Pelan harga

#### Kadar kaedah Ailoot

Input

USD 0.00008 */ 1K*

Output

USD 0.00045 */ 1K*

Bacaan cache

USD 0.00008 */ 1K*

Penulisan cache

USD 0.00008 */ 1K*

Penulisan cache, 5 minit

USD 0.00008 */ 1K tokens*

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

#### Butiran tarif rujukan

Jadual rujukan peringkat model tidak mengubah pemilihan kaedah, sebut harga atau caj. Caj aktif menggunakan kadar kaedah Ailoot yang dipilih.

Jadual rujukan model

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiOpenAI Chat · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiOpenAI Chat · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.00017** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **—** / 1K token Input · Penulisan cache **—** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

### Contoh permintaan

#### Ailoot · OpenAI Chat

Contoh teksPython SDKNode.js SDKPenstriman 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-3-super-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-3-super-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-3-super-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-3-super-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, fail dan bahagian kandungan yang dikembalikan.

Kekalkan setiap pilihan jawapan bersama kandungan, panggilan alat dan penaakulannya. Dalam SSE, gabungkan delta mengikut indeks pilihan jawapan/alat dan kekalkan sebab penamatan akhir serta data penggunaan.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

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

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=chat), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=chat)
**Ailoot Ultra** [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat)

#### Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

#### ID pemanggil berkaitan

[`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat), [`nvidia/nemotron-3-super-120b-a12b`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Ultra&caller=nvidia%2Fnemotron-3-super-120b-a12b&fmt=chat), [`nemotron-3-super`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super&fmt=chat), [`nemotron-3-super-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-super-120b-a12b&route=Core&caller=nemotron-3-super-latest&fmt=chat)

FAQ · nvidia/nemotron-3-super-120b-a12b

Apakah input dan hasil yang tersedia?

`POST /v1/messages` · `nvidia/nemotron-3-super-120b-a12b`: `text` → `text` `POST /v1/chat/completions` · `nvidia/nemotron-3-super-120b-a12b`: `text` → `text` `POST /v1/chat/completions` · `nvidia/nemotron-3-super-120b-a12b`: `text` → `text` `POST /v1/messages` · `nvidia/nemotron-3-super-120b-a12b`: `text` → `json`, `sse` `POST /v1/messages` · `nemotron-3-super`: `text` → `text` `POST /v1/chat/completions` · `nemotron-3-super`: `text` → `text` `POST /v1/messages` · `nemotron-3-super-latest`: `text` → `text` `POST /v1/chat/completions` · `nemotron-3-super-latest`: `text` → `text`

Apakah medan yang digunakan oleh permintaan?

`POST /v1/messages` · `nvidia/nemotron-3-super-120b-a12b`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/chat/completions` · `nvidia/nemotron-3-super-120b-a12b`: `model`, `messages`, `stream` `POST /v1/chat/completions` · `nvidia/nemotron-3-super-120b-a12b`: `model`, `messages`, `stream`, `modalities`, `provider` `POST /v1/messages` · `nvidia/nemotron-3-super-120b-a12b`: `model`, `messages`, `max_tokens`, `stream` `POST /v1/messages` · `nemotron-3-super`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/chat/completions` · `nemotron-3-super`: `model`, `messages`, `stream` `POST /v1/messages` · `nemotron-3-super-latest`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/chat/completions` · `nemotron-3-super-latest`: `model`, `messages`, `stream`

Apakah had yang terpakai?

`POST /v1/messages` · `nvidia/nemotron-3-super-120b-a12b`: `ctx`: `262144`; `max_out`: `32768`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/chat/completions` · `nvidia/nemotron-3-super-120b-a12b`: `ctx`: `4096`; `max_out`: `1024`; `messages.min_items`: `1` `POST /v1/chat/completions` · `nvidia/nemotron-3-super-120b-a12b`: `messages.min_items`: `1` `POST /v1/messages` · `nemotron-3-super`: `ctx`: `262144`; `max_out`: `32768`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/chat/completions` · `nemotron-3-super`: `ctx`: `4096`; `max_out`: `1024`; `messages.min_items`: `1` `POST /v1/messages` · `nemotron-3-super-latest`: `ctx`: `262144`; `max_out`: `32768`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/chat/completions` · `nemotron-3-super-latest`: `ctx`: `4096`; `max_out`: `1024`; `messages.min_items`: `1`

Sambungkan Ailoot kepada Claude Code, OpenCode, Hermes atau aplikasi anda.

## Syarikat dan portfolio projeknya

Syarikat dan portfolio projeknya: jutaan pelanggan; jualan bernilai berbilion setiap bulan.

## Beli token dengan diskaun.

Diskaun langganan untuk penggunaan berkala. Kod promosi — sehingga 50% bagi pembelian token.

Langganan

Pilih pelan berdiskaun untuk permintaan berkala anda.

Kod promosi sehingga 50%

Masukkan kod semasa pembelian. Harga dikira semula mengikut promosi semasa.

Perbelanjaan dalam sejarah

Model, token dan jumlah disimpan bagi setiap permintaan.

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

## Sambungkan API kepada produk yang anda jual.

SaaS, aplikasi dan bot — di bawah tawaran rasmi serta perjanjian lesen Ailoot. Untuk jualan semula, mohon lesen penjual semula.

Aplikasi komersial

Tambahkan penjanaan teks, imej, video dan audio pada ciri berbayar perkhidmatan anda.

Lesen penjual semula

Hantar keterangan projek dan susunan akses. Minta terma penggunaan serta jualan semula secara bertulis.

Dokumen pada laman

Tawaran, perjanjian lesen dan dasar pemprosesan data tersedia sebelum sambungan.

[Mohon lesen penjual semula](mailto:support@ailoot.ai) · [Tawaran dan perjanjian lesen](https://ailoot.ai/legal/offer?lang=ms)

## Ailoot · Syarikat dan portfolio projeknya





Ailoot berteraskan pengalaman operasi yang mantap, pangkalan pelanggan yang besar, perkhidmatan yang stabil dan pemantauan KPI berterusan.





Syarikat dan portfolio projeknya: jutaan pelanggan; jualan bernilai berbilion setiap bulan.





Ailoot menggunakan pengalaman operasi ini untuk akses API kepada ciri AI dalam produk pelanggan, ejen, aplikasi dan automasi.