{ "aboutHtml": "

ERNIE 4.5 0.3B menerima perbualan teks melalui Ailoot Ultra. ID model yang tepat ialah baidu/ernie-4.5-0.3b. Letakkan bahan sumber terus dalam mesej anda dan terangkan hasil yang diperlukan. Profil teks ini sesuai untuk tugasan seperti mengubah nota pelanggan menjadi balasan, memadatkan petikan dokumen atau mengekstrak set fakta tertentu ke dalam susun atur yang dipersetujui.

Permintaan yang berguna menggabungkan bahan, tugasan dan keperluan jawapan. Untuk balasan sokongan, bekalkan mesej pelanggan dan teks dasar yang mesti dipatuhi oleh balasan. Untuk ringkasan, nyatakan pembaca sasaran dan minta keputusan, persoalan yang belum selesai serta tindakan susulan. Untuk pengekstrakan, tentukan nama medan dan beritahu model cara mewakili fakta yang tiada dalam sumber. Arahan ini menghasilkan jawapan yang boleh disemak dengan bahan yang anda bekalkan.

Dengan Chat Completions, hantar POST /v1/chat/completions bersama model dan tatasusunan messages yang tidak kosong. Setiap mesej membekalkan role dan content dalam bentuk teks. Sertakan giliran perbualan terdahulu yang berkaitan apabila jawapan bergantung pada perbualan. Untuk mengolah dokumen, baca teks sebenar dokumen itu dan letakkan kandungan yang berkaitan dalam mesej; nama fail sahaja tidak membekalkan dokumen tersebut.

Dengan Messages, hantar POST /v1/messages bersama model, messages dan max_tokens. Gunakan giliran user dan assistant, dengan arahan system berasingan sebagai pilihan. Kandungan boleh berupa rentetan teks atau blok teks. max_tokens ialah integer sekurang-kurangnya 1. Profil model yang diterbitkan menyenaraikan had pelengkapan 8,000 token dan konteks 120,000 token; sediakan ruang untuk jawapan yang diminta semasa menyediakan perbualan. Saiz konteks tidak bermakna jawapan boleh mengandungi 120,000 token.

Kedua-dua antara muka menyediakan kawalan boolean stream, dengan nilai lalai false. Untuk jawapan JSON yang lengkap, simpan setiap medan hasil dan rekod usage yang dikembalikan. Untuk penghantaran berstrim, kumpulkan peristiwa dan gabungkan semua kandungan jawapan sebelum menganggap balasan lengkap. Chat Completions meletakkan balasan biasa dalam choices[].message.content; Messages mengembalikan blok kandungan bersama stop_reason dan usage. Simpan identiti permintaan asal dan apa-apa balasan yang diterima jika sambungan terputus sebelum selesai, supaya balasan yang tidak lengkap boleh disiasat tanpa menghantar semula permintaan yang sama secara membuta tuli.

", "aboutText": "ERNIE 4.5 0.3B menerima perbualan teks melalui Ailoot Ultra. ID model yang tepat ialah baidu/ernie-4.5-0.3b. Letakkan bahan sumber terus dalam mesej anda dan terangkan hasil yang diperlukan. Profil teks ini sesuai untuk tugasan seperti mengubah nota pelanggan menjadi balasan, memadatkan petikan dokumen atau mengekstrak set fakta tertentu ke dalam susun atur yang dipersetujui.\n\nPermintaan yang berguna menggabungkan bahan, tugasan dan keperluan jawapan. Untuk balasan sokongan, bekalkan mesej pelanggan dan teks dasar yang mesti dipatuhi oleh balasan. Untuk ringkasan, nyatakan pembaca sasaran dan minta keputusan, persoalan yang belum selesai serta tindakan susulan. Untuk pengekstrakan, tentukan nama medan dan beritahu model cara mewakili fakta yang tiada dalam sumber. Arahan ini menghasilkan jawapan yang boleh disemak dengan bahan yang anda bekalkan.\n\nDengan Chat Completions, hantar POST /v1/chat/completions bersama model dan tatasusunan messages yang tidak kosong. Setiap mesej membekalkan role dan content dalam bentuk teks. Sertakan giliran perbualan terdahulu yang berkaitan apabila jawapan bergantung pada perbualan. Untuk mengolah dokumen, baca teks sebenar dokumen itu dan letakkan kandungan yang berkaitan dalam mesej; nama fail sahaja tidak membekalkan dokumen tersebut.\n\nDengan Messages, hantar POST /v1/messages bersama model, messages dan max_tokens. Gunakan giliran user dan assistant, dengan arahan system berasingan sebagai pilihan. Kandungan boleh berupa rentetan teks atau blok teks. max_tokens ialah integer sekurang-kurangnya 1. Profil model yang diterbitkan menyenaraikan had pelengkapan 8,000 token dan konteks 120,000 token; sediakan ruang untuk jawapan yang diminta semasa menyediakan perbualan. Saiz konteks tidak bermakna jawapan boleh mengandungi 120,000 token.\n\nKedua-dua antara muka menyediakan kawalan boolean stream, dengan nilai lalai false. Untuk jawapan JSON yang lengkap, simpan setiap medan hasil dan rekod usage yang dikembalikan. Untuk penghantaran berstrim, kumpulkan peristiwa dan gabungkan semua kandungan jawapan sebelum menganggap balasan lengkap. Chat Completions meletakkan balasan biasa dalam choices[].message.content; Messages mengembalikan blok kandungan bersama stop_reason dan usage. Simpan identiti permintaan asal dan apa-apa balasan yang diterima jika sambungan terputus sebelum selesai, supaya balasan yang tidak lengkap boleh disiasat tanpa menghantar semula permintaan yang sama secara membuta tuli.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "50a7838ec3630acb2ee6328a027f4e9bf7e17594e4ec89618e38e7261d76bc87", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "ms", "methods": [ { "html": "
•

ERNIE 4.5 0.3B

Baidu /baidu/ernie-4.5-0.3b

Pengenalan

ERNIE 4.5 0.3B ialah model perbualan teks dalam keluarga sumber terbuka ERNIE 4.5. Gunakan ID tepat baidu/ernie-4.5-0.3b melalui Chat Completions atau Messages untuk mengolah teks yang dibekalkan: mendraf balasan, meringkaskan nota, mengekstrak maklumat yang dinyatakan atau menerangkan petikan pendek. Profil yang diterbitkan menyenaraikan konteks 120,000 token dan had pelengkapan 8,000 token; kedua-dua nilai menerangkan had yang berbeza.

