{ "aboutHtml": "

Summarize ialah model peringkasan abstraktif ScaleDown. Ia memadatkan teks dan dokumen yang dibekalkan menjadi tulisan semula yang lancar, bukannya memilih beberapa ayat asal secara verbatim. Kegunaan yang diterbitkan termasuk semakan dokumen, ringkasan transkrip dan memendekkan bahan yang diperoleh semula sebelum diproses oleh model lain.

Takrifkan perkara yang mesti dikekalkan dalam ringkasan

Berikan tugas itu fokus dan pembaca sasaran. Ringkasan mesyuarat boleh mengekalkan keputusan, tanggungjawab dan soalan yang masih terbuka. Semakan dokumen boleh mengekalkan dakwaan utama dan bukti sokongan. Aliran kerja perolehan semula boleh mengekalkan fakta yang penting untuk soalan yang akan dijawab oleh model seterusnya.

Nyatakan bahasa, panjang dan susun atur yang dikehendaki dalam arahan kandungan. Model yang diterbitkan menggunakan arahan dalam prompt sistem untuk pilihan tersebut, manakala konfigurasi pensampelannya tetap untuk menghasilkan output yang setia kepada sumber. Oleh itu, ringkasan untuk seseorang dan petikan ringkas untuk model lain boleh menggunakan susun atur berbeza tanpa menjadikan variasi pensampelan sebagai kawalan utama.

Tulisan semula dengan fakta yang boleh dijejaki

Simpan nama dokumen dan sempadan bahagian yang penting bersama sumber. Minta ringkasan mengekalkan nama, nombor, keputusan yang dinyatakan dan sebarang percanggahan pendapat yang mempengaruhi tafsiran. Untuk transkrip, bezakan cadangan daripada keputusan dan soalan yang belum diselesaikan daripada tindakan yang telah ditugaskan.

Selepas penjanaan, bandingkan teks yang dipadatkan dengan bahan asal. Semak sama ada sesuatu ayat mengubah tahap kepastian dakwaan, menggugurkan syarat atau menggabungkan pernyataan milik pembicara atau bahagian yang berbeza. Tujuan hasil yang lebih pendek ialah memudahkan bukti dibaca sambil mengekalkan maknanya.

Dokumen, imej dan konteks perolehan semula

Julat input yang diterbitkan merangkumi teks, imej dan fail seperti PDF, dan model mengembalikan teks. Bekalkan bahan yang boleh dibaca dan takrifkan sama ada tugas melibatkan seluruh dokumen atau bahagian yang dipilih. Koleksi mendapat manfaat daripada soalan ringkasan yang konsisten serta pengecam dokumen yang disimpan bersama setiap hasil.

Untuk prapemprosesan perolehan semula, pendekkan kandungan berdasarkan soalan khusus yang perlu ditangani oleh penaakulan pada peringkat seterusnya. Kekalkan petikan atau fakta yang menyokong jawapan, bukannya menghasilkan gambaran umum sumber. Pastikan bahan asal yang diperoleh semula tetap tersedia supaya hasil berikutnya masih boleh disemak terhadapnya.

Rancang panjang output

Tetingkap konteks yang diterbitkan ialah 1,000,000 token dan had pelengkapannya ialah 4,000 token. Tetapkan panjang ringkasan yang sesuai dengan artifak yang dimaksudkan. Jika koleksi besar memerlukan butiran yang banyak, susunkannya menjadi dokumen atau bahagian berpengecam dan simpan hasil berasingan bagi setiap satunya sebelum mengarang ringkasan peringkat koleksi.

Hasilnya ialah ringkasan teks. Sahkan sebarang struktur yang diproses mesin dalam aplikasi, sambil memastikan ringkasan bertulis boleh dibaca oleh khalayak sasarannya. Simpan ringkasan bersama identiti sumber dan arahan yang menentukan fokus, bahasa serta panjangnya.

Keupayaan

Kes penggunaan

Had

", "aboutText": "Summarize ialah model peringkasan abstraktif ScaleDown. Ia memadatkan teks dan dokumen yang dibekalkan menjadi tulisan semula yang lancar, bukannya memilih beberapa ayat asal secara verbatim. Kegunaan yang diterbitkan termasuk semakan dokumen, ringkasan transkrip dan memendekkan bahan yang diperoleh semula sebelum diproses oleh model lain.\n\n### Takrifkan perkara yang mesti dikekalkan dalam ringkasan\n\nBerikan tugas itu fokus dan pembaca sasaran. Ringkasan mesyuarat boleh mengekalkan keputusan, tanggungjawab dan soalan yang masih terbuka. Semakan dokumen boleh mengekalkan dakwaan utama dan bukti sokongan. Aliran kerja perolehan semula boleh mengekalkan fakta yang penting untuk soalan yang akan dijawab oleh model seterusnya.\n\nNyatakan bahasa, panjang dan susun atur yang dikehendaki dalam arahan kandungan. Model yang diterbitkan menggunakan arahan dalam prompt sistem untuk pilihan tersebut, manakala konfigurasi pensampelannya tetap untuk menghasilkan output yang setia kepada sumber. Oleh itu, ringkasan untuk seseorang dan petikan ringkas untuk model lain boleh menggunakan susun atur berbeza tanpa menjadikan variasi pensampelan sebagai kawalan utama.\n\n### Tulisan semula dengan fakta yang boleh dijejaki\n\nSimpan nama dokumen dan sempadan bahagian yang penting bersama sumber. Minta ringkasan mengekalkan nama, nombor, keputusan yang dinyatakan dan sebarang percanggahan pendapat yang mempengaruhi tafsiran. Untuk transkrip, bezakan cadangan daripada keputusan dan soalan yang belum diselesaikan daripada tindakan yang telah ditugaskan.\n\nSelepas penjanaan, bandingkan teks yang dipadatkan dengan bahan asal. Semak sama ada sesuatu ayat mengubah tahap kepastian dakwaan, menggugurkan syarat atau menggabungkan pernyataan milik pembicara atau bahagian yang berbeza. Tujuan hasil yang lebih pendek ialah memudahkan bukti dibaca sambil mengekalkan maknanya.\n\n### Dokumen, imej dan konteks perolehan semula\n\nJulat input yang diterbitkan merangkumi teks, imej dan fail seperti PDF, dan model mengembalikan teks. Bekalkan bahan yang boleh dibaca dan takrifkan sama ada tugas melibatkan seluruh dokumen atau bahagian yang dipilih. Koleksi mendapat manfaat daripada soalan ringkasan yang konsisten serta pengecam dokumen yang disimpan bersama setiap hasil.\n\nUntuk prapemprosesan perolehan semula, pendekkan kandungan berdasarkan soalan khusus yang perlu ditangani oleh penaakulan pada peringkat seterusnya. Kekalkan petikan atau fakta yang menyokong jawapan, bukannya menghasilkan gambaran umum sumber. Pastikan bahan asal yang diperoleh semula tetap tersedia supaya hasil berikutnya masih boleh disemak terhadapnya.\n\n### Rancang panjang output\n\nTetingkap konteks yang diterbitkan ialah 1,000,000 token dan had pelengkapannya ialah 4,000 token. Tetapkan panjang ringkasan yang sesuai dengan artifak yang dimaksudkan. Jika koleksi besar memerlukan butiran yang banyak, susunkannya menjadi dokumen atau bahagian berpengecam dan simpan hasil berasingan bagi setiap satunya sebelum mengarang ringkasan peringkat koleksi.\n\nHasilnya ialah ringkasan teks. Sahkan sebarang struktur yang diproses mesin dalam aplikasi, sambil memastikan ringkasan bertulis boleh dibaca oleh khalayak sasarannya. Simpan ringkasan bersama identiti sumber dan arahan yang menentukan fokus, bahasa serta panjangnya.\n\n### Keupayaan\n\n- Ringkasan abstraktif yang menulis semula dan memadatkan bahan yang dibekalkan.\n- Fokus, bahasa, panjang dan susun atur yang dipandu oleh arahan.\n- Konfigurasi pensampelan tetap yang ditala untuk output yang setia kepada sumber.\n- Input teks, imej dan fail dengan output teks.\n- Konteks 1,000,000 token dan had pelengkapan 4,000 token yang diterbitkan.\n\n### Kes penggunaan\n\n- **Ringkasan semakan dokumen** — Dokumen dan penemuan yang perlu dikekalkan oleh pembaca. Hasil: Ringkasan ringkas beridentiti dengan fakta utama dikekalkan.\n- **Ringkasan transkrip** — Transkrip yang berfokus pada keputusan, tanggungjawab atau soalan terbuka. Hasil: Teks lebih pendek yang memisahkan kategori tersebut.\n- **Prapemprosesan bahan yang diperoleh semula** — Kandungan yang diperoleh semula dan soalan pada peringkat seterusnya. Hasil: Petikan bukti padat untuk penaakulan kemudian.\n- **Ringkasan koleksi** — Dokumen bernama dengan arahan ringkasan yang dikongsi. Hasil: Ringkasan bagi setiap dokumen yang boleh dibandingkan.\n\n### Had\n\n- **Konteks** — Tetingkap konteks yang diterbitkan: 1,000,000 token.\n- **Jawapan** — Had pelengkapan yang diterbitkan: 4,000 token.\n- **Kawalan gaya** — Kawal fokus, bahasa, panjang dan format melalui arahan; pensampelan adalah tetap.\n- **Kontrak output** — Output yang diterbitkan ialah teks; panggilan fungsi dan JSON yang dikuatkuasakan mengikut skema tidak disenaraikan.\n", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "44b3170346702aece1d72d0185a4f478d162c967a9224216d868edf8fec15a65", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "ms", "methods": [ { "html": "
•

