{ "aboutHtml": "

ERNIE 4.5 0.3B menerima percakapan teks melalui Ailoot Ultra. ID model persisnya adalah baidu/ernie-4.5-0.3b. Masukkan materi sumber langsung ke dalam pesan dan jelaskan hasil yang Anda perlukan. Profil teks ini cocok untuk tugas seperti mengubah catatan pelanggan menjadi balasan, memadatkan kutipan dokumen, atau mengekstrak sekumpulan fakta tertentu ke dalam format yang telah ditentukan.

Permintaan yang berguna menggabungkan materi, tugas, dan ketentuan jawaban. Untuk balasan dukungan, sertakan pesan pelanggan dan teks kebijakan yang wajib diikuti balasan. Untuk rangkuman, sebutkan sasaran pembaca dan minta keputusan, pertanyaan yang belum terjawab, serta tindak lanjut. Untuk ekstraksi, tentukan nama kolom dan beri tahu model cara merepresentasikan fakta yang tidak terdapat dalam sumber. Instruksi ini menghasilkan jawaban yang dapat diperiksa terhadap materi yang Anda berikan.

Dengan Chat Completions, kirim POST /v1/chat/completions dengan model dan array messages yang tidak kosong. Setiap pesan menyertakan role dan content berupa teks. Sertakan giliran percakapan sebelumnya yang relevan jika jawaban bergantung pada percakapan. Untuk mengolah dokumen, baca teks aslinya dan masukkan isi yang relevan ke dalam pesan; nama berkas saja tidak menyertakan dokumen tersebut.

Dengan Messages, kirim POST /v1/messages dengan model, messages, dan max_tokens. Gunakan giliran user dan assistant, dengan instruksi system terpisah yang bersifat opsional. Content dapat berupa string teks atau blok teks. max_tokens adalah bilangan bulat minimal 1. Profil model yang dipublikasikan mencantumkan batas keluaran 8.000 token dan konteks 120.000 token; sisakan ruang untuk jawaban yang diminta saat menyiapkan percakapan. Ukuran konteks tidak berarti jawaban dapat memuat 120.000 token.

Kedua antarmuka menyediakan kontrol boolean stream, yang nilai bawaannya false. Untuk jawaban JSON lengkap, simpan semua kolom hasil dan catatan usage yang dikembalikan. Untuk pengiriman secara streaming, kumpulkan peristiwa dan rangkai seluruh isi jawaban sebelum menganggap respons lengkap. Chat Completions menempatkan balasan biasa di choices[].message.content; Messages mengembalikan blok content beserta stop_reason dan usage. Simpan identitas permintaan asli dan setiap respons yang diterima jika koneksi terputus sebelum selesai, agar respons yang tidak lengkap dapat diperiksa tanpa mengirim ulang permintaan yang sama secara membabi buta.

