{ "aboutHtml": "

Nemotron 3.5 Content Safety ialah model kawalan keselamatan berparameter 4B NVIDIA, ditala halus daripada Gemma-3-4B. Peranan yang didokumenkan ialah moderasi prompt dan balasan, pengelasan kandungan dan aliran kerja dasar keselamatan. NVIDIA menerangkan output yang menilai prompt pengguna dan balasan sebagai selamat atau tidak selamat, menambah label kategori keselamatan dan secara pilihan menyertakan jejak penaakulan. Penilaian itu ialah output model untuk dinilai dan digunakan oleh aplikasi. Setiap mesej mempunyai role system, developer, user atau assistant dan content rentetan biasa. name pilihan ialah rentetan; hadkan setiap mesej kepada medan ini. Hantar stream:false, atau jangan sertakan stream.

Gunakan ID model tepat nvidia/nemotron-3.5-content-safety:free dengan POST /v1/chat/completions dan tatasusunan messages yang tidak kosong. Letakkan bahan untuk dinilai dalam content teks dan bezakan prompt pengguna daripada balasan model apabila kedua-duanya disemak. Langkah moderasi praktikal boleh melabelkan kedua-dua petikan itu secara jelas dan meminta model mengenal pasti kategori yang berkaitan sambil memastikan penilaiannya terikat pada kandungan yang dibekalkan.

Edisi Ailoot ini menerima teks dan mengembalikan teks. Untuk baris gilir semakan, sediakan hantaran sebenar, draf mesej sokongan atau jawapan terjana yang memerlukan penilaian, bersama konteks sekeliling yang mengubah maknanya. Kekalkan keputusan aplikasi seperti menghalakan item bertanda untuk semakan manusia dalam aliran kerja anda sendiri. Input media, kawalan panggilan alat dan kawalan cache eksplisit berada di luar profil permintaan edisi ini.

Halaman model menyenaraikan tetingkap konteks 128,000 token dan sehingga 8,192 token pelengkapan. Ailoot turut memerlukan seluruh badan permintaan JSON UTF-8, termasuk arahan dan nama medan, muat dalam 128,000 bait. Untuk had output yang jelas, tetapkan tepat satu daripada max_tokens atau max_completion_tokens kepada integer positif dari 1 hingga 8,192. Jika kedua-duanya tidak dibekalkan, Ailoot meneruskan had output 4,096 token. Ambil kira keseluruhan perbualan dan penilaian yang anda minta. Penerangan model melaporkan liputan 12 bahasa; kekalkan kata-kata asal apabila penilaian bergantung pada bahasa sumber. Jika aplikasi anda menjangkakan label tertentu, huraikan dan sahkan teks yang dikembalikan berdasarkan peraturan pengendalian yang anda pilih. Jawapan yang diminta supaya kelihatan seperti JSON tidak menjamin output dengan skema yang dikuatkuasakan.

Gunakan stream:false untuk balasan perbualan JSON lengkap. Baca choices[].message.content, simpan setiap pilihan yang dikembalikan dan sebarang medan penaakulan yang dibekalkan, serta kekalkan finish_reason dan usage. Simpan penilaian bersama prompt dan balasan tepat yang dinilainya supaya keputusan boleh disemak kemudian. Penilaian satu teks terpakai pada teks dan konteks yang dibekalkan itu; nilai balasan yang berubah secara ketara sebagai itemnya sendiri.

Sediakan bahan yang tidak mengandungi maklumat sulit, sebagaimana diwajibkan oleh terma penggunaan yang didokumenkan bagi edisi percuma ini. Jika permintaan berakhir tanpa penilaian lengkap, simpan pengecam permintaan asal dan data yang dikembalikan semasa menyemak percubaan sedia ada. Kad ini mendokumenkan hasil perbualan langsung dan tidak membekalkan aliran kerja tugasan tak segerak atau pembatalan berasingan.