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.

ERNIE 4.5 0.3B menerima perbualan teks melalui Ailoot Ultra. ID model yang tepat ialah baidu/ernie-4.5-0.3b. Letakkan bahan sumber terus dalam mesej anda dan terangkan hasil yang diperlukan. Profil teks ini sesuai untuk tugasan seperti mengubah nota pelanggan menjadi balasan, memadatkan petikan dokumen atau mengekstrak set fakta tertentu ke dalam susun atur yang dipersetujui.

Permintaan yang berguna menggabungkan bahan, tugasan dan keperluan jawapan. Untuk balasan sokongan, bekalkan mesej pelanggan dan teks dasar yang mesti dipatuhi oleh balasan. Untuk ringkasan, nyatakan pembaca sasaran dan minta keputusan, persoalan yang belum selesai serta tindakan susulan. Untuk pengekstrakan, tentukan nama medan dan beritahu model cara mewakili fakta yang tiada dalam sumber. Arahan ini menghasilkan jawapan yang boleh disemak dengan bahan yang anda bekalkan.

Dengan Chat Completions, hantar POST /v1/chat/completions bersama model dan tatasusunan messages yang tidak kosong. Setiap mesej membekalkan role dan content dalam bentuk teks. Sertakan giliran perbualan terdahulu yang berkaitan apabila jawapan bergantung pada perbualan. Untuk mengolah dokumen, baca teks sebenar dokumen itu dan letakkan kandungan yang berkaitan dalam mesej; nama fail sahaja tidak membekalkan dokumen tersebut.

Dengan Messages, hantar POST /v1/messages bersama model, messages dan max_tokens. Gunakan giliran user dan assistant, dengan arahan system berasingan sebagai pilihan. Kandungan boleh berupa rentetan teks atau blok teks. max_tokens ialah integer sekurang-kurangnya 1. Profil model yang diterbitkan menyenaraikan had pelengkapan 8,000 token dan konteks 120,000 token; sediakan ruang untuk jawapan yang diminta semasa menyediakan perbualan. Saiz konteks tidak bermakna jawapan boleh mengandungi 120,000 token.

Kedua-dua antara muka menyediakan kawalan boolean stream, dengan nilai lalai false. Untuk jawapan JSON yang lengkap, simpan setiap medan hasil dan rekod usage yang dikembalikan. Untuk penghantaran berstrim, kumpulkan peristiwa dan gabungkan semua kandungan jawapan sebelum menganggap balasan lengkap. Chat Completions meletakkan balasan biasa dalam choices[].message.content; Messages mengembalikan blok kandungan bersama stop_reason dan usage. Simpan identiti permintaan asal dan apa-apa balasan yang diterima jika sambungan terputus sebelum selesai, supaya balasan yang tidak lengkap boleh disiasat tanpa menghantar semula permintaan yang sama secara membuta tuli.

Tersedia di Ailoot · input & kaedah

Ailoot Ultra · Chat Completions POST /v1/chat/completions
Input
text
Output
text
Konteks
120,000 tokens
Output maksimum
8,000 tokens
Format output
JSON or supported SSE
MedanJenisKeperluanNilai & hadLalai
MedanmodelJenisstringKeperluanDiperlukanNilai & had
baidu/ernie-4.5-0.3b
Lalai—
MedanmessagesJenisarrayKeperluanDiperlukanNilai & hadLalai—
MedanstreamJenisbooleanKeperluanPilihanNilai & hadLalaifalse
Medanmax_tokensJenisintegerKeperluanPilihanNilai & had
Minimum: 1
Lalai—
Medanmax_completion_tokensJenisintegerKeperluanPilihanNilai & had
Minimum: 1
Lalai—
MedannJenisintegerKeperluanPilihanNilai & had
Minimum: 1
Lalai—
MedantemperatureJenisnumberKeperluanPilihanNilai & hadLalai—
Medantop_pJenisnumberKeperluanPilihanNilai & hadLalai—
MedanseedJenisintegerKeperluanPilihanNilai & hadLalai—
MedanstopJenisKeperluanPilihanNilai & hadLalai—
Medanfrequency_penaltyJenisnumberKeperluanPilihanNilai & hadLalai—
Medanpresence_penaltyJenisnumberKeperluanPilihanNilai & hadLalai—
MedanuserJenisstringKeperluanPilihanNilai & hadLalai—
MedantoolsJenisarrayKeperluanPilihanNilai & hadLalai—
Medanservice_tierJenisstringKeperluanPilihanNilai & had
, auto, default
Lalai—
MedanmodalitiesJenisarrayKeperluanPilihanNilai & hadLalai—
Parameter kaedah dan kitar hayat
ParameterKontrak
Parametercontent_typeKontrakapplication/json
ParameterrequiredKontrakmodel, messages
ParameteroptionalKontrakstream, max_tokens, max_completion_tokens, n, temperature, top_p, seed, stop, frequency_penalty, presence_penalty, user, tools, service_tier, modalities
Parametermaterial_typesKontraktext
ParameterconditionsKontrakUse text input and text output. Explicit cache, hosted tools and media are unavailable. Standard function tools remain a protocol feature and run in the client.

