Source: https://ailoot.ai/models/ms/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning/ Canonical: https://ailoot.ai/models/ms/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning/ Language: ms # Nemotron 3 Nano Omni 30B A3B Reasoning [Markdown](https://ailoot.ai/models/ms/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning/index.md) · [JSON](https://ailoot.ai/models/ms/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning/facts.json) ## [Nemotron 3 Nano Omni 30B A3B Reasoning](https://ailoot.ai/models/ms/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning/) Nemotron 3 Nano Omni menggabungkan pemahaman teks, imej, video dan pertuturan untuk analisis dokumen, rakaman mesyuarat dan tugasan multimodal. - [**Ailoot · Anthropic Messages** `POST /v1/messages` `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning/#method-0) - [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning/#method-1) - [**Ailoot · Anthropic Messages** `POST /v1/messages` `nemotron-3-nano-omni`](https://ailoot.ai/models/ms/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning/#method-2) - [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nemotron-3-nano-omni`](https://ailoot.ai/models/ms/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning/#method-3) - [**Ailoot · Anthropic Messages** `POST /v1/messages` `nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning/#method-4) - [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/nvidia-nemotron-3-nano-omni-30b-a3b-reasoning/#method-5) Tentang model Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih. #### Pemahaman pelbagai jenis bahan Nemotron 3 Nano Omni dibangunkan oleh NVIDIA untuk soal jawab, ringkasan, transkripsi pertuturan dan analisis dokumen. Pada peringkat model, teks, imej, video dan audio digabungkan. Hasilnya berupa teks: model menerangkan kandungan, menjawab soalan dan menghasilkan transkripsi. Analisis rakaman mesyuarat, pencarian dan penerangan peristiwa dalam video serta analisis dokumen perniagaan dan saintifik disediakan. Pemahaman antara muka dan pengecaman teks dalam imej membolehkan model digunakan dalam tugasan ejen dengan persekitaran kerja visual. #### Asas bahasa dan pengekod Asasnya ialah model hibrid Mamba-2 dan Transformer dengan lapisan pakar: kira-kira 31 bilion parameter keseluruhan dan kira-kira 3 bilion parameter aktif bagi setiap token. Pengekod visual berasingan memproses imej dan bingkai, manakala pengekod pertuturan memproses isyarat audio. Konteks keseluruhan mencapai 256 ribu token. Sokongan bahasa yang dinyatakan ialah bahasa Inggeris. #### Format input Kad pengeluar menyenaraikan rentetan teks, imej RGB PNG dan JPEG, video MP4 serta audio WAV atau MP3. Untuk video, klip sehingga dua minit diterangkan; kadar pensampelan bingkai bergantung pada resolusi. Bagi 1080p, pilihan sehingga satu bingkai sesaat dan 128 bingkai dinyatakan, manakala bagi 720p, sehingga dua bingkai sesaat dan 256 bingkai. Bagi audio, tempoh sehingga satu jam dan kadar pensampelan dari 8 kHz dinyatakan. Halaman dokumen boleh diberikan sebagai imej untuk analisis: ini berbeza daripada penghantaran PDF mentah. Data yang disokong oleh permintaan khusus ditentukan oleh kaedah input yang dipilih. #### Penaakulan dan hasil teks Mod penaakulan dan mod pelaksanaan arahan langsung disediakan. Bagi dokumen panjang dan analisis multimodal rumit, pengeluar menggunakan penaakulan dengan bajet terkawal. Mod langsung disyorkan untuk pengecaman pertuturan. Model menyokong teks dalam format JSON, panggilan alat dan transkripsi dengan cap masa perkataan individu. Panjang penjanaan yang disyorkan merujuk kepada tetapan tugasan; panjang ini tidak menetapkan had maksimum token output sejagat. Tugas praktikal ### Tugas praktikal Contoh teknikal dalam bahasa Inggeris ``` Summarize an English meeting transcript Summarize this transcript for the project owner. Erin: “The test build passed, but the release checklist is incomplete.” Sam: “I will finish the checklist tomorrow; deployment still needs approval.” Return the completed fact, the promised action with owner and the remaining approval. Preserve the distinction between a test build and deployment. ``` #### Hasil yang dijangka ``` A three-part meeting note: completed work, owner action and unresolved approval. ``` #### Semak hasil ``` Check that a passed test build is not rewritten as a deployed release and that Sam’s promise remains future work. ``` **Ailoot · Anthropic Messages** `POST /v1/messages` `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=messages) NVIDIA /`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` ID model - `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` - `nemotron-3-nano-omni` - `nemotron-3-nano-omni-latest` ### Pengenalan Nemotron 3 Nano Omni menggabungkan pemahaman teks, imej, video dan pertuturan untuk analisis dokumen, rakaman mesyuarat dan tugasan multimodal. 