", "aboutText": "Nemotron 3.5 Content Safety ialah model kawalan keselamatan berparameter 4B NVIDIA, ditala halus daripada Gemma-3-4B. Peranan yang didokumenkan ialah moderasi prompt dan balasan, pengelasan kandungan dan aliran kerja dasar keselamatan. NVIDIA menerangkan output yang menilai prompt pengguna dan balasan sebagai selamat atau tidak selamat, menambah label kategori keselamatan dan secara pilihan menyertakan jejak penaakulan. Penilaian itu ialah output model untuk dinilai dan digunakan oleh aplikasi. Setiap mesej mempunyai role system, developer, user atau assistant dan content rentetan biasa. name pilihan ialah rentetan; hadkan setiap mesej kepada medan ini. Hantar stream:false, atau jangan sertakan stream.\n\nGunakan ID model tepat nvidia/nemotron-3.5-content-safety:free dengan POST /v1/chat/completions dan tatasusunan messages yang tidak kosong. Letakkan bahan untuk dinilai dalam content teks dan bezakan prompt pengguna daripada balasan model apabila kedua-duanya disemak. Langkah moderasi praktikal boleh melabelkan kedua-dua petikan itu secara jelas dan meminta model mengenal pasti kategori yang berkaitan sambil memastikan penilaiannya terikat pada kandungan yang dibekalkan.\n\nEdisi Ailoot ini menerima teks dan mengembalikan teks. Untuk baris gilir semakan, sediakan hantaran sebenar, draf mesej sokongan atau jawapan terjana yang memerlukan penilaian, bersama konteks sekeliling yang mengubah maknanya. Kekalkan keputusan aplikasi seperti menghalakan item bertanda untuk semakan manusia dalam aliran kerja anda sendiri. Input media, kawalan panggilan alat dan kawalan cache eksplisit berada di luar profil permintaan edisi ini.\n\nHalaman model menyenaraikan tetingkap konteks 128,000 token dan sehingga 8,192 token pelengkapan. Ailoot turut memerlukan seluruh badan permintaan JSON UTF-8, termasuk arahan dan nama medan, muat dalam 128,000 bait. Untuk had output yang jelas, tetapkan tepat satu daripada max_tokens atau max_completion_tokens kepada integer positif dari 1 hingga 8,192. Jika kedua-duanya tidak dibekalkan, Ailoot meneruskan had output 4,096 token. Ambil kira keseluruhan perbualan dan penilaian yang anda minta. Penerangan model melaporkan liputan 12 bahasa; kekalkan kata-kata asal apabila penilaian bergantung pada bahasa sumber. Jika aplikasi anda menjangkakan label tertentu, huraikan dan sahkan teks yang dikembalikan berdasarkan peraturan pengendalian yang anda pilih. Jawapan yang diminta supaya kelihatan seperti JSON tidak menjamin output dengan skema yang dikuatkuasakan.\n\nGunakan stream:false untuk balasan perbualan JSON lengkap. Baca choices[].message.content, simpan setiap pilihan yang dikembalikan dan sebarang medan penaakulan yang dibekalkan, serta kekalkan finish_reason dan usage. Simpan penilaian bersama prompt dan balasan tepat yang dinilainya supaya keputusan boleh disemak kemudian. Penilaian satu teks terpakai pada teks dan konteks yang dibekalkan itu; nilai balasan yang berubah secara ketara sebagai itemnya sendiri.\n\nSediakan bahan yang tidak mengandungi maklumat sulit, sebagaimana diwajibkan oleh terma penggunaan yang didokumenkan bagi edisi percuma ini. Jika permintaan berakhir tanpa penilaian lengkap, simpan pengecam permintaan asal dan data yang dikembalikan semasa menyemak percubaan sedia ada. Kad ini mendokumenkan hasil perbualan langsung dan tidak membekalkan aliran kerja tugasan tak segerak atau pembatalan berasingan.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "db4d732e11bf666f10e7d6f4cb59d559ba979c32572f9b84c8dcfbb1c9dab343", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "ms", "methods": [ { "html": "
NV

NVIDIA: Nemotron 3.5 Content Safety (free)

NVIDIA /nvidia/nemotron-3.5-content-safety:free

Pengenalan

Nemotron 3.5 Content Safety ialah model kawalan keselamatan 4B NVIDIA untuk mengelaskan prompt dan balasan model. Edisi Ailoot ini membaca teks dan mengembalikan teks, termasuk penilaian keselamatan dan label kategori oleh model. Gunakannya sebagai langkah moderasi terfokus dalam semakan yang lebih besar atau aliran kerja dasar aplikasi.