Kitar hayat: synchronous_json_or_sse

Pelan harga

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

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

Kadar Ailoot

Harga mengikut konfigurasi

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

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

Contoh permintaan

Ailoot Ultra · Chat Completions

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "baidu/ernie-4.5-0.3b", "messages": [{"role": "user", "content": "Summarize the supplied text in three concise points."}], "stream": false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n

Terima dan simpan hasil

Ailoot Ultra · Chat Completions

JSON or supported SSE

Simpan semua hasil yang selesai

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

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

Jika respons asal perlu disemak

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

Alias

Alias model

Ailoot Ultra baidu/ernie-4.5-0.3b

Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

ID pemanggil berkaitan

baidu/ernie-4.5-0.3b

", "method_identity": { "effective_request_model_id": "baidu/ernie-4.5-0.3b", "fmt": "chat", "http": "POST", "path": "/v1/chat/completions", "request_model_id": "baidu/ernie-4.5-0.3b", "route_label": "Ultra" }, "method_key": "Ultra|chat|/v1/chat/completions|baidu%2Fernie-4.5-0.3b", "ordinal": 0, "rawMethod": { "available": null, "cache_read": "0", "cache_write": "0", "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "example_body": { "messages": [ { "content": "Summarize the supplied text in three concise points.", "role": "user" } ], "model": "baidu/ernie-4.5-0.3b", "stream": false }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_json_or_sse", "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "outputs": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "family": "text", "format": "JSON or supported SSE" }, "parameters": [ { "default_known": false, "enum": [ "baidu/ernie-4.5-0.3b" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "default_known": false, "enum_known": false, "items": { "additionalProperties": true, "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "type": "object" }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant", "system", "developer" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "name": "messages", "required": true, "type": "array" }, { "default": false, "default_known": true, "enum_known": false, "name": "stream", "required": false, "type": "boolean" }, { "default_known": false, "enum_known": false, "minimum": 1, "name": "max_tokens", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "minimum": 1, "name": "max_completion_tokens", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "minimum": 1, "name": "n", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "name": "temperature", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "top_p", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "seed", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "name": "stop", "oneOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ], "required": false }, { "default_known": false, "enum_known": false, "name": "frequency_penalty", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "presence_penalty", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "user", "required": false, "type": "string" }, { "default_known": false, "enum_known": false, "items": { "type": "object" }, "name": "tools", "required": false, "type": "array" }, { "default_known": false, "enum": [ "", "auto", "default" ], "enum_known": true, "name": "service_tier", "required": false, "type": "string" }, { "default_known": false, "enum_known": false, "items": { "enum": [ "text" ], "type": "string" }, "name": "modalities", "required": false, "type": "array" } ], "request_schema": { "additionalProperties": true, "properties": { "frequency_penalty": { "type": "number" }, "max_completion_tokens": { "minimum": 1, "type": "integer" }, "max_tokens": { "minimum": 1, "type": "integer" }, "messages": { "items": { "additionalProperties": true, "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "type": "object" }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant", "system", "developer" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "modalities": { "items": { "enum": [ "text" ], "type": "string" }, "type": "array" }, "model": { "enum": [ "baidu/ernie-4.5-0.3b" ], "type": "string" }, "n": { "minimum": 1, "type": "integer" }, "presence_penalty": { "type": "number" }, "seed": { "type": "integer" }, "service_tier": { "enum": [ "", "auto", "default" ], "type": "string" }, "stop": { "oneOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ] }, "stream": { "default": false, "type": "boolean" }, "temperature": { "type": "number" }, "tools": { "items": { "type": "object" }, "type": "array" }, "top_p": { "type": "number" }, "user": { "type": "string" } }, "required": [ "model", "messages" ], "type": "object" }, "schema_template": { "body": { "messages": [ { "content": "Summarize the supplied text in three concise points.", "role": "user" } ], "model": "baidu/ernie-4.5-0.3b", "stream": false }, "content_type": "application/json" } }, "input": { "conditions": [ "Use text input and text output. Explicit cache, hosted tools and media are unavailable. Standard function tools remain a protocol feature and run in the client." ], "content_type": "application/json", "material_types": [ "text" ], "optional": [ "stream", "max_tokens", "max_completion_tokens", "n", "temperature", "top_p", "seed", "stop", "frequency_penalty", "presence_penalty", "user", "tools", "service_tier", "modalities" ], "required": [ "model", "messages" ] }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_json_or_sse", "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/chat/completions" }, "method_aliases": [], "output": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "family": "text", "format": "JSON or supported SSE" } }, "ctx": 120000, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"baidu/ernie-4.5-0.3b\", \"messages\": [{\"role\": \"user\", \"content\": \"Summarize the supplied text in three concise points.\"}], \"stream\": false}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n", "label": "curl · create once and retain the complete result", "language": "bash" } ], "family": "openai", "fast_multiplier": 1, "flex_multiplier": 1, "fmt": "chat", "http": "POST", "img_in": null, "img_out": null, "in": "0", "input": [ "text" ], "label": "Chat Completions", "max_out": 8000, "max_reasoning_effort_multiplier": 1, "method_aliases": [], "out": "0", "output": [ "text" ], "path": "/v1/chat/completions", "price_conditions": [ { "label": "Fast mode", "value": "Standard rate", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Standard rate", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Standard rate", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" }, { "label": "Text-only zero rates", "value": "Cache, tools and media follow their separately listed pricing conditions.", "when": "For text-only input and output" } ], "pricing": { "allow_explicit_cache": false, "billing_mode": "token", "cache_read_price": 0, "cache_write_1h_price": null, "cache_write_price": 0, "fast_multiplier": 1, "flex_multiplier": 1, "image_input_price": null, "image_output_price": null, "input_price": 0, "intervals": [], "max_reasoning_effort_multiplier": 1, "output_price": 0, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "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": "baidu/ernie-4.5-0.3b", "route_label": "Ultra", "status_reads": [], "tiers": [], "unit": "token", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "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": "
•