", "aboutText": "ERNIE 4.5 0.3B menerima percakapan teks melalui Ailoot Ultra. ID model persisnya adalah baidu/ernie-4.5-0.3b. Masukkan materi sumber langsung ke dalam pesan dan jelaskan hasil yang Anda perlukan. Profil teks ini cocok untuk tugas seperti mengubah catatan pelanggan menjadi balasan, memadatkan kutipan dokumen, atau mengekstrak sekumpulan fakta tertentu ke dalam format yang telah ditentukan.\n\nPermintaan yang berguna menggabungkan materi, tugas, dan ketentuan jawaban. Untuk balasan dukungan, sertakan pesan pelanggan dan teks kebijakan yang wajib diikuti balasan. Untuk rangkuman, sebutkan sasaran pembaca dan minta keputusan, pertanyaan yang belum terjawab, serta tindak lanjut. Untuk ekstraksi, tentukan nama kolom dan beri tahu model cara merepresentasikan fakta yang tidak terdapat dalam sumber. Instruksi ini menghasilkan jawaban yang dapat diperiksa terhadap materi yang Anda berikan.\n\nDengan Chat Completions, kirim POST /v1/chat/completions dengan model dan array messages yang tidak kosong. Setiap pesan menyertakan role dan content berupa teks. Sertakan giliran percakapan sebelumnya yang relevan jika jawaban bergantung pada percakapan. Untuk mengolah dokumen, baca teks aslinya dan masukkan isi yang relevan ke dalam pesan; nama berkas saja tidak menyertakan dokumen tersebut.\n\nDengan Messages, kirim POST /v1/messages dengan model, messages, dan max_tokens. Gunakan giliran user dan assistant, dengan instruksi system terpisah yang bersifat opsional. Content dapat berupa string teks atau blok teks. max_tokens adalah bilangan bulat minimal 1. Profil model yang dipublikasikan mencantumkan batas keluaran 8.000 token dan konteks 120.000 token; sisakan ruang untuk jawaban yang diminta saat menyiapkan percakapan. Ukuran konteks tidak berarti jawaban dapat memuat 120.000 token.\n\nKedua antarmuka menyediakan kontrol boolean stream, yang nilai bawaannya false. Untuk jawaban JSON lengkap, simpan semua kolom hasil dan catatan usage yang dikembalikan. Untuk pengiriman secara streaming, kumpulkan peristiwa dan rangkai seluruh isi jawaban sebelum menganggap respons lengkap. Chat Completions menempatkan balasan biasa di choices[].message.content; Messages mengembalikan blok content beserta stop_reason dan usage. Simpan identitas permintaan asli dan setiap respons yang diterima jika koneksi terputus sebelum selesai, agar respons yang tidak lengkap dapat diperiksa tanpa mengirim ulang permintaan yang sama secara membabi buta.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "7ded1a0685e6402a32a4ba7fab915b24a5c98cd80ec0ca9ad05237162e13c67d", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "id", "methods": [ { "html": "
•

ERNIE 4.5 0.3B

Baidu /baidu/ernie-4.5-0.3b

Mulai

ERNIE 4.5 0.3B adalah model percakapan teks dalam keluarga sumber terbuka ERNIE 4.5. Gunakan ID persis baidu/ernie-4.5-0.3b melalui Chat Completions atau Messages untuk mengolah teks yang diberikan: menyusun balasan, merangkum catatan, mengekstrak informasi tertentu, atau menjelaskan bacaan singkat. Profil yang dipublikasikan mencantumkan konteks 120.000 token dan batas keluaran 8.000 token; kedua nilai tersebut menjelaskan batas yang berbeda.

Masukan yang diterima
Teks
Hasil
Teks
Tentang model

Deskripsi ini mencakup kemampuan model. Masukan, keluaran, dan opsi yang tersedia di Ailoot tercantum di bawah untuk metode yang dipilih.

ERNIE 4.5 0.3B menerima percakapan teks melalui Ailoot Ultra. ID model persisnya adalah baidu/ernie-4.5-0.3b. Masukkan materi sumber langsung ke dalam pesan dan jelaskan hasil yang Anda perlukan. Profil teks ini cocok untuk tugas seperti mengubah catatan pelanggan menjadi balasan, memadatkan kutipan dokumen, atau mengekstrak sekumpulan fakta tertentu ke dalam format yang telah ditentukan.

Permintaan yang berguna menggabungkan materi, tugas, dan ketentuan jawaban. Untuk balasan dukungan, sertakan pesan pelanggan dan teks kebijakan yang wajib diikuti balasan. Untuk rangkuman, sebutkan sasaran pembaca dan minta keputusan, pertanyaan yang belum terjawab, serta tindak lanjut. Untuk ekstraksi, tentukan nama kolom dan beri tahu model cara merepresentasikan fakta yang tidak terdapat dalam sumber. Instruksi ini menghasilkan jawaban yang dapat diperiksa terhadap materi yang Anda berikan.

Dengan Chat Completions, kirim POST /v1/chat/completions dengan model dan array messages yang tidak kosong. Setiap pesan menyertakan role dan content berupa teks. Sertakan giliran percakapan sebelumnya yang relevan jika jawaban bergantung pada percakapan. Untuk mengolah dokumen, baca teks aslinya dan masukkan isi yang relevan ke dalam pesan; nama berkas saja tidak menyertakan dokumen tersebut.

Dengan Messages, kirim POST /v1/messages dengan model, messages, dan max_tokens. Gunakan giliran user dan assistant, dengan instruksi system terpisah yang bersifat opsional. Content dapat berupa string teks atau blok teks. max_tokens adalah bilangan bulat minimal 1. Profil model yang dipublikasikan mencantumkan batas keluaran 8.000 token dan konteks 120.000 token; sisakan ruang untuk jawaban yang diminta saat menyiapkan percakapan. Ukuran konteks tidak berarti jawaban dapat memuat 120.000 token.