ScaleDown: Summarize

ScaleDown /scaledown/summarize

Pengenalan

Summarize menulis semula teks dan dokumen yang panjang menjadi ringkasan yang lancar dan setia kepada sumber. Tetapkan fokus, bahasa, panjang dan format melalui arahan, kemudian gunakan hasil untuk semakan dokumen, ringkasan transkrip atau konteks perolehan semula yang lebih pendek. Tetingkap yang diterbitkan ialah 1,000,000 token, dengan had pelengkapan 4,000 token.

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.

Summarize ialah model peringkasan abstraktif ScaleDown. Ia memadatkan teks dan dokumen yang dibekalkan menjadi tulisan semula yang lancar, bukannya memilih beberapa ayat asal secara verbatim. Kegunaan yang diterbitkan termasuk semakan dokumen, ringkasan transkrip dan memendekkan bahan yang diperoleh semula sebelum diproses oleh model lain.

Takrifkan perkara yang mesti dikekalkan dalam ringkasan

Berikan tugas itu fokus dan pembaca sasaran. Ringkasan mesyuarat boleh mengekalkan keputusan, tanggungjawab dan soalan yang masih terbuka. Semakan dokumen boleh mengekalkan dakwaan utama dan bukti sokongan. Aliran kerja perolehan semula boleh mengekalkan fakta yang penting untuk soalan yang akan dijawab oleh model seterusnya.

Nyatakan bahasa, panjang dan susun atur yang dikehendaki dalam arahan kandungan. Model yang diterbitkan menggunakan arahan dalam prompt sistem untuk pilihan tersebut, manakala konfigurasi pensampelannya tetap untuk menghasilkan output yang setia kepada sumber. Oleh itu, ringkasan untuk seseorang dan petikan ringkas untuk model lain boleh menggunakan susun atur berbeza tanpa menjadikan variasi pensampelan sebagai kawalan utama.

Tulisan semula dengan fakta yang boleh dijejaki

Simpan nama dokumen dan sempadan bahagian yang penting bersama sumber. Minta ringkasan mengekalkan nama, nombor, keputusan yang dinyatakan dan sebarang percanggahan pendapat yang mempengaruhi tafsiran. Untuk transkrip, bezakan cadangan daripada keputusan dan soalan yang belum diselesaikan daripada tindakan yang telah ditugaskan.

Selepas penjanaan, bandingkan teks yang dipadatkan dengan bahan asal. Semak sama ada sesuatu ayat mengubah tahap kepastian dakwaan, menggugurkan syarat atau menggabungkan pernyataan milik pembicara atau bahagian yang berbeza. Tujuan hasil yang lebih pendek ialah memudahkan bukti dibaca sambil mengekalkan maknanya.

Dokumen, imej dan konteks perolehan semula

Julat input yang diterbitkan merangkumi teks, imej dan fail seperti PDF, dan model mengembalikan teks. Bekalkan bahan yang boleh dibaca dan takrifkan sama ada tugas melibatkan seluruh dokumen atau bahagian yang dipilih. Koleksi mendapat manfaat daripada soalan ringkasan yang konsisten serta pengecam dokumen yang disimpan bersama setiap hasil.

Untuk prapemprosesan perolehan semula, pendekkan kandungan berdasarkan soalan khusus yang perlu ditangani oleh penaakulan pada peringkat seterusnya. Kekalkan petikan atau fakta yang menyokong jawapan, bukannya menghasilkan gambaran umum sumber. Pastikan bahan asal yang diperoleh semula tetap tersedia supaya hasil berikutnya masih boleh disemak terhadapnya.

Rancang panjang output

Tetingkap konteks yang diterbitkan ialah 1,000,000 token dan had pelengkapannya ialah 4,000 token. Tetapkan panjang ringkasan yang sesuai dengan artifak yang dimaksudkan. Jika koleksi besar memerlukan butiran yang banyak, susunkannya menjadi dokumen atau bahagian berpengecam dan simpan hasil berasingan bagi setiap satunya sebelum mengarang ringkasan peringkat koleksi.

Hasilnya ialah ringkasan teks. Sahkan sebarang struktur yang diproses mesin dalam aplikasi, sambil memastikan ringkasan bertulis boleh dibaca oleh khalayak sasarannya. Simpan ringkasan bersama identiti sumber dan arahan yang menentukan fokus, bahasa serta panjangnya.

Keupayaan

  • Ringkasan abstraktif yang menulis semula dan memadatkan bahan yang dibekalkan.
  • Fokus, bahasa, panjang dan susun atur yang dipandu oleh arahan.
  • Konfigurasi pensampelan tetap yang ditala untuk output yang setia kepada sumber.
  • Input teks, imej dan fail dengan output teks.
  • Konteks 1,000,000 token dan had pelengkapan 4,000 token yang diterbitkan.

Kes penggunaan

  • Ringkasan semakan dokumen — Dokumen dan penemuan yang perlu dikekalkan oleh pembaca. Hasil: Ringkasan ringkas beridentiti dengan fakta utama dikekalkan.
  • Ringkasan transkrip — Transkrip yang berfokus pada keputusan, tanggungjawab atau soalan terbuka. Hasil: Teks lebih pendek yang memisahkan kategori tersebut.
  • Prapemprosesan bahan yang diperoleh semula — Kandungan yang diperoleh semula dan soalan pada peringkat seterusnya. Hasil: Petikan bukti padat untuk penaakulan kemudian.
  • Ringkasan koleksi — Dokumen bernama dengan arahan ringkasan yang dikongsi. Hasil: Ringkasan bagi setiap dokumen yang boleh dibandingkan.