ERNIE 4.5 0.3B

Baidu /baidu/ernie-4.5-0.3b

Pengenalan

ERNIE 4.5 0.3B ialah model perbualan teks dalam keluarga sumber terbuka ERNIE 4.5. Gunakan ID tepat baidu/ernie-4.5-0.3b melalui Chat Completions atau Messages untuk mengolah teks yang dibekalkan: mendraf balasan, meringkaskan nota, mengekstrak maklumat yang dinyatakan atau menerangkan petikan pendek. Profil yang diterbitkan menyenaraikan konteks 120,000 token dan had pelengkapan 8,000 token; kedua-dua nilai menerangkan had yang berbeza.

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.

ERNIE 4.5 0.3B menerima perbualan teks melalui Ailoot Ultra. ID model yang tepat ialah baidu/ernie-4.5-0.3b. Letakkan bahan sumber terus dalam mesej anda dan terangkan hasil yang diperlukan. Profil teks ini sesuai untuk tugasan seperti mengubah nota pelanggan menjadi balasan, memadatkan petikan dokumen atau mengekstrak set fakta tertentu ke dalam susun atur yang dipersetujui.

Permintaan yang berguna menggabungkan bahan, tugasan dan keperluan jawapan. Untuk balasan sokongan, bekalkan mesej pelanggan dan teks dasar yang mesti dipatuhi oleh balasan. Untuk ringkasan, nyatakan pembaca sasaran dan minta keputusan, persoalan yang belum selesai serta tindakan susulan. Untuk pengekstrakan, tentukan nama medan dan beritahu model cara mewakili fakta yang tiada dalam sumber. Arahan ini menghasilkan jawapan yang boleh disemak dengan bahan yang anda bekalkan.

Dengan Chat Completions, hantar POST /v1/chat/completions bersama model dan tatasusunan messages yang tidak kosong. Setiap mesej membekalkan role dan content dalam bentuk teks. Sertakan giliran perbualan terdahulu yang berkaitan apabila jawapan bergantung pada perbualan. Untuk mengolah dokumen, baca teks sebenar dokumen itu dan letakkan kandungan yang berkaitan dalam mesej; nama fail sahaja tidak membekalkan dokumen tersebut.

Dengan Messages, hantar POST /v1/messages bersama model, messages dan max_tokens. Gunakan giliran user dan assistant, dengan arahan system berasingan sebagai pilihan. Kandungan boleh berupa rentetan teks atau blok teks. max_tokens ialah integer sekurang-kurangnya 1. Profil model yang diterbitkan menyenaraikan had pelengkapan 8,000 token dan konteks 120,000 token; sediakan ruang untuk jawapan yang diminta semasa menyediakan perbualan. Saiz konteks tidak bermakna jawapan boleh mengandungi 120,000 token.

Kedua-dua antara muka menyediakan kawalan boolean stream, dengan nilai lalai false. Untuk jawapan JSON yang lengkap, simpan setiap medan hasil dan rekod usage yang dikembalikan. Untuk penghantaran berstrim, kumpulkan peristiwa dan gabungkan semua kandungan jawapan sebelum menganggap balasan lengkap. Chat Completions meletakkan balasan biasa dalam choices[].message.content; Messages mengembalikan blok kandungan bersama stop_reason dan usage. Simpan identiti permintaan asal dan apa-apa balasan yang diterima jika sambungan terputus sebelum selesai, supaya balasan yang tidak lengkap boleh disiasat tanpa menghantar semula permintaan yang sama secara membuta tuli.

Tersedia di Ailoot · input & kaedah

Ailoot Ultra · Messages POST /v1/messages
Input
text
Output
text
Konteks
120,000 tokens
Output maksimum
8,000 tokens
Format output
JSON or supported SSE
MedanJenisKeperluanNilai & hadLalai
MedanmodelJenisstringKeperluanDiperlukanNilai & had
baidu/ernie-4.5-0.3b
Lalai—
MedanmessagesJenisarrayKeperluanDiperlukanNilai & hadLalai—
MedanstreamJenisbooleanKeperluanPilihanNilai & hadLalaifalse
MedansystemJenisstringKeperluanPilihanNilai & hadLalai—
Medanmax_tokensJenisintegerKeperluanDiperlukanNilai & had
Minimum: 1
Lalai—
MedantemperatureJenisnumberKeperluanPilihanNilai & hadLalai—
Medantop_pJenisnumberKeperluanPilihanNilai & hadLalai—
Medantop_kJenisintegerKeperluanPilihanNilai & hadLalai—
Medanstop_sequencesJenisarrayKeperluanPilihanNilai & hadLalai—
MedanmetadataJenisobjectKeperluanPilihanNilai & hadLalai—
MedantoolsJenisarrayKeperluanPilihanNilai & hadLalai—
Medanservice_tierJenisstringKeperluanPilihanNilai & had
, auto, default
Lalai—
MedanmodalitiesJenisarrayKeperluanPilihanNilai & hadLalai—
Parameter kaedah dan kitar hayat
ParameterKontrak
Parametercontent_typeKontrakapplication/json
ParameterrequiredKontrakmodel, messages, max_tokens
ParameteroptionalKontrakstream, system, temperature, top_p, top_k, stop_sequences, metadata, tools, service_tier, modalities
Parametermaterial_typesKontraktext
ParameterconditionsKontrakUse text input and text output. Explicit cache, hosted tools and media are unavailable. Standard function tools remain a protocol feature and run in the client.