Kedua antarmuka menyediakan kontrol boolean stream, yang nilai bawaannya false. Untuk jawaban JSON lengkap, simpan semua kolom hasil dan catatan usage yang dikembalikan. Untuk pengiriman secara streaming, kumpulkan peristiwa dan rangkai seluruh isi jawaban sebelum menganggap respons lengkap. Chat Completions menempatkan balasan biasa di choices[].message.content; Messages mengembalikan blok content beserta stop_reason dan usage. Simpan identitas permintaan asli dan setiap respons yang diterima jika koneksi terputus sebelum selesai, agar respons yang tidak lengkap dapat diperiksa tanpa mengirim ulang permintaan yang sama secara membabi buta.

Tersedia di Ailoot · masukan & metode

Ailoot Ultra · Chat Completions POST /v1/chat/completions
Masukan
text
Keluaran
text
Konteks
120.000 tokens
Keluaran maksimum
8.000 tokens
Format keluaran
JSON or supported SSE
KolomJenisPersyaratanNilai & batasanBawaan
KolommodelJenisstringPersyaratanWajibNilai & batasan
baidu/ernie-4.5-0.3b
Bawaan—
KolommessagesJenisarrayPersyaratanWajibNilai & batasanBawaan—
KolomstreamJenisbooleanPersyaratanOpsionalNilai & batasanBawaanfalse
Kolommax_tokensJenisintegerPersyaratanOpsionalNilai & batasan
Minimum: 1
Bawaan—
Kolommax_completion_tokensJenisintegerPersyaratanOpsionalNilai & batasan
Minimum: 1
Bawaan—
KolomnJenisintegerPersyaratanOpsionalNilai & batasan
Minimum: 1
Bawaan—
KolomtemperatureJenisnumberPersyaratanOpsionalNilai & batasanBawaan—
Kolomtop_pJenisnumberPersyaratanOpsionalNilai & batasanBawaan—
KolomseedJenisintegerPersyaratanOpsionalNilai & batasanBawaan—
KolomstopJenisPersyaratanOpsionalNilai & batasanBawaan—
Kolomfrequency_penaltyJenisnumberPersyaratanOpsionalNilai & batasanBawaan—
Kolompresence_penaltyJenisnumberPersyaratanOpsionalNilai & batasanBawaan—
KolomuserJenisstringPersyaratanOpsionalNilai & batasanBawaan—
KolomtoolsJenisarrayPersyaratanOpsionalNilai & batasanBawaan—
Kolomservice_tierJenisstringPersyaratanOpsionalNilai & batasan
, auto, default
Bawaan—
KolommodalitiesJenisarrayPersyaratanOpsionalNilai & batasanBawaan—
Parameter metode dan siklus hidup
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.

Siklus hidup: synchronous_json_or_sse

Paket

Referensi tarif tidak menambah opsi permintaan. Parameter yang didukung tercantum pada metode yang dipilih.

Mode Fast
Tarif standar Saat mode fast dipilih
Mode Flex
Tarif standar Saat mode flex dipilih
Upaya penalaran maksimum
Tarif standar Saat upaya penalaran maksimum menggunakan penyesuaian default
Harga cache eksplisit
Tidak diaktifkan Saat cache eksplisit diminta
Tarif nol khusus teks
Cache, alat, dan media mengikuti ketentuan harga masing-masing yang tercantum secara terpisah. Untuk masukan dan keluaran yang hanya berupa teks

Tarif Ailoot

Harga menurut konfigurasi

KonfigurasiJadwal tarifBiaya
KonfigurasiTarif dasar tokenJadwal tarifTarif dasarBiaya
Masukan · Token masukan $0 / 1K token
Keluaran · Token keluaran $0 / 1K token
Masukan · Pembacaan cache $0 / 1K token
Masukan · Penulisan cache $0 / 1K token
Masukan · Penulisan cache, 1 jam — / 1K token

Ailoot mencadangkan perkiraan dana sebelum permintaan. Setelah hasil diterima, tagihan akhir diselesaikan berdasarkan penggunaan yang terukur. Penyelesaian tagihan streaming menggunakan catatan penggunaan akhir. Cara kerja cadangan dan penyelesaian tagihan →

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, berkas, dan bagian konten yang dikembalikan.