Had

  • Konteks — Tetingkap konteks yang diterbitkan: 1,000,000 token.
  • Jawapan — Had pelengkapan yang diterbitkan: 4,000 token.
  • Kawalan gaya — Kawal fokus, bahasa, panjang dan format melalui arahan; pensampelan adalah tetap.
  • Kontrak output — Output yang diterbitkan ialah teks; panggilan fungsi dan JSON yang dikuatkuasakan mengikut skema tidak disenaraikan.

Tersedia di Ailoot · input & kaedah

Ailoot Ultra · OpenAI Chat POST /v1/chat/completions
Input
text
Output
text
Format output
json atau SSE
MedanJenisKeperluanNilai & hadLalai
MedanmodelJenisstringKeperluanDiperlukanNilai & had
scaledown/summarize
Lalai—
MedanmessagesJenismessage[]KeperluanDiperlukanNilai & had
Item minimum: 1
Lalai—
Medanmessages[].roleJenisstringKeperluanDiperlukanNilai & had
Bergantung pada model
Lalai—
Medanmessages[].contentJenisstringKeperluanPilihanNilai & had
Terpakai apabila: Perbualan teks
Lalai—
MedanstreamJenisbooleanKeperluanPilihanNilai & hadLalaifalse
Gabungan bahan input

Teks · Teks UTF8

messages[].content

Parameter kaedah dan kitar hayat
ParameterKontrak
Parametercontent_typeKontrakapplication/json
ParameterrequiredKontrakmodel, messages
Parametermaterial_typesKontraktext
ParametermessagesKontraktatasusunan mesej dengan struktur role/content
Parameterfile_materialKontrakdokumen UTF-8 sebenar dimasukkan sebagai teks literal; ID fail tidak diandaikan
Parameteroptional_controlsKontrakstream
Parametercontrol_scopeKontrakPerbualan teks; stream ialah nilai boolean dengan false sebagai lalai.
Parameteroutput_modalitiesKontraktext
Parameterhosted_operationsKontrakfalse
Parametermultimodal_input_bindingKontraknull

Alias kaedah: /chat/completions

Kitar hayat: synchronous_or_streamed

Hantar ID model yang tepat bersama messages.

Panjang konteks bukan had output.

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

Pelan harga

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

Mod pantas
Tidak dinyatakan Apabila mod pantas dipilih
Mod flex
Tidak dinyatakan Apabila mod flex dipilih
Usaha penaakulan maksimum
Tidak dinyatakan Apabila usaha penaakulan maksimum menggunakan pelarasan default

Kadar Ailoot

Harga mengikut konfigurasi

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

KonfigurasiJadual kadarToken konteks, melebihiToken konteks, sehingga dan termasukCaj
KonfigurasiKadar asas tokenJadual kadarKadar asasToken konteks, melebihi—Token konteks, sehingga dan termasukTiada had atasCaj
Input · Token input $0.0001 / 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
KonfigurasiTahap panjang permintaan 1Jadual kadar—Token konteks, melebihi0Token konteks, sehingga dan termasukTiada had atasCaj
Input · Token input $0.0001 / 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 · OpenAI Chat

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"scaledown/summarize","messages":[{"role":"user","content":"hello"}],"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\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n    if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\n

Terima dan simpan hasil

Ailoot Ultra · OpenAI Chat

json atau SSE

Simpan semua hasil yang selesai

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

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

Jika respons asal perlu disemak

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

Medan respons
MedanJenis
Medanchoices[].indexJenisinteger
Medanchoices[].message.contentJenisstring|null
Medanchoices[].message.tool_callsJenistool_call[]
Medanchoices[].message.reasoning_contentJenisstring
Medanchoices[].message.reasoning_detailsJenisobject|array
Medanchoices[].finish_reasonJenisstring|null
MedanusageJenisobject
Ralat dan langkah seterusnya
ResponsSyaratLangkah seterusnya
Respons400 · invalid_request_errorSyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sahLangkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu.

Alias

Alias model

Ailoot Ultra scaledown/summarize

Alias laluan kaedah

/chat/completions

ID pemanggil berkaitan

scaledown/summarize

", "method_identity": { "effective_request_model_id": "scaledown/summarize", "fmt": "chat", "http": "POST", "path": "/v1/chat/completions", "request_model_id": "scaledown/summarize", "route_label": "Ultra" }, "method_key": "Ultra|chat|/v1/chat/completions|scaledown%2Fsummarize", "ordinal": 0, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "errors": [ { "code": null, "condition": "Medan wajib, perwakilan bahan atau nilai parameter tidak sah", "http_status": 400, "recovery": "Betulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu.", "type": "invalid_request_error" } ], "hints": [ "Model context is not an output cap.", "Send the conversation as text messages. Stream must be a boolean; omitted stream defaults to false." ], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/chat/completions" }, "job_read": null, "mode": "synchronous_or_streamed", "unknown": "Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan." }, "material_combinations": [ { "mode": "text", "representation": "messages[].content", "required_material": "Teks UTF8" } ], "operation_modes": [ "conversation" ], "outputs": { "all_results": "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.", "family": "text", "fields": [ { "description": null, "name": "choices[].index", "type": "integer" }, { "description": null, "name": "choices[].message.content", "type": "string|null" }, { "description": null, "name": "choices[].message.tool_calls", "type": "tool_call[]" }, { "description": null, "name": "choices[].message.reasoning_content", "type": "string" }, { "description": null, "name": "choices[].message.reasoning_details", "type": "object|array" }, { "description": null, "name": "choices[].finish_reason", "type": "string|null" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json atau SSE" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "scaledown/summarize" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "messages", "required": true, "type": "message[]" }, { "availability": "model_dependent", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "messages[].role", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "messages[].content", "required": false, "type": "string", "when": "Perbualan teks" }, { "availability": "source_interface", "default": false, "default_known": true, "enum": null, "enum_known": false, "name": "stream", "required": false, "type": "boolean" } ], "profile_binding": "Text conversation at the exact model ID and method path.", "unsupported": [ "additional models/models list", "plugins", "route", "hosted tools; ordinary client function tools remain separate", "non-text output modalities", "provider.options overrides", "one-hour prompt-cache TTL" ] }, "hints": [ "Hantar ID model yang tepat bersama messages.", "Panjang konteks bukan had output.", "Fail teks boleh membekalkan teks literal; input imej/audio/objek fail memerlukan pengikatan tepat." ], "input": { "content_type": "application/json", "control_scope": "Perbualan teks; stream ialah nilai boolean dengan false sebagai lalai.", "file_material": "dokumen UTF-8 sebenar dimasukkan sebagai teks literal; ID fail tidak diandaikan", "hosted_operations": false, "material_types": [ "text" ], "messages": "tatasusunan mesej dengan struktur role/content", "multimodal_input_binding": null, "optional_controls": [ "stream" ], "output_modalities": [ "text" ], "required": [ "model", "messages" ] }, "lifecycle": { "mode": "synchronous_or_streamed", "unknown": "preserve original request id; no generic chat job retrieval path" }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/chat/completions" }, "method_aliases": [ "/chat/completions" ], "operation_modes": [ "text_chat" ], "output": { "content": "choices[].message.content or stream delta", "family": "text", "format": "json or supported SSE", "tool_calls": "retain actual returned function calls" } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Kadar asas token", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Tahap panjang permintaan 1", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\":\"scaledown/summarize\",\"messages\":[{\"role\":\"user\",\"content\":\"hello\"}],\"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\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"choices\",[]):\n if x.get(\"message\",{}).get(\"content\"): print(x[\"message\"][\"content\"])\nPY_RESULT\n", "label": "curl · retained exact creation", "language": "bash" }, { "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.chat.completions.create(model=\"scaledown/summarize\", messages=[{\"role\":\"user\",\"content\":\"hello\"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n 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\n file = Path(stem + \"-\" + label + \".\" + ext)\n file.write_bytes(raw)\n print(\"Saved\", file)\n for index, block in enumerate(data.get(\"content\") or []):\n print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get(\"choices\") or []:\n print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n for index, item in enumerate(data.get(\"output\") or []):\n print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n for ci, candidate in enumerate(data.get(\"candidates\") or []):\n for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n if blob and blob.get(\"data\"):\n mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(result.to_dict(mode=\"json\"))\n", "label": "Python SDK · all choices", "language": "python" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "chat", "hints": [ "Send exact model ID with messages.", "Context length is not an output cap.", "A text file may supply literal text; image/audio/file-object inputs need exact binding." ], "http": "POST", "in": 0.1, "input": [ "text" ], "label": "OpenAI Chat", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [ "/chat/completions" ], "out": 0, "output": [ "text" ], "path": "/v1/chat/completions", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "token", "image_input_price": null, "image_output_price": null, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Request-length tier 1", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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": "scaledown/summarize", "route_label": "Ultra", "status_reads": [], "tiers": [ { "cache_read": null, "cache_read_multiplier": null, "cache_write": null, "cache_write_1h": null, "cache_write_multiplier": null, "created_at": "0001-01-01T00:00:00Z", "in": 0.1, "input_multiplier": null, "interval_boundary": "min_exclusive_max_inclusive", "max": null, "max_tokens": null, "min": 0, "min_tokens": 0, "null_rate_policy": "unknown or inherited; never zero", "out": 0, "output_multiplier": null, "per_request_price": null, "sort_order": 0, "tier_label": "", "updated_at": "0001-01-01T00:00:00Z" } ], "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] } }, { "html": "
•