Kitar hayat: synchronous_json_or_sse

Pelan harga

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

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

Kadar Ailoot

Harga mengikut konfigurasi

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

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "baidu/ernie-4.5-0.3b", "messages": [{"role": "user", "content": "Summarize the supplied text in three concise points."}], "stream": false, "max_tokens": 256}')\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/messages \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n

Terima dan simpan hasil

Ailoot Ultra · Messages

JSON or supported SSE

Simpan semua hasil yang selesai

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

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

Jika respons asal perlu disemak

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

Alias

Alias model

Ailoot Ultra baidu/ernie-4.5-0.3b

Alias laluan kaedah

Gunakan laluan kaedah yang dipaparkan di atas.

ID pemanggil berkaitan

baidu/ernie-4.5-0.3b

", "method_identity": { "effective_request_model_id": "baidu/ernie-4.5-0.3b", "fmt": "messages", "http": "POST", "path": "/v1/messages", "request_model_id": "baidu/ernie-4.5-0.3b", "route_label": "Ultra" }, "method_key": "Ultra|messages|/v1/messages|baidu%2Fernie-4.5-0.3b", "ordinal": 1, "rawMethod": { "available": null, "cache_read": "0", "cache_write": "0", "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "example_body": { "max_tokens": 256, "messages": [ { "content": "Summarize the supplied text in three concise points.", "role": "user" } ], "model": "baidu/ernie-4.5-0.3b", "stream": false }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/messages" }, "mode": "synchronous_json_or_sse", "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "outputs": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "family": "text", "format": "JSON or supported SSE" }, "parameters": [ { "default_known": false, "enum": [ "baidu/ernie-4.5-0.3b" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "default_known": false, "enum_known": false, "items": { "additionalProperties": true, "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "type": "object" }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "name": "messages", "required": true, "type": "array" }, { "default": false, "default_known": true, "enum_known": false, "name": "stream", "required": false, "type": "boolean" }, { "default_known": false, "enum_known": false, "name": "system", "required": false, "type": "string" }, { "default_known": false, "enum_known": false, "minimum": 1, "name": "max_tokens", "required": true, "type": "integer" }, { "default_known": false, "enum_known": false, "name": "temperature", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "top_p", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "top_k", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "items": { "type": "string" }, "name": "stop_sequences", "required": false, "type": "array" }, { "default_known": false, "enum_known": false, "name": "metadata", "required": false, "type": "object" }, { "default_known": false, "enum_known": false, "items": { "type": "object" }, "name": "tools", "required": false, "type": "array" }, { "default_known": false, "enum": [ "", "auto", "default" ], "enum_known": true, "name": "service_tier", "required": false, "type": "string" }, { "default_known": false, "enum_known": false, "items": { "enum": [ "text" ], "type": "string" }, "name": "modalities", "required": false, "type": "array" } ], "request_schema": { "additionalProperties": true, "properties": { "max_tokens": { "minimum": 1, "type": "integer" }, "messages": { "items": { "additionalProperties": true, "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "type": "object" }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "metadata": { "type": "object" }, "modalities": { "items": { "enum": [ "text" ], "type": "string" }, "type": "array" }, "model": { "enum": [ "baidu/ernie-4.5-0.3b" ], "type": "string" }, "service_tier": { "enum": [ "", "auto", "default" ], "type": "string" }, "stop_sequences": { "items": { "type": "string" }, "type": "array" }, "stream": { "default": false, "type": "boolean" }, "system": { "type": "string" }, "temperature": { "type": "number" }, "tools": { "items": { "type": "object" }, "type": "array" }, "top_k": { "type": "integer" }, "top_p": { "type": "number" } }, "required": [ "model", "messages", "max_tokens" ], "type": "object" }, "schema_template": { "body": { "max_tokens": 256, "messages": [ { "content": "Summarize the supplied text in three concise points.", "role": "user" } ], "model": "baidu/ernie-4.5-0.3b", "stream": false }, "content_type": "application/json" } }, "input": { "conditions": [ "Use text input and text output. Explicit cache, hosted tools and media are unavailable. Standard function tools remain a protocol feature and run in the client." ], "content_type": "application/json", "material_types": [ "text" ], "optional": [ "stream", "system", "temperature", "top_p", "top_k", "stop_sequences", "metadata", "tools", "service_tier", "modalities" ], "required": [ "model", "messages", "max_tokens" ] }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/messages" }, "mode": "synchronous_json_or_sse", "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/messages" }, "method_aliases": [], "output": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "family": "text", "format": "JSON or supported SSE" } }, "ctx": 120000, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"baidu/ernie-4.5-0.3b\", \"messages\": [{\"role\": \"user\", \"content\": \"Summarize the supplied text in three concise points.