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

Jika respons asli perlu diperiksa

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 jalur metode

Gunakan jalur metode yang ditampilkan di atas.

ID pemanggil terkait

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

Mulai

ERNIE 4.5 0.3B adalah model percakapan teks dalam keluarga sumber terbuka ERNIE 4.5. Gunakan ID persis baidu/ernie-4.5-0.3b melalui Chat Completions atau Messages untuk mengolah teks yang diberikan: menyusun balasan, merangkum catatan, mengekstrak informasi tertentu, atau menjelaskan bacaan singkat. Profil yang dipublikasikan mencantumkan konteks 120.000 token dan batas keluaran 8.000 token; kedua nilai tersebut menjelaskan batas yang berbeda.

Masukan yang diterima
Teks
Hasil
Teks
Tentang model

Deskripsi ini mencakup kemampuan model. Masukan, keluaran, dan opsi yang tersedia di Ailoot tercantum di bawah untuk metode yang dipilih.

ERNIE 4.5 0.3B menerima percakapan teks melalui Ailoot Ultra. ID model persisnya adalah baidu/ernie-4.5-0.3b. Masukkan materi sumber langsung ke dalam pesan dan jelaskan hasil yang Anda perlukan. Profil teks ini cocok untuk tugas seperti mengubah catatan pelanggan menjadi balasan, memadatkan kutipan dokumen, atau mengekstrak sekumpulan fakta tertentu ke dalam format yang telah ditentukan.

Permintaan yang berguna menggabungkan materi, tugas, dan ketentuan jawaban. Untuk balasan dukungan, sertakan pesan pelanggan dan teks kebijakan yang wajib diikuti balasan. Untuk rangkuman, sebutkan sasaran pembaca dan minta keputusan, pertanyaan yang belum terjawab, serta tindak lanjut. Untuk ekstraksi, tentukan nama kolom dan beri tahu model cara merepresentasikan fakta yang tidak terdapat dalam sumber. Instruksi ini menghasilkan jawaban yang dapat diperiksa terhadap materi yang Anda berikan.

Dengan Chat Completions, kirim POST /v1/chat/completions dengan model dan array messages yang tidak kosong. Setiap pesan menyertakan role dan content berupa teks. Sertakan giliran percakapan sebelumnya yang relevan jika jawaban bergantung pada percakapan. Untuk mengolah dokumen, baca teks aslinya dan masukkan isi yang relevan ke dalam pesan; nama berkas saja tidak menyertakan dokumen tersebut.

Dengan Messages, kirim POST /v1/messages dengan model, messages, dan max_tokens. Gunakan giliran user dan assistant, dengan instruksi system terpisah yang bersifat opsional. Content dapat berupa string teks atau blok teks. max_tokens adalah bilangan bulat minimal 1. Profil model yang dipublikasikan mencantumkan batas keluaran 8.000 token dan konteks 120.000 token; sisakan ruang untuk jawaban yang diminta saat menyiapkan percakapan. Ukuran konteks tidak berarti jawaban dapat memuat 120.000 token.

Kedua antarmuka menyediakan kontrol boolean stream, yang nilai bawaannya false. Untuk jawaban JSON lengkap, simpan semua kolom hasil dan catatan usage yang dikembalikan. Untuk pengiriman secara streaming, kumpulkan peristiwa dan rangkai seluruh isi jawaban sebelum menganggap respons lengkap. Chat Completions menempatkan balasan biasa di choices[].message.content; Messages mengembalikan blok content beserta stop_reason dan usage. Simpan identitas permintaan asli dan setiap respons yang diterima jika koneksi terputus sebelum selesai, agar respons yang tidak lengkap dapat diperiksa tanpa mengirim ulang permintaan yang sama secara membabi buta.