ScaleDown: Summarize

ScaleDown /scaledown/summarize

Pengenalan

Summarize menulis semula teks dan dokumen yang panjang menjadi ringkasan yang lancar dan setia kepada sumber. Tetapkan fokus, bahasa, panjang dan format melalui arahan, kemudian gunakan hasil untuk semakan dokumen, ringkasan transkrip atau konteks perolehan semula yang lebih pendek. Tetingkap yang diterbitkan ialah 1,000,000 token, dengan had pelengkapan 4,000 token.

Input yang diterima
Teks
Hasil
json · sse
Tentang model

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

Summarize ialah model peringkasan abstraktif ScaleDown. Ia memadatkan teks dan dokumen yang dibekalkan menjadi tulisan semula yang lancar, bukannya memilih beberapa ayat asal secara verbatim. Kegunaan yang diterbitkan termasuk semakan dokumen, ringkasan transkrip dan memendekkan bahan yang diperoleh semula sebelum diproses oleh model lain.

Takrifkan perkara yang mesti dikekalkan dalam ringkasan

Berikan tugas itu fokus dan pembaca sasaran. Ringkasan mesyuarat boleh mengekalkan keputusan, tanggungjawab dan soalan yang masih terbuka. Semakan dokumen boleh mengekalkan dakwaan utama dan bukti sokongan. Aliran kerja perolehan semula boleh mengekalkan fakta yang penting untuk soalan yang akan dijawab oleh model seterusnya.

Nyatakan bahasa, panjang dan susun atur yang dikehendaki dalam arahan kandungan. Model yang diterbitkan menggunakan arahan dalam prompt sistem untuk pilihan tersebut, manakala konfigurasi pensampelannya tetap untuk menghasilkan output yang setia kepada sumber. Oleh itu, ringkasan untuk seseorang dan petikan ringkas untuk model lain boleh menggunakan susun atur berbeza tanpa menjadikan variasi pensampelan sebagai kawalan utama.

Tulisan semula dengan fakta yang boleh dijejaki

Simpan nama dokumen dan sempadan bahagian yang penting bersama sumber. Minta ringkasan mengekalkan nama, nombor, keputusan yang dinyatakan dan sebarang percanggahan pendapat yang mempengaruhi tafsiran. Untuk transkrip, bezakan cadangan daripada keputusan dan soalan yang belum diselesaikan daripada tindakan yang telah ditugaskan.

Selepas penjanaan, bandingkan teks yang dipadatkan dengan bahan asal. Semak sama ada sesuatu ayat mengubah tahap kepastian dakwaan, menggugurkan syarat atau menggabungkan pernyataan milik pembicara atau bahagian yang berbeza. Tujuan hasil yang lebih pendek ialah memudahkan bukti dibaca sambil mengekalkan maknanya.

Dokumen, imej dan konteks perolehan semula

Julat input yang diterbitkan merangkumi teks, imej dan fail seperti PDF, dan model mengembalikan teks. Bekalkan bahan yang boleh dibaca dan takrifkan sama ada tugas melibatkan seluruh dokumen atau bahagian yang dipilih. Koleksi mendapat manfaat daripada soalan ringkasan yang konsisten serta pengecam dokumen yang disimpan bersama setiap hasil.

Untuk prapemprosesan perolehan semula, pendekkan kandungan berdasarkan soalan khusus yang perlu ditangani oleh penaakulan pada peringkat seterusnya. Kekalkan petikan atau fakta yang menyokong jawapan, bukannya menghasilkan gambaran umum sumber. Pastikan bahan asal yang diperoleh semula tetap tersedia supaya hasil berikutnya masih boleh disemak terhadapnya.

Rancang panjang output

Tetingkap konteks yang diterbitkan ialah 1,000,000 token dan had pelengkapannya ialah 4,000 token. Tetapkan panjang ringkasan yang sesuai dengan artifak yang dimaksudkan. Jika koleksi besar memerlukan butiran yang banyak, susunkannya menjadi dokumen atau bahagian berpengecam dan simpan hasil berasingan bagi setiap satunya sebelum mengarang ringkasan peringkat koleksi.

Hasilnya ialah ringkasan teks. Sahkan sebarang struktur yang diproses mesin dalam aplikasi, sambil memastikan ringkasan bertulis boleh dibaca oleh khalayak sasarannya. Simpan ringkasan bersama identiti sumber dan arahan yang menentukan fokus, bahasa serta panjangnya.

Keupayaan

  • Ringkasan abstraktif yang menulis semula dan memadatkan bahan yang dibekalkan.
  • Fokus, bahasa, panjang dan susun atur yang dipandu oleh arahan.
  • Konfigurasi pensampelan tetap yang ditala untuk output yang setia kepada sumber.
  • Input teks, imej dan fail dengan output teks.
  • Konteks 1,000,000 token dan had pelengkapan 4,000 token yang diterbitkan.