\"}], \"stream\": false, \"max_tokens\": 256}')\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/messages \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n", "label": "curl · create once and retain the complete result", "language": "bash" } ], "family": "anthropic", "fast_multiplier": 1, "flex_multiplier": 1, "fmt": "messages", "http": "POST", "img_in": null, "img_out": null, "in": "0", "input": [ "text" ], "label": "Messages", "max_out": 8000, "max_reasoning_effort_multiplier": 1, "method_aliases": [], "out": "0", "output": [ "text" ], "path": "/v1/messages", "price_conditions": [ { "label": "Fast mode", "value": "Standard rate", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Standard rate", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Standard rate", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" }, { "label": "Text-only zero rates", "value": "Cache, tools and media follow their separately listed pricing conditions.", "when": "For text-only input and output" } ], "pricing": { "allow_explicit_cache": false, "billing_mode": "token", "cache_read_price": 0, "cache_write_1h_price": null, "cache_write_price": 0, "fast_multiplier": 1, "flex_multiplier": 1, "image_input_price": null, "image_output_price": null, "input_price": 0, "intervals": [], "max_reasoning_effort_multiplier": 1, "output_price": 0, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "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": "baidu/ernie-4.5-0.3b", "route_label": "Ultra", "status_reads": [], "tiers": [], "unit": "token", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "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": "baidu/ernie-4.5-0.3b", "nativeProvenance": { "input_facts_canonical_sha256": "fa9857a4f5dbb9d23d1d669ba2c45be9f5b6bc9f259fe77db54c8e41975f8426", "input_html_sha256": "db6f93fdee1364df82305fc2fad9401135811d34ae1a6176e6ab7e44a9ec4f2a", "private_audit_sha256": "03399cebf2dc5d47bfcd58fddaebaccbb8274c592fe8e5267e5071d9e7de3098", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/ms/baidu-ernie-4-5-0-3b/", "description": "ERNIE 4.5 0.3B ialah model perbualan teks dalam keluarga sumber terbuka ERNIE 4.5. Gunakan ID tepat baidu/ernie-4.5-0.3b melalui Chat Completions atau Messages untuk mengolah teks yang dibekalkan: mendraf balasan, meringkaskan nota, mengekstrak maklumat yang dinyatakan atau menerangkan petikan pendek. Profil yang diterbitkan menyenaraikan konteks 120,000 token dan had pelengkapan 8,000 token; kedua-dua nilai menerangkan had yang berbeza.", "locale": "ms", "md_url": "https://ailoot.ai/models/ms/baidu-ernie-4-5-0-3b/index.md", "title": "ERNIE 4.5 0.3B — Ailoot", "url": "https://ailoot.ai/models/ms/baidu-ernie-4-5-0-3b/" }, "rawModel": { "about": "ERNIE 4.5 0.3B menerima perbualan teks melalui Ailoot Ultra. ID model yang tepat ialah baidu/ernie-4.5-0.3b. Letakkan bahan sumber terus dalam mesej anda dan terangkan hasil yang diperlukan. Profil teks ini sesuai untuk tugasan seperti mengubah nota pelanggan menjadi balasan, memadatkan petikan dokumen atau mengekstrak set fakta tertentu ke dalam susun atur yang dipersetujui.\n\nPermintaan yang berguna menggabungkan bahan, tugasan dan keperluan jawapan. Untuk balasan sokongan, bekalkan mesej pelanggan dan teks dasar yang mesti dipatuhi oleh balasan. Untuk ringkasan, nyatakan pembaca sasaran dan minta keputusan, persoalan yang belum selesai serta tindakan susulan. Untuk pengekstrakan, tentukan nama medan dan beritahu model cara mewakili fakta yang tiada dalam sumber. Arahan ini menghasilkan jawapan yang boleh disemak dengan bahan yang anda bekalkan.\n\nDengan Chat Completions, hantar POST /v1/chat/completions bersama model dan tatasusunan messages yang tidak kosong. Setiap mesej membekalkan role dan content dalam bentuk teks. Sertakan giliran perbualan terdahulu yang berkaitan apabila jawapan bergantung pada perbualan. Untuk mengolah dokumen, baca teks sebenar dokumen itu dan letakkan kandungan yang berkaitan dalam mesej; nama fail sahaja tidak membekalkan dokumen tersebut.\n\nDengan Messages, hantar POST /v1/messages bersama model, messages dan max_tokens. Gunakan giliran user dan assistant, dengan arahan system berasingan sebagai pilihan. Kandungan boleh berupa rentetan teks atau blok teks. max_tokens ialah integer sekurang-kurangnya 1. Profil model yang diterbitkan menyenaraikan had pelengkapan 8,000 token dan konteks 120,000 token; sediakan ruang untuk jawapan yang diminta semasa menyediakan perbualan. Saiz konteks tidak bermakna jawapan boleh mengandungi 120,000 token.\n\nKedua-dua antara muka menyediakan kawalan boolean stream, dengan nilai lalai false. Untuk jawapan JSON yang lengkap, simpan setiap medan hasil dan rekod usage yang dikembalikan. Untuk penghantaran berstrim, kumpulkan peristiwa dan gabungkan semua kandungan jawapan sebelum menganggap balasan lengkap. Chat Completions meletakkan balasan biasa dalam choices[].message.content; Messages mengembalikan blok kandungan bersama stop_reason dan usage. Simpan identiti permintaan asal dan apa-apa balasan yang diterima jika sambungan terputus sebelum selesai, supaya balasan yang tidak lengkap boleh disiasat tanpa menghantar semula permintaan yang sama secara membuta tuli.", "alias_of": null, "aliases": [], "author": "Baidu", "ctx": 120000, "formats": [ "chat", "messages" ], "id": "baidu/ernie-4.5-0.3b", "input": [ "text" ], "kind": "text", "max_out": 8000, "methods": [ { "available": null, "cache_read": "0", "cache_write": "0", "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "example_body": { "messages": [ { "content": "Summarize the supplied text in three concise points.", "role": "user" } ], "model": "baidu/ernie-4.5-0.3b", "stream": false }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_json_or_sse", "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "outputs": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "family": "text", "format": "JSON or supported SSE" }, "parameters": [ { "default_known": false, "enum": [ "baidu/ernie-4.5-0.3b" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "default_known": false, "enum_known": false, "items": { "additionalProperties": true, "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "type": "object" }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant", "system", "developer" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "name": "messages", "required": true, "type": "array" }, { "default": false, "default_known": true, "enum_known": false, "name": "stream", "required": false, "type": "boolean" }, { "default_known": false, "enum_known": false, "minimum": 1, "name": "max_tokens", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "minimum": 1, "name": "max_completion_tokens", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "minimum": 1, "name": "n", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "name": "temperature", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "top_p", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "seed", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "name": "stop", "oneOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ], "required": false }, { "default_known": false, "enum_known": false, "name": "frequency_penalty", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "presence_penalty", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "user", "required": false, "type": "string" }, { "default_known": false, "enum_known": false, "items": { "type": "object" }, "name": "tools", "required": false, "type": "array" }, { "default_known": false, "enum": [ "", "auto", "default" ], "enum_known": true, "name": "service_tier", "required": false, "type": "string" }, { "default_known": false, "enum_known": false, "items": { "enum": [ "text" ], "type": "string" }, "name": "modalities", "required": false, "type": "array" } ], "request_schema": { "additionalProperties": true, "properties": { "frequency_penalty": { "type": "number" }, "max_completion_tokens": { "minimum": 1, "type": "integer" }, "max_tokens": { "minimum": 1, "type": "integer" }, "messages": { "items": { "additionalProperties": true, "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "type": "object" }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant", "system", "developer" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "modalities": { "items": { "enum": [ "text" ], "type": "string" }, "type": "array" }, "model": { "enum": [ "baidu/ernie-4.5-0.3b" ], "type": "string" }, "n": { "minimum": 1, "type": "integer" }, "presence_penalty": { "type": "number" }, "seed": { "type": "integer" }, "service_tier": { "enum": [ "", "auto", "default" ], "type": "string" }, "stop": { "oneOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ] }, "stream": { "default": false, "type": "boolean" }, "temperature": { "type": "number" }, "tools": { "items": { "type": "object" }, "type": "array" }, "top_p": { "type": "number" }, "user": { "type": "string" } }, "required": [ "model", "messages" ], "type": "object" }, "schema_template": { "body": { "messages": [ { "content": "Summarize the supplied text in three concise points.", "role": "user" } ], "model": "baidu/ernie-4.5-0.3b", "stream": false }, "content_type": "application/json" } }, "input": { "conditions": [ "Use text input and text output. Explicit cache, hosted tools and media are unavailable. Standard function tools remain a protocol feature and run in the client." ], "content_type": "application/json", "material_types": [ "text" ], "optional": [ "stream", "max_tokens", "max_completion_tokens", "n", "temperature", "top_p", "seed", "stop", "frequency_penalty", "presence_penalty", "user", "tools", "service_tier", "modalities" ], "required": [ "model", "messages" ] }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/chat/completions" }, "mode": "synchronous_json_or_sse", "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/chat/completions" }, "method_aliases": [], "output": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "family": "text", "format": "JSON or supported SSE" } }, "ctx": 120000, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"baidu/ernie-4.5-0.3b\", \"messages\": [{\"role\": \"user\", \"content\": \"Summarize the supplied text in three concise points.\"}], \"stream\": false}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n", "label": "curl · create once and retain the complete result", "language": "bash" } ], "family": "openai", "fast_multiplier": 1, "flex_multiplier": 1, "fmt": "chat", "http": "POST", "img_in": null, "img_out": null, "in": "0", "input": [ "text" ], "label": "Chat Completions", "max_out": 8000, "max_reasoning_effort_multiplier": 1, "method_aliases": [], "out": "0", "output": [ "text" ], "path": "/v1/chat/completions", "price_conditions": [ { "label": "Fast mode", "value": "Standard rate", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Standard rate", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Standard rate", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" }, { "label": "Text-only zero rates", "value": "Cache, tools and media follow their separately listed pricing conditions.", "when": "For text-only input and output" } ], "pricing": { "allow_explicit_cache": false, "billing_mode": "token", "cache_read_price": 0, "cache_write_1h_price": null, "cache_write_price": 0, "fast_multiplier": 1, "flex_multiplier": 1, "image_input_price": null, "image_output_price": null, "input_price": 0, "intervals": [], "max_reasoning_effort_multiplier": 1, "output_price": 0, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "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": "baidu/ernie-4.5-0.3b", "route_label": "Ultra", "status_reads": [], "tiers": [], "unit": "token", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "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": "0", "cache_write": "0", "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "authentication": { "api_key_source": "AILOOT_API_KEY", "header": "Authorization: Bearer" }, "example_body": { "max_tokens": 256, "messages": [ { "content": "Summarize the supplied text in three concise points.", "role": "user" } ], "model": "baidu/ernie-4.5-0.3b", "stream": false }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/messages" }, "mode": "synchronous_json_or_sse", "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "outputs": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "family": "text", "format": "JSON or supported SSE" }, "parameters": [ { "default_known": false, "enum": [ "baidu/ernie-4.5-0.3b" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "default_known": false, "enum_known": false, "items": { "additionalProperties": true, "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "type": "object" }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "name": "messages", "required": true, "type": "array" }, { "default": false, "default_known": true, "enum_known": false, "name": "stream", "required": false, "type": "boolean" }, { "default_known": false, "enum_known": false, "name": "system", "required": false, "type": "string" }, { "default_known": false, "enum_known": false, "minimum": 1, "name": "max_tokens", "required": true, "type": "integer" }, { "default_known": false, "enum_known": false, "name": "temperature", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "top_p", "required": false, "type": "number" }, { "default_known": false, "enum_known": false, "name": "top_k", "required": false, "type": "integer" }, { "default_known": false, "enum_known": false, "items": { "type": "string" }, "name": "stop_sequences", "required": false, "type": "array" }, { "default_known": false, "enum_known": false, "name": "metadata", "required": false, "type": "object" }, { "default_known": false, "enum_known": false, "items": { "type": "object" }, "name": "tools", "required": false, "type": "array" }, { "default_known": false, "enum": [ "", "auto", "default" ], "enum_known": true, "name": "service_tier", "required": false, "type": "string" }, { "default_known": false, "enum_known": false, "items": { "enum": [ "text" ], "type": "string" }, "name": "modalities", "required": false, "type": "array" } ], "request_schema": { "additionalProperties": true, "properties": { "max_tokens": { "minimum": 1, "type": "integer" }, "messages": { "items": { "additionalProperties": true, "properties": { "content": { "oneOf": [ { "type": "string" }, { "items": { "type": "object" }, "type": "array" } ] }, "role": { "enum": [ "user", "assistant" ], "type": "string" } }, "required": [ "role", "content" ], "type": "object" }, "minItems": 1, "type": "array" }, "metadata": { "type": "object" }, "modalities": { "items": { "enum": [ "text" ], "type": "string" }, "type": "array" }, "model": { "enum": [ "baidu/ernie-4.5-0.3b" ], "type": "string" }, "service_tier": { "enum": [ "", "auto", "default" ], "type": "string" }, "stop_sequences": { "items": { "type": "string" }, "type": "array" }, "stream": { "default": false, "type": "boolean" }, "system": { "type": "string" }, "temperature": { "type": "number" }, "tools": { "items": { "type": "object" }, "type": "array" }, "top_k": { "type": "integer" }, "top_p": { "type": "number" } }, "required": [ "model", "messages", "max_tokens" ], "type": "object" }, "schema_template": { "body": { "max_tokens": 256, "messages": [ { "content": "Summarize the supplied text in three concise points.", "role": "user" } ], "model": "baidu/ernie-4.5-0.3b", "stream": false }, "content_type": "application/json" } }, "input": { "conditions": [ "Use text input and text output. Explicit cache, hosted tools and media are unavailable. Standard function tools remain a protocol feature and run in the client." ], "content_type": "application/json", "material_types": [ "text" ], "optional": [ "stream", "system", "temperature", "top_p", "top_k", "stop_sequences", "metadata", "tools", "service_tier", "modalities" ], "required": [ "model", "messages", "max_tokens" ] }, "lifecycle": { "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/messages" }, "mode": "synchronous_json_or_sse", "status": [], "unknown": "Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/messages" }, "method_aliases": [], "output": { "all_results": "Retain the complete response, all actual results, original identifiers, usage and response headers.", "family": "text", "format": "JSON or supported SSE" } }, "ctx": 120000, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"baidu/ernie-4.5-0.3b\", \"messages\": [{\"role\": \"user\", \"content\": \"Summarize the supplied text in three concise points.\"}], \"stream\": false, \"max_tokens\": 256}')\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/messages \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\n", "label": "curl · create once and retain the complete result", "language": "bash" } ], "family": "anthropic", "fast_multiplier": 1, "flex_multiplier": 1, "fmt": "messages", "http": "POST", "img_in": null, "img_out": null, "in": "0", "input": [ "text" ], "label": "Messages", "max_out": 8000, "max_reasoning_effort_multiplier": 1, "method_aliases": [], "out": "0", "output": [ "text" ], "path": "/v1/messages", "price_conditions": [ { "label": "Fast mode", "value": "Standard rate", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Standard rate", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Standard rate", "when": "When maximum reasoning effort uses the default adjustment" }, { "label": "Explicit cache pricing", "value": "Not enabled", "when": "When explicit cache is requested" }, { "label": "Text-only zero rates", "value": "Cache, tools and media follow their separately listed pricing conditions.", "when": "For text-only input and output" } ], "pricing": { "allow_explicit_cache": false, "billing_mode": "token", "cache_read_price": 0, "cache_write_1h_price": null, "cache_write_price": 0, "fast_multiplier": 1, "flex_multiplier": 1, "image_input_price": null, "image_output_price": null, "input_price": 0, "intervals": [], "max_reasoning_effort_multiplier": 1, "output_price": 0, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "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": "baidu/ernie-4.5-0.3b", "route_label": "Ultra", "status_reads": [], "tiers": [], "unit": "token", "units": [ { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": "0", "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": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": "0", "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": "baidu/ernie-4.5-0.3b", "request_model_id": "baidu/ernie-4.5-0.3b", "route_label": "Ultra" } ], "name": "ERNIE 4.5 0.3B", "price": { "in": "0", "in_label": null, "out": "0", "out_label": null, "sort_in": "0", "sort_out": "0", "varies": false }, "short": "ERNIE 4.5 0.3B ialah model perbualan teks dalam keluarga sumber terbuka ERNIE 4.5. Gunakan ID tepat baidu/ernie-4.5-0.3b melalui Chat Completions atau Messages untuk mengolah teks yang dibekalkan: mendraf balasan, meringkaskan nota, mengekstrak maklumat yang dinyatakan atau menerangkan petikan pendek. Profil yang diterbitkan menyenaraikan konteks 120,000 token dan had pelengkapan 8,000 token; kedua-dua nilai menerangkan had yang berbeza." }, "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": "ERNIE 4.5 0.3B ialah model perbualan teks dalam keluarga sumber terbuka ERNIE 4.5. Gunakan ID tepat baidu/ernie-4.5-0.3b melalui Chat Completions atau Messages untuk mengolah teks yang dibekalkan: mendraf balasan, meringkaskan nota, mengekstrak maklumat yang dinyatakan atau menerangkan petikan pendek. Profil yang diterbitkan menyenaraikan konteks 120,000 token dan had pelengkapan 8,000 token; kedua-dua nilai menerangkan had yang berbeza.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "bc1ce239d29e0264766a37d8df184660125b7993e150e2f359a14ac7387b263b", "renderer_sha256": "1dab5ba62521e9568c8b7c82005622cabbf330a075df7cce1f83274a04009460" }, "sourceRevision": "68514b95af45adcfd3c588f1701ef3378afa4b77931af73d8d77ca5f8dce1310" }