Tersedia di Ailoot · masukan & metode

Ailoot Ultra · Messages POST /v1/messages
Masukan
text
Keluaran
text
Konteks
120.000 tokens
Keluaran maksimum
8.000 tokens
Format keluaran
JSON or supported SSE
KolomJenisPersyaratanNilai & batasanBawaan
KolommodelJenisstringPersyaratanWajibNilai & batasan
baidu/ernie-4.5-0.3b
Bawaan—
KolommessagesJenisarrayPersyaratanWajibNilai & batasanBawaan—
KolomstreamJenisbooleanPersyaratanOpsionalNilai & batasanBawaanfalse
KolomsystemJenisstringPersyaratanOpsionalNilai & batasanBawaan—
Kolommax_tokensJenisintegerPersyaratanWajibNilai & batasan
Minimum: 1
Bawaan—
KolomtemperatureJenisnumberPersyaratanOpsionalNilai & batasanBawaan—
Kolomtop_pJenisnumberPersyaratanOpsionalNilai & batasanBawaan—
Kolomtop_kJenisintegerPersyaratanOpsionalNilai & batasanBawaan—
Kolomstop_sequencesJenisarrayPersyaratanOpsionalNilai & batasanBawaan—
KolommetadataJenisobjectPersyaratanOpsionalNilai & batasanBawaan—
KolomtoolsJenisarrayPersyaratanOpsionalNilai & batasanBawaan—
Kolomservice_tierJenisstringPersyaratanOpsionalNilai & batasan
, auto, default
Bawaan—
KolommodalitiesJenisarrayPersyaratanOpsionalNilai & batasanBawaan—
Parameter metode dan siklus hidup
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.

Siklus hidup: synchronous_json_or_sse

Paket

Referensi tarif tidak menambah opsi permintaan. Parameter yang didukung tercantum pada metode yang dipilih.

Mode Fast
Tarif standar Saat mode fast dipilih
Mode Flex
Tarif standar Saat mode flex dipilih
Upaya penalaran maksimum
Tarif standar Saat upaya penalaran maksimum menggunakan penyesuaian default
Harga cache eksplisit
Tidak diaktifkan Saat cache eksplisit diminta
Tarif nol khusus teks
Cache, alat, dan media mengikuti ketentuan harga masing-masing yang tercantum secara terpisah. Untuk masukan dan keluaran yang hanya berupa teks

Tarif Ailoot

Harga menurut konfigurasi

KonfigurasiJadwal tarifBiaya
KonfigurasiTarif dasar tokenJadwal tarifTarif dasarBiaya
Masukan · Token masukan $0 / 1K token
Keluaran · Token keluaran $0 / 1K token
Masukan · Pembacaan cache $0 / 1K token
Masukan · Penulisan cache $0 / 1K token
Masukan · Penulisan cache, 1 jam — / 1K token

Ailoot mencadangkan perkiraan dana sebelum permintaan. Setelah hasil diterima, tagihan akhir diselesaikan berdasarkan penggunaan yang terukur. Penyelesaian tagihan streaming menggunakan catatan penggunaan akhir. Cara kerja cadangan dan penyelesaian tagihan →

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, berkas, dan bagian konten yang dikembalikan.

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

Jika respons asli perlu diperiksa

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 jalur metode

Gunakan jalur metode yang ditampilkan di atas.