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-nano-omni-30b-a3b-reasoning | 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 0.0003 */ 1K* Output USD 0.0011 */ 1K* Bacaan cache USD 0.0003 */ 1K* Penulisan cache USD 0.0003 */ 1K* Penulisan cache, 5 minit USD 0.0003 */ 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/) ### 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-nano-omni-30b-a3b-reasoning", "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-nano-omni-30b-a3b-reasoning", 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-nano-omni-30b-a3b-reasoning", 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-nano-omni-30b-a3b-reasoning',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 **Ailoot** [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=messages), [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=messages), [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=messages) #### Alias laluan kaedah Gunakan laluan kaedah yang dipaparkan di atas. #### ID pemanggil berkaitan [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=messages), [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=messages), [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=messages) **Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=chat) NVIDIA /`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` ID model - `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` - `nemotron-3-nano-omni` - `nemotron-3-nano-omni-latest` ### Pengenalan Nemotron 3 Nano Omni menggabungkan pemahaman teks, imej, video dan pertuturan untuk analisis dokumen, rakaman mesyuarat dan tugasan multimodal. 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-nano-omni-30b-a3b-reasoning | 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 0.0003 */ 1K* Output USD 0.0011 */ 1K* Bacaan cache USD 0.0003 */ 1K* Penulisan cache USD 0.0003 */ 1K* Penulisan cache, 5 minit USD 0.0003 */ 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/) ### 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-nano-omni-30b-a3b-reasoning", "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-nano-omni-30b-a3b-reasoning", 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-nano-omni-30b-a3b-reasoning", 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-nano-omni-30b-a3b-reasoning',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 **Ailoot** [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=chat), [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=chat), [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=chat) #### Alias laluan kaedah Gunakan laluan kaedah yang dipaparkan di atas. #### ID pemanggil berkaitan [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=chat), [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=chat), [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=chat) **Ailoot · Anthropic Messages** `POST /v1/messages` `nemotron-3-nano-omni` [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=messages) NVIDIA /`nemotron-3-nano-omni` ID model - `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` - `nemotron-3-nano-omni` - `nemotron-3-nano-omni-latest` ### Pengenalan Nemotron 3 Nano Omni menggabungkan pemahaman teks, imej, video dan pertuturan untuk analisis dokumen, rakaman mesyuarat dan tugasan multimodal. 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-nano-omni | 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 0.0003 */ 1K* Output USD 0.0011 */ 1K* Bacaan cache USD 0.0003 */ 1K* Penulisan cache USD 0.0003 */ 1K* Penulisan cache, 5 minit USD 0.0003 */ 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/) ### 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-nano-omni", "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-nano-omni", 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-nano-omni", 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-nano-omni',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 **Ailoot** [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=messages), [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=messages), [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=messages) #### Alias laluan kaedah Gunakan laluan kaedah yang dipaparkan di atas. #### ID pemanggil berkaitan [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=messages), [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=messages), [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=messages) **Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nemotron-3-nano-omni` [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=chat) NVIDIA /`nemotron-3-nano-omni` ID model - `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` - `nemotron-3-nano-omni` - `nemotron-3-nano-omni-latest` ### Pengenalan Nemotron 3 Nano Omni menggabungkan pemahaman teks, imej, video dan pertuturan untuk analisis dokumen, rakaman mesyuarat dan tugasan multimodal. 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-nano-omni | 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 0.0003 */ 1K* Output USD 0.0011 */ 1K* Bacaan cache USD 0.0003 */ 1K* Penulisan cache USD 0.0003 */ 1K* Penulisan cache, 5 minit USD 0.0003 */ 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/) ### 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-nano-omni", "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-nano-omni", 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-nano-omni", 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-nano-omni',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 **Ailoot** [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=chat), [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=chat), [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=chat) #### Alias laluan kaedah Gunakan laluan kaedah yang dipaparkan di atas. #### ID pemanggil berkaitan [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=chat), [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=chat), [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=chat) **Ailoot · Anthropic Messages** `POST /v1/messages` `nemotron-3-nano-omni-latest` [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=messages) NVIDIA /`nemotron-3-nano-omni-latest` ID model - `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` - `nemotron-3-nano-omni` - `nemotron-3-nano-omni-latest` ### Pengenalan Nemotron 3 Nano Omni menggabungkan pemahaman teks, imej, video dan pertuturan untuk analisis dokumen, rakaman mesyuarat dan tugasan multimodal. 