Kes penggunaan

  • Ringkasan semakan dokumen — Dokumen dan penemuan yang perlu dikekalkan oleh pembaca. Hasil: Ringkasan ringkas beridentiti dengan fakta utama dikekalkan.
  • Ringkasan transkrip — Transkrip yang berfokus pada keputusan, tanggungjawab atau soalan terbuka. Hasil: Teks lebih pendek yang memisahkan kategori tersebut.
  • Prapemprosesan bahan yang diperoleh semula — Kandungan yang diperoleh semula dan soalan pada peringkat seterusnya. Hasil: Petikan bukti padat untuk penaakulan kemudian.
  • Ringkasan koleksi — Dokumen bernama dengan arahan ringkasan yang dikongsi. Hasil: Ringkasan bagi setiap dokumen yang boleh dibandingkan.

Had

  • Konteks — Tetingkap konteks yang diterbitkan: 1,000,000 token.
  • Jawapan — Had pelengkapan yang diterbitkan: 4,000 token.
  • Kawalan gaya — Kawal fokus, bahasa, panjang dan format melalui arahan; pensampelan adalah tetap.
  • Kontrak output — Output yang diterbitkan ialah teks; panggilan fungsi dan JSON yang dikuatkuasakan mengikut skema tidak disenaraikan.

Tersedia di Ailoot · input & kaedah

Ailoot Ultra · Anthropic Messages POST /v1/messages
Input
text
Output
json, sse
Format output
JSON atau SSE
MedanJenisKeperluanNilai & hadLalai
MedanmodelJenisstringKeperluanDiperlukanNilai & had
scaledown/summarize
Lalai—
MedanmessagesJenismessage[]KeperluanDiperlukanNilai & hadLalai—
Medanmessages[].roleJenisstringKeperluanDiperlukanNilai & had
user, assistant
Lalai—
Medanmessages[].contentJenisstringKeperluanDiperlukanNilai & hadLalai—
Medanmax_tokensJenisintegerKeperluanDiperlukanNilai & hadLalai—
MedanstreamJenisbooleanKeperluanPilihanNilai & hadLalaifalse
Gabungan bahan input

Teks · Teks UTF-8

rentetan messages[].content

Parameter kaedah dan kitar hayat
ParameterKontrak
Parametercontent_typeKontrakapplication/json
ParameterrequiredKontrakmodel, messages, max_tokens
Parameteroptional_controlsKontrakstream
Parametermaterial_typesKontraktext
Parametertext_file_materialKontrakBaca dokumen UTF-8 sebenar dan letakkan teksnya dalam rentetan input atau kandungan mesej yang ditunjukkan.

Kitar hayat: synchronous_or_streamed

Pelan harga

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

Mod pantas
Tidak dinyatakan Apabila mod pantas dipilih
Mod flex
Tidak dinyatakan Apabila mod flex dipilih
Usaha penaakulan maksimum
Tidak dinyatakan Apabila usaha penaakulan maksimum menggunakan pelarasan default

Kadar Ailoot

Harga mengikut konfigurasi

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

KonfigurasiJadual kadarToken konteks, melebihiToken konteks, sehingga dan termasukCaj
KonfigurasiKadar asas tokenJadual kadarKadar asasToken konteks, melebihi—Token konteks, sehingga dan termasukTiada had atasCaj
Input · Token input $0.0001 / 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
KonfigurasiTahap panjang permintaan 1Jadual kadar—Token konteks, melebihi0Token konteks, sehingga dan termasukTiada had atasCaj
Input · Token input $0.0001 / 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 · Anthropic Messages

{\n  "model": "scaledown/summarize",\n  "max_tokens": 128,\n  "messages": [\n    {\n      "role": "user",\n      "content": "Summarize the incident report."\n    }\n  ],\n  "stream": false\n}

Terima dan simpan hasil

Ailoot Ultra · Anthropic Messages

JSON atau SSE

Simpan semua hasil yang selesai

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

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

Jika respons asal perlu disemak

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

Medan respons
MedanJenis
MedanidJenisstring
MedanmodelJenisstring
Medancontent[]Jenistext|thinking|tool_use|other content block
Medanstop_reasonJenisstring|null
MedanusageJenisobject
Ralat dan langkah seterusnya
ResponsSyaratLangkah seterusnya
Respons400 · invalid_request_errorSyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sahLangkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu.