ID pemanggil terkait

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": "9c577fa3ee9066c2167e7a6d6e6225bacd6b63534ff1b89c447c203056cf1a80", "input_html_sha256": "18318470cb3bfb0201adf80f56be8b4954b08cfdd2510758b7923e153a5c36a4", "private_audit_sha256": "e18927b08ef6d2cefb04bc46921c740054ee16deac9d5589e9bd9c0cc1d8bbc9", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/id/baidu-ernie-4-5-0-3b/", "description": "ERNIE 4.5 0.3B adalah model percakapan teks dalam keluarga sumber terbuka ERNIE 4.5. Gunakan ID persis baidu/ernie-4.5-0.3b melalui Chat Completions atau Messages untuk mengolah teks yang diberikan: menyusun balasan, merangkum catatan, mengekstrak informasi tertentu, atau menjelaskan bacaan singkat. Profil yang dipublikasikan mencantumkan konteks 120.000 token dan batas keluaran 8.000 token; kedua nilai tersebut menjelaskan batas yang berbeda.", "locale": "id", "md_url": "https://ailoot.ai/models/id/baidu-ernie-4-5-0-3b/index.md", "title": "ERNIE 4.5 0.3B — Ailoot", "url": "https://ailoot.ai/models/id/baidu-ernie-4-5-0-3b/" }, "rawModel": { "about": "ERNIE 4.5 0.3B menerima percakapan teks melalui Ailoot Ultra. ID model persisnya adalah baidu/ernie-4.5-0.3b. Masukkan materi sumber langsung ke dalam pesan dan jelaskan hasil yang Anda perlukan. Profil teks ini cocok untuk tugas seperti mengubah catatan pelanggan menjadi balasan, memadatkan kutipan dokumen, atau mengekstrak sekumpulan fakta tertentu ke dalam format yang telah ditentukan.\n\nPermintaan yang berguna menggabungkan materi, tugas, dan ketentuan jawaban. Untuk balasan dukungan, sertakan pesan pelanggan dan teks kebijakan yang wajib diikuti balasan. Untuk rangkuman, sebutkan sasaran pembaca dan minta keputusan, pertanyaan yang belum terjawab, serta tindak lanjut. Untuk ekstraksi, tentukan nama kolom dan beri tahu model cara merepresentasikan fakta yang tidak terdapat dalam sumber. Instruksi ini menghasilkan jawaban yang dapat diperiksa terhadap materi yang Anda berikan.\n\nDengan Chat Completions, kirim POST /v1/chat/completions dengan model dan array messages yang tidak kosong. Setiap pesan menyertakan role dan content berupa teks. Sertakan giliran percakapan sebelumnya yang relevan jika jawaban bergantung pada percakapan. Untuk mengolah dokumen, baca teks aslinya dan masukkan isi yang relevan ke dalam pesan; nama berkas saja tidak menyertakan dokumen tersebut.\n\nDengan Messages, kirim POST /v1/messages dengan model, messages, dan max_tokens. Gunakan giliran user dan assistant, dengan instruksi system terpisah yang bersifat opsional. Content dapat berupa string teks atau blok teks. max_tokens adalah bilangan bulat minimal 1. Profil model yang dipublikasikan mencantumkan batas keluaran 8.000 token dan konteks 120.000 token; sisakan ruang untuk jawaban yang diminta saat menyiapkan percakapan. Ukuran konteks tidak berarti jawaban dapat memuat 120.000 token.\n\nKedua antarmuka menyediakan kontrol boolean stream, yang nilai bawaannya false. Untuk jawaban JSON lengkap, simpan semua kolom hasil dan catatan usage yang dikembalikan. Untuk pengiriman secara streaming, kumpulkan peristiwa dan rangkai seluruh isi jawaban sebelum menganggap respons lengkap. Chat Completions menempatkan balasan biasa di choices[].message.content; Messages mengembalikan blok content beserta stop_reason dan usage. Simpan identitas permintaan asli dan setiap respons yang diterima jika koneksi terputus sebelum selesai, agar respons yang tidak lengkap dapat diperiksa tanpa mengirim ulang permintaan yang sama secara membabi buta.", "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 adalah model percakapan teks dalam keluarga sumber terbuka ERNIE 4.5. Gunakan ID persis baidu/ernie-4.5-0.3b melalui Chat Completions atau Messages untuk mengolah teks yang diberikan: menyusun balasan, merangkum catatan, mengekstrak informasi tertentu, atau menjelaskan bacaan singkat. Profil yang dipublikasikan mencantumkan konteks 120.000 token dan batas keluaran 8.000 token; kedua nilai tersebut menjelaskan batas yang berbeda." }, "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 adalah model percakapan teks dalam keluarga sumber terbuka ERNIE 4.5. Gunakan ID persis baidu/ernie-4.5-0.3b melalui Chat Completions atau Messages untuk mengolah teks yang diberikan: menyusun balasan, merangkum catatan, mengekstrak informasi tertentu, atau menjelaskan bacaan singkat. Profil yang dipublikasikan mencantumkan konteks 120.000 token dan batas keluaran 8.000 token; kedua nilai tersebut menjelaskan batas yang berbeda.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "afd6f1d8c5adf0064ef0b8ea582b4c11ad9ef3b748d797b22822d49e09fa6d83", "renderer_sha256": "2a0471475a29000c23db326ca1e315df73dee7524f6bc2907818ee3458813f2d" }, "sourceRevision": "223d744708b7898863efb0c4adf6b7c4378bea53c64cb0c294717ba90058081e" }