Input yang diterima
Teks
Hasil
Teks
Tentang model

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

Nemotron 3.5 Content Safety ialah model kawalan keselamatan berparameter 4B NVIDIA, ditala halus daripada Gemma-3-4B. Peranan yang didokumenkan ialah moderasi prompt dan balasan, pengelasan kandungan dan aliran kerja dasar keselamatan. NVIDIA menerangkan output yang menilai prompt pengguna dan balasan sebagai selamat atau tidak selamat, menambah label kategori keselamatan dan secara pilihan menyertakan jejak penaakulan. Penilaian itu ialah output model untuk dinilai dan digunakan oleh aplikasi. Setiap mesej mempunyai role system, developer, user atau assistant dan content rentetan biasa. name pilihan ialah rentetan; hadkan setiap mesej kepada medan ini. Hantar stream:false, atau jangan sertakan stream.

Gunakan ID model tepat nvidia/nemotron-3.5-content-safety:free dengan POST /v1/chat/completions dan tatasusunan messages yang tidak kosong. Letakkan bahan untuk dinilai dalam content teks dan bezakan prompt pengguna daripada balasan model apabila kedua-duanya disemak. Langkah moderasi praktikal boleh melabelkan kedua-dua petikan itu secara jelas dan meminta model mengenal pasti kategori yang berkaitan sambil memastikan penilaiannya terikat pada kandungan yang dibekalkan.

Edisi Ailoot ini menerima teks dan mengembalikan teks. Untuk baris gilir semakan, sediakan hantaran sebenar, draf mesej sokongan atau jawapan terjana yang memerlukan penilaian, bersama konteks sekeliling yang mengubah maknanya. Kekalkan keputusan aplikasi seperti menghalakan item bertanda untuk semakan manusia dalam aliran kerja anda sendiri. Input media, kawalan panggilan alat dan kawalan cache eksplisit berada di luar profil permintaan edisi ini.

Halaman model menyenaraikan tetingkap konteks 128,000 token dan sehingga 8,192 token pelengkapan. Ailoot turut memerlukan seluruh badan permintaan JSON UTF-8, termasuk arahan dan nama medan, muat dalam 128,000 bait. Untuk had output yang jelas, tetapkan tepat satu daripada max_tokens atau max_completion_tokens kepada integer positif dari 1 hingga 8,192. Jika kedua-duanya tidak dibekalkan, Ailoot meneruskan had output 4,096 token. Ambil kira keseluruhan perbualan dan penilaian yang anda minta. Penerangan model melaporkan liputan 12 bahasa; kekalkan kata-kata asal apabila penilaian bergantung pada bahasa sumber. Jika aplikasi anda menjangkakan label tertentu, huraikan dan sahkan teks yang dikembalikan berdasarkan peraturan pengendalian yang anda pilih. Jawapan yang diminta supaya kelihatan seperti JSON tidak menjamin output dengan skema yang dikuatkuasakan.

Gunakan stream:false untuk balasan perbualan JSON lengkap. Baca choices[].message.content, simpan setiap pilihan yang dikembalikan dan sebarang medan penaakulan yang dibekalkan, serta kekalkan finish_reason dan usage. Simpan penilaian bersama prompt dan balasan tepat yang dinilainya supaya keputusan boleh disemak kemudian. Penilaian satu teks terpakai pada teks dan konteks yang dibekalkan itu; nilai balasan yang berubah secara ketara sebagai itemnya sendiri.

Sediakan bahan yang tidak mengandungi maklumat sulit, sebagaimana diwajibkan oleh terma penggunaan yang didokumenkan bagi edisi percuma ini. Jika permintaan berakhir tanpa penilaian lengkap, simpan pengecam permintaan asal dan data yang dikembalikan semasa menyemak percubaan sedia ada. Kad ini mendokumenkan hasil perbualan langsung dan tidak membekalkan aliran kerja tugasan tak segerak atau pembatalan berasingan.