Alias

Alias model

Ailoot Ultra scaledown/summarize

Alias laluan kaedah

/chat/completions

ID pemanggil berkaitan

scaledown/summarize

", "method_identity": { "effective_request_model_id": "scaledown/summarize", "fmt": "messages", "http": "POST", "path": "/v1/messages", "request_model_id": "scaledown/summarize", "route_label": "Ultra" }, "method_key": "Ultra|messages|/v1/messages|scaledown%2Fsummarize", "ordinal": 1, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "authentication": { "api_key_source": "AILOOT_API_KEY", "headers": [ "Authorization: Bearer", "x-api-key", "anthropic-version" ], "version_example": "2023-06-01" }, "errors": [ { "code": null, "condition": "Medan wajib, perwakilan bahan atau nilai parameter tidak sah", "http_status": 400, "recovery": "Betulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu.", "type": "invalid_request_error" } ], "example_body": { "max_tokens": 128, "messages": [ { "content": "Summarize the incident report.", "role": "user" } ], "model": "scaledown/summarize", "stream": false }, "lifecycle": { "create": { "http": "POST", "path": "/v1/messages" }, "job_read": null, "mode": "synchronous_or_streamed", "unknown": "Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan." }, "material_combinations": [ { "mode": "text", "representation": "rentetan messages[].content", "required_material": "Teks UTF-8" } ], "operation_modes": [ "synchronous_json", "streamed_SSE" ], "outputs": { "all_results": "Kekalkan semua blok kandungan, tandatangan penaakulan dan ID penggunaan alat sebenar. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan output.", "family": "protocol", "fields": [ { "description": null, "name": "id", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "content[]", "type": "text|thinking|tool_use|other content block" }, { "description": null, "name": "stop_reason", "type": "string|null" }, { "description": null, "name": "usage", "type": "object" } ], "format": "JSON atau SSE" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "scaledown/summarize" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "messages", "required": true, "type": "message[]" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "user", "assistant" ], "enum_known": true, "name": "messages[].role", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "messages[].content", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "max_tokens", "required": true, "type": "integer" }, { "availability": "source_interface", "default": false, "default_known": true, "enum": null, "enum_known": false, "name": "stream", "required": false, "type": "boolean" } ], "profile_binding": "Documented current stock Messages bridge; optional model capabilities are separate from this minimal text request.", "request_schema": { "additionalProperties": false, "properties": { "max_tokens": { "minimum": 1, "type": "integer" }, "messages": { "items": { "additionalProperties": false, "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "oneOf": [ { "properties": { "text": { "type": "string" }, "type": { "const": "text" } }, "required": [ "type", "text" ], "type": "object" }, { "properties": { "source": { "oneOf": [ { "properties": { "type": { "const": "url" }, "url": { "type": "string" } }, "required": [ "type", "url" ], "type": "object" }, { "properties": { "data": { "type": "string" }, "media_type": { "type": "string" }, "type": { "const": "base64" } }, "required": [ "type", "media_type", "data" ], "type": "object" } ] }, "type": { "const": "image" } }, "required": [ "type", "source" ], "type": "object" } ] }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "model": { "enum": [ "scaledown/summarize" ], "type": "string" }, "stream": { "default": false, "type": "boolean" } }, "required": [ "model", "messages", "max_tokens" ], "type": "object" }, "schema_template": { "max_tokens": 128, "messages": [ { "content": "Summarize the incident report.", "role": "user" } ], "model": "scaledown/summarize", "stream": false }, "unsupported": [ "No query API key.", "Hosted/server-side tools and model-specific optional controls are not part of this minimal family example." ] }, "input": { "content_type": "application/json", "material_types": [ "text" ], "optional_controls": [ "stream" ], "required": [ "model", "messages", "max_tokens" ], "text_file_material": "Baca dokumen UTF-8 sebenar dan letakkan teksnya dalam rentetan input atau kandungan mesej yang ditunjukkan." }, "lifecycle": { "create": { "http": "POST", "path": "/v1/messages" }, "job_read": null, "mode": "synchronous_or_streamed", "unknown": "Keep request/response IDs and headers. No generic text job retrieval URL is supplied." }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/messages" }, "output": { "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.", "family": "protocol", "format": "JSON or SSE" } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Kadar asas token", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Tahap panjang permintaan 1", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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": "{\n \"model\": \"scaledown/summarize\",\n \"max_tokens\": 128,\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Summarize the incident report.\"\n }\n ],\n \"stream\": false\n}", "label": "Complete minimal JSON body", "language": "json" }, { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'scaledown/summarize', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n", "label": "curl · use your UTF-8 document", "language": "bash" }, { "code": "import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'scaledown/summarize', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n", "label": "Python · save the complete result", "language": "python" } ], "family": "anthropic", "fast_multiplier": null, "flex_multiplier": null, "fmt": "messages", "http": "POST", "in": 0.1, "input": [ "text" ], "label": "Anthropic Messages", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": 0, "output": [ "json", "sse" ], "path": "/v1/messages", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "token", "image_input_price": null, "image_output_price": null, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Request-length tier 1", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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": "scaledown/summarize", "route_label": "Ultra", "status_reads": [], "tiers": [ { "cache_read": null, "cache_read_multiplier": null, "cache_write": null, "cache_write_1h": null, "cache_write_multiplier": null, "created_at": "0001-01-01T00:00:00Z", "in": 0.1, "input_multiplier": null, "max": null, "max_tokens": null, "min": 0, "min_tokens": 0, "out": 0, "output_multiplier": null, "per_request_price": null, "sort_order": 0, "tier_label": "", "updated_at": "0001-01-01T00:00:00Z" } ], "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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": "scaledown/summarize", "nativeProvenance": { "input_facts_canonical_sha256": "aa7fb72aeb13fe3506201b93b3b1f456965274ca37d0761b7a13e24b684cb263", "input_html_sha256": "a84d58c58331c521cc2e1bec5429b091c910b764eaa2fbd21adf4715d7824fe4", "private_audit_sha256": "3a6f45c3a445906c6899da6a371652784e197dda0a9ab3a8bc6eb8b6b34fcbc8", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/ms/scaledown-summarize/", "description": "Summarize menulis semula teks dan dokumen yang panjang menjadi ringkasan yang lancar dan setia kepada sumber. Tetapkan fokus, bahasa, panjang dan format melalui arahan, kemudian gunakan hasil untuk semakan dokumen, ringkasan transkrip atau konteks perolehan semula yang lebih pendek. Tetingkap yang diterbitkan ialah 1,000,000 token, dengan had pelengkapan 4,000 token.", "locale": "ms", "md_url": "https://ailoot.ai/models/ms/scaledown-summarize/index.md", "title": "ScaleDown: Summarize — Ailoot", "url": "https://ailoot.ai/models/ms/scaledown-summarize/" }, "rawModel": { "about": "Summarize ialah model peringkasan abstraktif ScaleDown. Ia memadatkan teks dan dokumen yang dibekalkan menjadi tulisan semula yang lancar, bukannya memilih beberapa ayat asal secara verbatim. Kegunaan yang diterbitkan termasuk semakan dokumen, ringkasan transkrip dan memendekkan bahan yang diperoleh semula sebelum diproses oleh model lain.\n\n### Takrifkan perkara yang mesti dikekalkan dalam ringkasan\n\nBerikan tugas itu fokus dan pembaca sasaran. Ringkasan mesyuarat boleh mengekalkan keputusan, tanggungjawab dan soalan yang masih terbuka. Semakan dokumen boleh mengekalkan dakwaan utama dan bukti sokongan. Aliran kerja perolehan semula boleh mengekalkan fakta yang penting untuk soalan yang akan dijawab oleh model seterusnya.\n\nNyatakan bahasa, panjang dan susun atur yang dikehendaki dalam arahan kandungan. Model yang diterbitkan menggunakan arahan dalam prompt sistem untuk pilihan tersebut, manakala konfigurasi pensampelannya tetap untuk menghasilkan output yang setia kepada sumber. Oleh itu, ringkasan untuk seseorang dan petikan ringkas untuk model lain boleh menggunakan susun atur berbeza tanpa menjadikan variasi pensampelan sebagai kawalan utama.\n\n### Tulisan semula dengan fakta yang boleh dijejaki\n\nSimpan nama dokumen dan sempadan bahagian yang penting bersama sumber. Minta ringkasan mengekalkan nama, nombor, keputusan yang dinyatakan dan sebarang percanggahan pendapat yang mempengaruhi tafsiran. Untuk transkrip, bezakan cadangan daripada keputusan dan soalan yang belum diselesaikan daripada tindakan yang telah ditugaskan.