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-nano-omni-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 0.0003 */ 1K* Output USD 0.0011 */ 1K* Bacaan cache USD 0.0003 */ 1K* Penulisan cache USD 0.0003 */ 1K* Penulisan cache, 5 minit USD 0.0003 */ 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/) ### 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-nano-omni-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-nano-omni-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-nano-omni-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-nano-omni-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 **Ailoot** [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=messages), [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=messages), [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=messages) #### Alias laluan kaedah Gunakan laluan kaedah yang dipaparkan di atas. #### ID pemanggil berkaitan [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=messages), [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=messages), [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=messages) **Ailoot · OpenAI Chat** `POST /v1/chat/completions` `nemotron-3-nano-omni-latest` [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=chat) NVIDIA /`nemotron-3-nano-omni-latest` ID model - `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` - `nemotron-3-nano-omni` - `nemotron-3-nano-omni-latest` ### Pengenalan Nemotron 3 Nano Omni menggabungkan pemahaman teks, imej, video dan pertuturan untuk analisis dokumen, rakaman mesyuarat dan tugasan multimodal. 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-nano-omni-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 0.0003 */ 1K* Output USD 0.0011 */ 1K* Bacaan cache USD 0.0003 */ 1K* Penulisan cache USD 0.0003 */ 1K* Penulisan cache, 5 minit USD 0.0003 */ 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/) ### 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-nano-omni-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-nano-omni-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-nano-omni-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-nano-omni-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 **Ailoot** [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=chat), [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=chat), [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=chat) #### Alias laluan kaedah Gunakan laluan kaedah yang dipaparkan di atas. #### ID pemanggil berkaitan [`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&fmt=chat), [`nemotron-3-nano-omni`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni&fmt=chat), [`nemotron-3-nano-omni-latest`](https://ailoot.ai/models/ms/#m=nvidia%2Fnemotron-3-nano-omni-30b-a3b-reasoning&route=Core&caller=nemotron-3-nano-omni-latest&fmt=chat) FAQ · nvidia/nemotron-3-nano-omni-30b-a3b-reasoning Apakah input dan hasil yang tersedia? `POST /v1/messages` · `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`: `text` → `text` `POST /v1/chat/completions` · `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`: `text` → `text` `POST /v1/messages` · `nemotron-3-nano-omni`: `text` → `text` `POST /v1/chat/completions` · `nemotron-3-nano-omni`: `text` → `text` `POST /v1/messages` · `nemotron-3-nano-omni-latest`: `text` → `text` `POST /v1/chat/completions` · `nemotron-3-nano-omni-latest`: `text` → `text` Apakah medan yang digunakan oleh permintaan? `POST /v1/messages` · `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/chat/completions` · `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`: `model`, `messages`, `stream` `POST /v1/messages` · `nemotron-3-nano-omni`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/chat/completions` · `nemotron-3-nano-omni`: `model`, `messages`, `stream` `POST /v1/messages` · `nemotron-3-nano-omni-latest`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/chat/completions` · `nemotron-3-nano-omni-latest`: `model`, `messages`, `stream` Apakah had yang terpakai? `POST /v1/messages` · `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`: `ctx`: `262144`; `max_out`: `32768`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/chat/completions` · `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`: `ctx`: `4096`; `max_out`: `1024`; `messages.min_items`: `1` `POST /v1/messages` · `nemotron-3-nano-omni`: `ctx`: `262144`; `max_out`: `32768`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/chat/completions` · `nemotron-3-nano-omni`: `ctx`: `4096`; `max_out`: `1024`; `messages.min_items`: `1` `POST /v1/messages` · `nemotron-3-nano-omni-latest`: `ctx`: `262144`; `max_out`: `32768`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/chat/completions` · `nemotron-3-nano-omni-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.