Tersedia di Ailoot · input & kaedah

Ailoot Ultra · Chat Completions POST /v1/chat/completions
Input
text
Output
text
Konteks
128,000 tokens
Output maksimum
8,192 tokens
Format output
JSON or supported SSE
MedanJenisKeperluanNilai & hadLalai
MedanmodelJenisstringKeperluanDiperlukanNilai & had
nvidia/nemotron-3.5-content-safety:free
Lalai—
MedanmessagesJenisarrayKeperluanDiperlukanNilai & hadLalai—
MedanstreamJenisbooleanKeperluanPilihanNilai & had
false
Lalaifalse
Medanmax_tokensJenisintegerKeperluanPilihanNilai & had
Minimum: 1
Maksimum: 8,192
Lalai—
Medanmax_completion_tokensJenisintegerKeperluanPilihanNilai & had
Minimum: 1
Maksimum: 8,192
Lalai—
MedannJenisintegerKeperluanPilihanNilai & had
Minimum: 1
Maksimum: 128
Lalai—
MedantemperatureJenisnumberKeperluanPilihanNilai & hadLalai—
Medantop_pJenisnumberKeperluanPilihanNilai & hadLalai—
MedanseedJenisintegerKeperluanPilihanNilai & hadLalai—
MedanstopJenisKeperluanPilihanNilai & hadLalai—
Medanfrequency_penaltyJenisnumberKeperluanPilihanNilai & hadLalai—
Medanpresence_penaltyJenisnumberKeperluanPilihanNilai & hadLalai—
MedanuserJenisstringKeperluanPilihanNilai & hadLalai—
Parameter kaedah dan kitar hayat
ParameterKontrak
Parametercontent_typeKontrakapplication/json
ParameterrequiredKontrakmodel, messages
ParameteroptionalKontrakstream, max_tokens, max_completion_tokens, n, temperature, top_p, seed, stop, frequency_penalty, presence_penalty, user
Parametermaterial_typesKontraktext
ParameterconditionsKontrakUse literal text messages only. Cache controls, tools, image/audio/video content and streamed responses are unavailable for this method., The complete encoded JSON request must not exceed 128000 bytes.

Kitar hayat: synchronous_json_or_sse

Pelan harga

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

Mod pantas
Kadar standard Apabila mod pantas dipilih
Mod flex
Kadar standard Apabila mod flex dipilih
Usaha penaakulan maksimum
Kadar standard Apabila usaha penaakulan maksimum menggunakan pelarasan default
Harga cache eksplisit
Tidak diaktifkan Apabila cache eksplisit diminta
Kadar sifar untuk teks sahaja
Data cache, alat dan media tertakluk pada syarat harga masing-masing yang disenaraikan secara berasingan. Untuk input dan output teks sahaja

Kadar Ailoot

Harga mengikut konfigurasi

KonfigurasiJadual kadarCaj
KonfigurasiKadar asas tokenJadual kadarKadar asasCaj
Input · Token input $0 / 1K token
Output · Token output $0 / 1K token
Input · Bacaan cache — / 1K token
Input · Penulisan cache — / 1K token
Input · Penulisan cache, 1 jam — / 1K token

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. Cara rizab dan penyelesaian caj berfungsi →

Contoh permintaan

Ailoot Ultra · Chat Completions

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "nvidia/nemotron-3.5-content-safety:free", "messages": [{"role": "user", "content": "Summarize the supplied text in three concise points."}], "stream": false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n

Terima dan simpan hasil

Ailoot Ultra · Chat Completions

JSON or supported SSE

Simpan semua hasil yang selesai

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

Retain the complete response, all actual results, original identifiers, usage and response headers.

Jika respons asal perlu disemak

Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.