\n\nSelepas penjanaan, bandingkan teks yang dipadatkan dengan bahan asal. Semak sama ada sesuatu ayat mengubah tahap kepastian dakwaan, menggugurkan syarat atau menggabungkan pernyataan milik pembicara atau bahagian yang berbeza. Tujuan hasil yang lebih pendek ialah memudahkan bukti dibaca sambil mengekalkan maknanya.\n\n### Dokumen, imej dan konteks perolehan semula\n\nJulat input yang diterbitkan merangkumi teks, imej dan fail seperti PDF, dan model mengembalikan teks. Bekalkan bahan yang boleh dibaca dan takrifkan sama ada tugas melibatkan seluruh dokumen atau bahagian yang dipilih. Koleksi mendapat manfaat daripada soalan ringkasan yang konsisten serta pengecam dokumen yang disimpan bersama setiap hasil.\n\nUntuk prapemprosesan perolehan semula, pendekkan kandungan berdasarkan soalan khusus yang perlu ditangani oleh penaakulan pada peringkat seterusnya. Kekalkan petikan atau fakta yang menyokong jawapan, bukannya menghasilkan gambaran umum sumber. Pastikan bahan asal yang diperoleh semula tetap tersedia supaya hasil berikutnya masih boleh disemak terhadapnya.\n\n### Rancang panjang output\n\nTetingkap konteks yang diterbitkan ialah 1,000,000 token dan had pelengkapannya ialah 4,000 token. Tetapkan panjang ringkasan yang sesuai dengan artifak yang dimaksudkan. Jika koleksi besar memerlukan butiran yang banyak, susunkannya menjadi dokumen atau bahagian berpengecam dan simpan hasil berasingan bagi setiap satunya sebelum mengarang ringkasan peringkat koleksi.\n\nHasilnya ialah ringkasan teks. Sahkan sebarang struktur yang diproses mesin dalam aplikasi, sambil memastikan ringkasan bertulis boleh dibaca oleh khalayak sasarannya. Simpan ringkasan bersama identiti sumber dan arahan yang menentukan fokus, bahasa serta panjangnya.\n\n### Keupayaan\n\n- Ringkasan abstraktif yang menulis semula dan memadatkan bahan yang dibekalkan.\n- Fokus, bahasa, panjang dan susun atur yang dipandu oleh arahan.\n- Konfigurasi pensampelan tetap yang ditala untuk output yang setia kepada sumber.\n- Input teks, imej dan fail dengan output teks.\n- Konteks 1,000,000 token dan had pelengkapan 4,000 token yang diterbitkan.\n\n### Kes penggunaan\n\n- **Ringkasan semakan dokumen** — Dokumen dan penemuan yang perlu dikekalkan oleh pembaca. Hasil: Ringkasan ringkas beridentiti dengan fakta utama dikekalkan.\n- **Ringkasan transkrip** — Transkrip yang berfokus pada keputusan, tanggungjawab atau soalan terbuka. Hasil: Teks lebih pendek yang memisahkan kategori tersebut.\n- **Prapemprosesan bahan yang diperoleh semula** — Kandungan yang diperoleh semula dan soalan pada peringkat seterusnya. Hasil: Petikan bukti padat untuk penaakulan kemudian.\n- **Ringkasan koleksi** — Dokumen bernama dengan arahan ringkasan yang dikongsi. Hasil: Ringkasan bagi setiap dokumen yang boleh dibandingkan.\n\n### Had\n\n- **Konteks** — Tetingkap konteks yang diterbitkan: 1,000,000 token.\n- **Jawapan** — Had pelengkapan yang diterbitkan: 4,000 token.\n- **Kawalan gaya** — Kawal fokus, bahasa, panjang dan format melalui arahan; pensampelan adalah tetap.\n- **Kontrak output** — Output yang diterbitkan ialah teks; panggilan fungsi dan JSON yang dikuatkuasakan mengikut skema tidak disenaraikan.\n", "alias_of": null, "aliases": [], "author": "ScaleDown", "available": null, "canonical_model": "scaledown/summarize", "capabilities": { "context_length": 1000000, "manufacturer_input": [ "text", "image", "file" ], "manufacturer_output": [ "text" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ], "summary": "Maklumat lengkap tentang harga konfigurasi terdapat dalam butiran." } ], "ctx": null, "entity_type": "model", "formats": [ "chat", "messages" ], "id": "scaledown/summarize", "input": [ "text" ], "kind": "text", "max_out": null, "methods": [ { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "errors": [ { "code": null, "condition": "Medan wajib, perwakilan bahan atau nilai parameter tidak sah", "http_status": 400, "recovery": "Betulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu.", "type": "invalid_request_error" } ], "hints": [ "Model context is not an output cap.", "Send the conversation as text messages. Stream must be a boolean; omitted stream defaults to false." ], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/chat/completions" }, "job_read": null, "mode": "synchronous_or_streamed", "unknown": "Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan." }, "material_combinations": [ { "mode": "text", "representation": "messages[].content", "required_material": "Teks UTF8" } ], "operation_modes": [ "conversation" ], "outputs": { "all_results": "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.", "family": "text", "fields": [ { "description": null, "name": "choices[].index", "type": "integer" }, { "description": null, "name": "choices[].message.content", "type": "string|null" }, { "description": null, "name": "choices[].message.tool_calls", "type": "tool_call[]" }, { "description": null, "name": "choices[].message.reasoning_content", "type": "string" }, { "description": null, "name": "choices[].message.reasoning_details", "type": "object|array" }, { "description": null, "name": "choices[].finish_reason", "type": "string|null" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json atau SSE" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "scaledown/summarize" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "messages", "required": true, "type": "message[]" }, { "availability": "model_dependent", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "messages[].role", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "messages[].content", "required": false, "type": "string", "when": "Perbualan teks" }, { "availability": "source_interface", "default": false, "default_known": true, "enum": null, "enum_known": false, "name": "stream", "required": false, "type": "boolean" } ], "profile_binding": "Text conversation at the exact model ID and method path.", "unsupported": [ "additional models/models list", "plugins", "route", "hosted tools; ordinary client function tools remain separate", "non-text output modalities", "provider.options overrides", "one-hour prompt-cache TTL" ] }, "hints": [ "Hantar ID model yang tepat bersama messages.", "Panjang konteks bukan had output.", "Fail teks boleh membekalkan teks literal; input imej/audio/objek fail memerlukan pengikatan tepat." ], "input": { "content_type": "application/json", "control_scope": "Perbualan teks; stream ialah nilai boolean dengan false sebagai lalai.", "file_material": "dokumen UTF-8 sebenar dimasukkan sebagai teks literal; ID fail tidak diandaikan", "hosted_operations": false, "material_types": [ "text" ], "messages": "tatasusunan mesej dengan struktur role/content", "multimodal_input_binding": null, "optional_controls": [ "stream" ], "output_modalities": [ "text" ], "required": [ "model", "messages" ] }, "lifecycle": { "mode": "synchronous_or_streamed", "unknown": "preserve original request id; no generic chat job retrieval path" }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/chat/completions" }, "method_aliases": [ "/chat/completions" ], "operation_modes": [ "text_chat" ], "output": { "content": "choices[].message.content or stream delta", "family": "text", "format": "json or supported SSE", "tool_calls": "retain actual returned function calls" } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Kadar asas token", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Tahap panjang permintaan 1", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\":\"scaledown/summarize\",\"messages\":[{\"role\":\"user\",\"content\":\"hello\"}],\"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\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"choices\",[]):\n if x.get(\"message\",{}).get(\"content\"): print(x[\"message\"][\"content\"])\nPY_RESULT\n", "label": "curl · retained exact creation", "language": "bash" }, { "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.chat.completions.create(model=\"scaledown/summarize\", messages=[{\"role\":\"user\",\"content\":\"hello\"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n 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\n file = Path(stem + \"-\" + label + \".\" + ext)\n file.write_bytes(raw)\n print(\"Saved\", file)\n for index, block in enumerate(data.get(\"content\") or []):\n print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get(\"choices\") or []:\n print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n for index, item in enumerate(data.get(\"output\") or []):\n print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n for ci, candidate in enumerate(data.get(\"candidates\") or []):\n for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n if blob and blob.get(\"data\"):\n mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(result.to_dict(mode=\"json\"))\n", "label": "Python SDK · all choices", "language": "python" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "chat", "hints": [ "Send exact model ID with messages.", "Context length is not an output cap.", "A text file may supply literal text; image/audio/file-object inputs need exact binding." ], "http": "POST", "in": 0.1, "input": [ "text" ], "label": "OpenAI Chat", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [ "/chat/completions" ], "out": 0, "output": [ "text" ], "path": "/v1/chat/completions", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "token", "image_input_price": null, "image_output_price": null, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Request-length tier 1", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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": "scaledown/summarize", "route_label": "Ultra", "status_reads": [], "tiers": [ { "cache_read": null, "cache_read_multiplier": null, "cache_write": null, "cache_write_1h": null, "cache_write_multiplier": null, "created_at": "0001-01-01T00:00:00Z", "in": 0.1, "input_multiplier": null, "interval_boundary": "min_exclusive_max_inclusive", "max": null, "max_tokens": null, "min": 0, "min_tokens": 0, "null_rate_policy": "unknown or inherited; never zero", "out": 0, "output_multiplier": null, "per_request_price": null, "sort_order": 0, "tier_label": "", "updated_at": "0001-01-01T00:00:00Z" } ], "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] }, { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "authentication": { "api_key_source": "AILOOT_API_KEY", "headers": [ "Authorization: Bearer", "x-api-key", "anthropic-version" ], "version_example": "2023-06-01" }, "errors": [ { "code": null, "condition": "Medan wajib, perwakilan bahan atau nilai parameter tidak sah", "http_status": 400, "recovery": "Betulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu.", "type": "invalid_request_error" } ], "example_body": { "max_tokens": 128, "messages": [ { "content": "Summarize the incident report.", "role": "user" } ], "model": "scaledown/summarize", "stream": false }, "lifecycle": { "create": { "http": "POST", "path": "/v1/messages" }, "job_read": null, "mode": "synchronous_or_streamed", "unknown": "Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan." }, "material_combinations": [ { "mode": "text", "representation": "rentetan messages[].content", "required_material": "Teks UTF-8" } ], "operation_modes": [ "synchronous_json", "streamed_SSE" ], "outputs": { "all_results": "Kekalkan semua blok kandungan, tandatangan penaakulan dan ID penggunaan alat sebenar. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan output.", "family": "protocol", "fields": [ { "description": null, "name": "id", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "content[]", "type": "text|thinking|tool_use|other content block" }, { "description": null, "name": "stop_reason", "type": "string|null" }, { "description": null, "name": "usage", "type": "object" } ], "format": "JSON atau SSE" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "scaledown/summarize" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "messages", "required": true, "type": "message[]" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "user", "assistant" ], "enum_known": true, "name": "messages[].role", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "messages[].content", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "max_tokens", "required": true, "type": "integer" }, { "availability": "source_interface", "default": false, "default_known": true, "enum": null, "enum_known": false, "name": "stream", "required": false, "type": "boolean" } ], "profile_binding": "Documented current stock Messages bridge; optional model capabilities are separate from this minimal text request.", "request_schema": { "additionalProperties": false, "properties": { "max_tokens": { "minimum": 1, "type": "integer" }, "messages": { "items": { "additionalProperties": false, "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "oneOf": [ { "properties": { "text": { "type": "string" }, "type": { "const": "text" } }, "required": [ "type", "text" ], "type": "object" }, { "properties": { "source": { "oneOf": [ { "properties": { "type": { "const": "url" }, "url": { "type": "string" } }, "required": [ "type", "url" ], "type": "object" }, { "properties": { "data": { "type": "string" }, "media_type": { "type": "string" }, "type": { "const": "base64" } }, "required": [ "type", "media_type", "data" ], "type": "object" } ] }, "type": { "const": "image" } }, "required": [ "type", "source" ], "type": "object" } ] }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "model": { "enum": [ "scaledown/summarize" ], "type": "string" }, "stream": { "default": false, "type": "boolean" } }, "required": [ "model", "messages", "max_tokens" ], "type": "object" }, "schema_template": { "max_tokens": 128, "messages": [ { "content": "Summarize the incident report.", "role": "user" } ], "model": "scaledown/summarize", "stream": false }, "unsupported": [ "No query API key.", "Hosted/server-side tools and model-specific optional controls are not part of this minimal family example." ] }, "input": { "content_type": "application/json", "material_types": [ "text" ], "optional_controls": [ "stream" ], "required": [ "model", "messages", "max_tokens" ], "text_file_material": "Baca dokumen UTF-8 sebenar dan letakkan teksnya dalam rentetan input atau kandungan mesej yang ditunjukkan." }, "lifecycle": { "create": { "http": "POST", "path": "/v1/messages" }, "job_read": null, "mode": "synchronous_or_streamed", "unknown": "Keep request/response IDs and headers. No generic text job retrieval URL is supplied." }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/messages" }, "output": { "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.", "family": "protocol", "format": "JSON or SSE" } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Kadar asas token", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Tahap panjang permintaan 1", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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": "{\n \"model\": \"scaledown/summarize\",\n \"max_tokens\": 128,\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Summarize the incident report.\"\n }\n ],\n \"stream\": false\n}", "label": "Complete minimal JSON body", "language": "json" }, { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'scaledown/summarize', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n", "label": "curl · use your UTF-8 document", "language": "bash" }, { "code": "import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'scaledown/summarize', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n", "label": "Python · save the complete result", "language": "python" } ], "family": "anthropic", "fast_multiplier": null, "flex_multiplier": null, "fmt": "messages", "http": "POST", "in": 0.1, "input": [ "text" ], "label": "Anthropic Messages", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": 0, "output": [ "json", "sse" ], "path": "/v1/messages", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "token", "image_input_price": null, "image_output_price": null, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Request-length tier 1", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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": "scaledown/summarize", "route_label": "Ultra", "status_reads": [], "tiers": [ { "cache_read": null, "cache_read_multiplier": null, "cache_write": null, "cache_write_1h": null, "cache_write_multiplier": null, "created_at": "0001-01-01T00:00:00Z", "in": 0.1, "input_multiplier": null, "max": null, "max_tokens": null, "min": 0, "min_tokens": 0, "out": 0, "output_multiplier": null, "per_request_price": null, "sort_order": 0, "tier_label": "", "updated_at": "0001-01-01T00:00:00Z" } ], "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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": "scaledown/summarize", "request_model_id": "scaledown/summarize", "route_label": "Ultra" } ], "name": "ScaleDown: Summarize", "price": { "in": 0.1, "in_label": null, "out": 0, "out_label": null, "scope_label": "Token rates", "sort_in": 0.1, "sort_out": 0, "varies": true }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "OpenAI Chat · Base token rates", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "OpenAI Chat · Request-length tier 1", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] }, { "dimensions": { "regime": "base" }, "label": "Anthropic Messages · Base token rates", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] }, { "dimensions": { "max_context_tokens_inclusive": null, "min_context_tokens_exclusive": 0 }, "label": "Anthropic Messages · Request-length tier 1", "units": [ { "amount": "0.0001000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.0000001", "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" } ] } ], "public_id": "scaledown/summarize", "short": "Summarize menulis semula teks dan dokumen yang panjang menjadi ringkasan yang lancar dan setia kepada sumber. Tetapkan fokus, bahasa, panjang dan format melalui arahan, kemudian gunakan hasil untuk semakan dokumen, ringkasan transkrip atau konteks perolehan semula yang lebih pendek. Tetingkap yang diterbitkan ialah 1,000,000 token, dengan had pelengkapan 4,000 token." }, "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 }, { "contract_json_pointer": "/methods/1/rawMethod/contract", "html_json_pointer": "/methods/1/html", "method_ordinal": 1 } ], "role": "current-semantic-reference" }, "raw_input": { "examples_role": "historical-input-not-current-ready-examples", "json_pointers": [ "/rawModel", "/methods/0/rawMethod", "/methods/1/rawMethod" ], "role": "historical-owner-input" }, "schema": "ailoot-native-model-representations-v1" }, "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "Summarize menulis semula teks dan dokumen yang panjang menjadi ringkasan yang lancar dan setia kepada sumber. Tetapkan fokus, bahasa, panjang dan format melalui arahan, kemudian gunakan hasil untuk semakan dokumen, ringkasan transkrip atau konteks perolehan semula yang lebih pendek. Tetingkap yang diterbitkan ialah 1,000,000 token, dengan had pelengkapan 4,000 token.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "215ee6717a4b731e17950ca07a40bfdfa66144cec9a0dcf5a0256ab2f1f07ff3", "renderer_sha256": "1dab5ba62521e9568c8b7c82005622cabbf330a075df7cce1f83274a04009460" }, "sourceRevision": "d5740c6bc0abd5c7b8ca3218fda14af853c0c0c2259658ac986e450513a8bcba" }