Alias

Alias model

Ailoot Ultra nvidia/nemotron-3.5-content-safety:free

Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

ID pemanggil berkaitan

nvidia/nemotron-3.5-content-safety:free

", "method_identity": { "effective_request_model_id": "nvidia/nemotron-3.5-content-safety:free", "fmt": "chat", "http": "POST", "path": "/v1/chat/completions", "request_model_id": "nvidia/nemotron-3.5-content-safety:free", "route_label": "Ultra" }, "method_key": "Ultra|chat|/v1/chat/completions|nvidia%2Fnemotron-3.5-content-safety%3Afree", "ordinal": 0, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "example_body": { "messages": [ { "content": "Summarize the supplied text in three concise points.", "role": "user" } ], "model": "nvidia/nemotron-3.5-content-safety:free", "stream": false }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_json_or_sse", "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "outputs": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "family": "text", "format": "JSON or supported SSE" }, "parameters": [ { "default_known": false, "enum": [ "nvidia/nemotron-3.5-content-safety:free" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "default_known": false, "enum_known": false, "items": { "additionalProperties": false, "properties": { "content": { "type": "string" }, "role": { "enum": [ "user", "assistant", "system", "developer" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "name": "messages", "required": true, "type": "array" }, { "default": false, "default_known": true, "enum": [ false ], "enum_known": true, "name": "stream", "required": false, "type": "boolean" }, { "default_known": false, "enum_known": false, "maximum": 8192, "minimum": 1, "name": "max_tokens", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "maximum": 8192, "minimum": 1, "name": "max_completion_tokens", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "maximum": 128, "minimum": 1, "name": "n", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "name": "temperature", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "top_p", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "seed", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "name": "stop", "oneOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ], "required": false }, { "default_known": false, "enum_known": false, "name": "frequency_penalty", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "presence_penalty", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "user", "required": false, "type": "string" } ], "request_schema": { "additionalProperties": false, "properties": { "frequency_penalty": { "type": "number" }, "max_completion_tokens": { "maximum": 8192, "minimum": 1, "type": "integer" }, "max_tokens": { "maximum": 8192, "minimum": 1, "type": "integer" }, "messages": { "items": { "additionalProperties": false, "properties": { "content": { "type": "string" }, "role": { "enum": [ "user", "assistant", "system", "developer" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "model": { "enum": [ "nvidia/nemotron-3.5-content-safety:free" ], "type": "string" }, "n": { "maximum": 128, "minimum": 1, "type": "integer" }, "presence_penalty": { "type": "number" }, "seed": { "type": "integer" }, "stop": { "oneOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ] }, "stream": { "default": false, "enum": [ false ], "type": "boolean" }, "temperature": { "type": "number" }, "top_p": { "type": "number" }, "user": { "type": "string" } }, "required": [ "model", "messages" ], "type": "object" }, "schema_template": { "body": { "messages": [ { "content": "Summarize the supplied text in three concise points.", "role": "user" } ], "model": "nvidia/nemotron-3.5-content-safety:free", "stream": false }, "content_type": "application/json" } }, "input": { "conditions": [ "Use literal text messages only. Cache controls, tools, image/audio/video content and streamed responses are unavailable for this method.", "The complete encoded JSON request must not exceed 128000 bytes." ], "content_type": "application/json", "material_types": [ "text" ], "optional": [ "stream", "max_tokens", "max_completion_tokens", "n", "temperature", "top_p", "seed", "stop", "frequency_penalty", "presence_penalty", "user" ], "required": [ "model", "messages" ] }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_json_or_sse", "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/chat/completions" }, "method_aliases": [], "output": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "family": "text", "format": "JSON or supported SSE" } }, "ctx": 128000, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nvidia/nemotron-3.5-content-safety:free\", \"messages\": [{\"role\": \"user\", \"content\": \"Summarize the supplied text in three concise points.\"}], \"stream\": false}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n", "label": "curl · create once and retain the complete result", "language": "bash" } ], "family": "openai", "fast_multiplier": 1, "flex_multiplier": 1, "fmt": "chat", "http": "POST", "img_in": null, "img_out": null, "in": "0", "input": [ "text" ], "label": "Chat Completions", "max_out": 8192, "max_reasoning_effort_multiplier": 1, "method_aliases": [], "out": "0", "output": [ "text" ], "path": "/v1/chat/completions", "price_conditions": [ { "label": "Fast mode", "value": "Standard rate", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Standard rate", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Standard rate", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" }, { "label": "Text-only zero rates", "value": "Cache, tools and media follow their separately listed pricing conditions.", "when": "For text-only input and output" } ], "pricing": { "allow_explicit_cache": false, "billing_mode": "token", "cache_read_price": null, "cache_write_1h_price": null, "cache_write_price": null, "fast_multiplier": 1, "flex_multiplier": 1, "image_input_price": null, "image_output_price": null, "input_price": 0, "intervals": [], "max_reasoning_effort_multiplier": 1, "output_price": 0, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "nvidia/nemotron-3.5-content-safety:free", "route_label": "Ultra", "status_reads": [], "tiers": [], "unit": "token", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } } ], "model_id": "nvidia/nemotron-3.5-content-safety:free", "nativeProvenance": { "input_facts_canonical_sha256": "30f63e0eb6154dfc2a8b1576a1651e9ae245255c501e6842e90e066f2ed96180", "input_html_sha256": "5b74d6bdc705e0bb1eb7884da6b542ce74bd3e9355da9e053c71fde9747c2ef5", "private_audit_sha256": "17e3af135ba0ef71f94e7150727cd938dbffd7326ccfa5490c01097987d42c98", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/ms/nvidia-nemotron-3-5-content-safety-u003a-free/", "description": "Nemotron 3.5 Content Safety ialah model kawalan keselamatan 4B NVIDIA untuk mengelaskan prompt dan balasan model. Edisi Ailoot ini membaca teks dan mengembalikan teks, termasuk penilaian keselamatan dan label kategori oleh model. Gunakannya sebagai langkah moderasi terfokus dalam semakan yang lebih besar atau aliran kerja dasar aplikasi.", "locale": "ms", "md_url": "https://ailoot.ai/models/ms/nvidia-nemotron-3-5-content-safety-u003a-free/index.md", "title": "NVIDIA: Nemotron 3.5 Content Safety (free) — Ailoot", "url": "https://ailoot.ai/models/ms/nvidia-nemotron-3-5-content-safety-u003a-free/" }, "rawModel": { "about": "Nemotron 3.5 Content Safety ialah model kawalan keselamatan berparameter 4B NVIDIA, ditala halus daripada Gemma-3-4B. Peranan yang didokumenkan ialah moderasi prompt dan balasan, pengelasan kandungan dan aliran kerja dasar keselamatan. NVIDIA menerangkan output yang menilai prompt pengguna dan balasan sebagai selamat atau tidak selamat, menambah label kategori keselamatan dan secara pilihan menyertakan jejak penaakulan. Penilaian itu ialah output model untuk dinilai dan digunakan oleh aplikasi. Setiap mesej mempunyai role system, developer, user atau assistant dan content rentetan biasa. name pilihan ialah rentetan; hadkan setiap mesej kepada medan ini. Hantar stream:false, atau jangan sertakan stream.\n\nGunakan ID model tepat nvidia/nemotron-3.5-content-safety:free dengan POST /v1/chat/completions dan tatasusunan messages yang tidak kosong. Letakkan bahan untuk dinilai dalam content teks dan bezakan prompt pengguna daripada balasan model apabila kedua-duanya disemak. Langkah moderasi praktikal boleh melabelkan kedua-dua petikan itu secara jelas dan meminta model mengenal pasti kategori yang berkaitan sambil memastikan penilaiannya terikat pada kandungan yang dibekalkan.\n\nEdisi Ailoot ini menerima teks dan mengembalikan teks. Untuk baris gilir semakan, sediakan hantaran sebenar, draf mesej sokongan atau jawapan terjana yang memerlukan penilaian, bersama konteks sekeliling yang mengubah maknanya. Kekalkan keputusan aplikasi seperti menghalakan item bertanda untuk semakan manusia dalam aliran kerja anda sendiri. Input media, kawalan panggilan alat dan kawalan cache eksplisit berada di luar profil permintaan edisi ini.\n\nHalaman model menyenaraikan tetingkap konteks 128,000 token dan sehingga 8,192 token pelengkapan. Ailoot turut memerlukan seluruh badan permintaan JSON UTF-8, termasuk arahan dan nama medan, muat dalam 128,000 bait. Untuk had output yang jelas, tetapkan tepat satu daripada max_tokens atau max_completion_tokens kepada integer positif dari 1 hingga 8,192. Jika kedua-duanya tidak dibekalkan, Ailoot meneruskan had output 4,096 token. Ambil kira keseluruhan perbualan dan penilaian yang anda minta. Penerangan model melaporkan liputan 12 bahasa; kekalkan kata-kata asal apabila penilaian bergantung pada bahasa sumber. Jika aplikasi anda menjangkakan label tertentu, huraikan dan sahkan teks yang dikembalikan berdasarkan peraturan pengendalian yang anda pilih. Jawapan yang diminta supaya kelihatan seperti JSON tidak menjamin output dengan skema yang dikuatkuasakan.\n\nGunakan stream:false untuk balasan perbualan JSON lengkap. Baca choices[].message.content, simpan setiap pilihan yang dikembalikan dan sebarang medan penaakulan yang dibekalkan, serta kekalkan finish_reason dan usage. Simpan penilaian bersama prompt dan balasan tepat yang dinilainya supaya keputusan boleh disemak kemudian. Penilaian satu teks terpakai pada teks dan konteks yang dibekalkan itu; nilai balasan yang berubah secara ketara sebagai itemnya sendiri.\n\nSediakan bahan yang tidak mengandungi maklumat sulit, sebagaimana diwajibkan oleh terma penggunaan yang didokumenkan bagi edisi percuma ini. Jika permintaan berakhir tanpa penilaian lengkap, simpan pengecam permintaan asal dan data yang dikembalikan semasa menyemak percubaan sedia ada. Kad ini mendokumenkan hasil perbualan langsung dan tidak membekalkan aliran kerja tugasan tak segerak atau pembatalan berasingan.", "alias_of": null, "aliases": [], "author": "NVIDIA", "ctx": 128000, "formats": [ "chat" ], "id": "nvidia/nemotron-3.5-content-safety:free", "input": [ "text" ], "kind": "text", "max_out": 8192, "methods": [ { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "example_body": { "messages": [ { "content": "Summarize the supplied text in three concise points.", "role": "user" } ], "model": "nvidia/nemotron-3.5-content-safety:free", "stream": false }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_json_or_sse", "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "outputs": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "family": "text", "format": "JSON or supported SSE" }, "parameters": [ { "default_known": false, "enum": [ "nvidia/nemotron-3.5-content-safety:free" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "default_known": false, "enum_known": false, "items": { "additionalProperties": false, "properties": { "content": { "type": "string" }, "role": { "enum": [ "user", "assistant", "system", "developer" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "name": "messages", "required": true, "type": "array" }, { "default": false, "default_known": true, "enum": [ false ], "enum_known": true, "name": "stream", "required": false, "type": "boolean" }, { "default_known": false, "enum_known": false, "maximum": 8192, "minimum": 1, "name": "max_tokens", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "maximum": 8192, "minimum": 1, "name": "max_completion_tokens", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "maximum": 128, "minimum": 1, "name": "n", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "name": "temperature", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "top_p", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "seed", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "name": "stop", "oneOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ], "required": false }, { "default_known": false, "enum_known": false, "name": "frequency_penalty", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "presence_penalty", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "user", "required": false, "type": "string" } ], "request_schema": { "additionalProperties": false, "properties": { "frequency_penalty": { "type": "number" }, "max_completion_tokens": { "maximum": 8192, "minimum": 1, "type": "integer" }, "max_tokens": { "maximum": 8192, "minimum": 1, "type": "integer" }, "messages": { "items": { "additionalProperties": false, "properties": { "content": { "type": "string" }, "role": { "enum": [ "user", "assistant", "system", "developer" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "model": { "enum": [ "nvidia/nemotron-3.5-content-safety:free" ], "type": "string" }, "n": { "maximum": 128, "minimum": 1, "type": "integer" }, "presence_penalty": { "type": "number" }, "seed": { "type": "integer" }, "stop": { "oneOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ] }, "stream": { "default": false, "enum": [ false ], "type": "boolean" }, "temperature": { "type": "number" }, "top_p": { "type": "number" }, "user": { "type": "string" } }, "required": [ "model", "messages" ], "type": "object" }, "schema_template": { "body": { "messages": [ { "content": "Summarize the supplied text in three concise points.", "role": "user" } ], "model": "nvidia/nemotron-3.5-content-safety:free", "stream": false }, "content_type": "application/json" } }, "input": { "conditions": [ "Use literal text messages only. Cache controls, tools, image/audio/video content and streamed responses are unavailable for this method.", "The complete encoded JSON request must not exceed 128000 bytes." ], "content_type": "application/json", "material_types": [ "text" ], "optional": [ "stream", "max_tokens", "max_completion_tokens", "n", "temperature", "top_p", "seed", "stop", "frequency_penalty", "presence_penalty", "user" ], "required": [ "model", "messages" ] }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_json_or_sse", "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/chat/completions" }, "method_aliases": [], "output": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "family": "text", "format": "JSON or supported SSE" } }, "ctx": 128000, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"nvidia/nemotron-3.5-content-safety:free\", \"messages\": [{\"role\": \"user\", \"content\": \"Summarize the supplied text in three concise points.\"}], \"stream\": false}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n", "label": "curl · create once and retain the complete result", "language": "bash" } ], "family": "openai", "fast_multiplier": 1, "flex_multiplier": 1, "fmt": "chat", "http": "POST", "img_in": null, "img_out": null, "in": "0", "input": [ "text" ], "label": "Chat Completions", "max_out": 8192, "max_reasoning_effort_multiplier": 1, "method_aliases": [], "out": "0", "output": [ "text" ], "path": "/v1/chat/completions", "price_conditions": [ { "label": "Fast mode", "value": "Standard rate", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Standard rate", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Standard rate", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" }, { "label": "Text-only zero rates", "value": "Cache, tools and media follow their separately listed pricing conditions.", "when": "For text-only input and output" } ], "pricing": { "allow_explicit_cache": false, "billing_mode": "token", "cache_read_price": null, "cache_write_1h_price": null, "cache_write_price": null, "fast_multiplier": 1, "flex_multiplier": 1, "image_input_price": null, "image_output_price": null, "input_price": 0, "intervals": [], "max_reasoning_effort_multiplier": 1, "output_price": 0, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "nvidia/nemotron-3.5-content-safety:free", "route_label": "Ultra", "status_reads": [], "tiers": [], "unit": "token", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "model_aliases": [ { "canonical_model_id": "nvidia/nemotron-3.5-content-safety:free", "request_model_id": "nvidia/nemotron-3.5-content-safety:free", "route_label": "Ultra" } ], "name": "NVIDIA: Nemotron 3.5 Content Safety (free)", "price": { "in": "0", "in_label": null, "out": "0", "out_label": null, "sort_in": "0", "sort_out": "0", "varies": false }, "short": "Nemotron 3.5 Content Safety ialah model kawalan keselamatan 4B NVIDIA untuk mengelaskan prompt dan balasan model. Edisi Ailoot ini membaca teks dan mengembalikan teks, termasuk penilaian keselamatan dan label kategori oleh model. Gunakannya sebagai langkah moderasi terfokus dalam semakan yang lebih besar atau aliran kerja dasar aplikasi." }, "renderer_schema": { "method_order": "Original DTO methods order; every exact route/format/path/caller survives.", "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers." }, "representation": "exact-public-dto-and-native-renderer-html", "representationNotes": { "current_reference": { "about_json_pointer": "/aboutHtml", "methods": [ { "contract_json_pointer": "/methods/0/rawMethod/contract", "html_json_pointer": "/methods/0/html", "method_ordinal": 0 } ], "role": "current-semantic-reference" }, "raw_input": { "examples_role": "historical-input-not-current-ready-examples", "json_pointers": [ "/rawModel", "/methods/0/rawMethod" ], "role": "historical-owner-input" }, "schema": "ailoot-native-model-representations-v1" }, "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "Nemotron 3.5 Content Safety ialah model kawalan keselamatan 4B NVIDIA untuk mengelaskan prompt dan balasan model. Edisi Ailoot ini membaca teks dan mengembalikan teks, termasuk penilaian keselamatan dan label kategori oleh model. Gunakannya sebagai langkah moderasi terfokus dalam semakan yang lebih besar atau aliran kerja dasar aplikasi.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "892ebed66c3fefa425bca69890c1359e116acc4d22cc26be5f526a93bbc1e5ea", "renderer_sha256": "1dab5ba62521e9568c8b7c82005622cabbf330a075df7cce1f83274a04009460" }, "sourceRevision": "ffefe1a8c06e146a1bbbf28872199c0fe42f914837eae973b70f43f013084eb5" }