Source: https://ailoot.ai/models/ms/claude-opus-5/
Canonical: https://ailoot.ai/models/ms/claude-opus-5/
Language: ms
# Anthropic: Claude Opus 5
[Markdown](https://ailoot.ai/models/ms/claude-opus-5/index.md) · [JSON](https://ailoot.ai/models/ms/claude-opus-5/facts.json)
## [Anthropic: Claude Opus 5](https://ailoot.ai/models/ms/claude-opus-5/)
Claude Opus 5 direka untuk pembangunan yang teliti, analisis maklumat dan kerja profesional berbilang langkah. Menyokong penaakulan adaptif dan pemeriksaan hasil menggunakan alat aplikasi.
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `claude-opus-5`](https://ailoot.ai/models/ms/claude-opus-5/#method-0)
- [**Ailoot · OpenAI Responses** `POST /v1/responses` `claude-opus-5`](https://ailoot.ai/models/ms/claude-opus-5/#method-1)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `claude-opus-5`](https://ailoot.ai/models/ms/claude-opus-5/#method-2)
- [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `claude-opus-5`](https://ailoot.ai/models/ms/claude-opus-5/#method-3)
- [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `claude-opus-5`](https://ailoot.ai/models/ms/claude-opus-5/#method-4)
- [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `anthropic/claude-opus-5`](https://ailoot.ai/models/ms/claude-opus-5/#method-5)
- [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `anthropic/claude-opus-5`](https://ailoot.ai/models/ms/claude-opus-5/#method-6)
Tentang model
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
Claude Opus 5 ialah model Anthropic untuk kerja profesional rutin yang memerlukan maklumat dikaji, pilihan berasas dibuat dan tugasan dilaksanakan secara berurutan. Pengeluar menekankan kejuruteraan perisian, senario perniagaan berbilang langkah, kerja saintifik dan analisis data visual. Penerangannya berpusat pada pelaksanaan yang teliti dan pemeriksaan hasil sendiri.
#### Mengenal pasti punca, memeriksa dan membetulkan
Dalam pembangunan, Opus 5 boleh menyelidik punca asas ralat dan menggunakan semakan untuk menilai perubahan yang dicadangkan. Jika bahan sedia ada untuk perbandingan tidak mencukupi, senario yang diterangkan merangkumi pembinaan semakan sendiri, contohnya untuk tingkah laku penghurai. Kerja dibina berdasarkan data yang diterima: model membacanya, memilih tindakan, melihat hasil dan membetulkan masalah yang dikenal pasti.
Untuk melaksanakan arahan, menyunting fail dan menjalankan semakan, aplikasi memerlukan alat yang sepadan. Inisiatif model berkaitan dengan pemilihan dan urutan tindakan dalam persekitaran yang disediakan; ini tidak bermaksud akses kendiri kepada projek atau keupayaan melakukan operasi di luar aplikasi.
#### Imej sebagai data untuk program
Opus 5 menerima **teks dan imej** lalu mengeluarkan **teks**. Dalam senario visual, pengeluar menunjukkan pengekstrakan geometri daripada imej dan pembinaan semula komponen melalui kod yang ditulis. Contoh lain merangkumi simulasi aerodinamik interaktif dan ilustrasi sel yang dihasilkan melalui pengaturcaraan.
Format input visual biasa pengeluar ialah JPEG/PNG/GIF/WebP, dengan bingkai pertama digunakan bagi animasi. Untuk analisis natif: sisi panjang ialah 2576 piksel dan jumlah token visual ialah 4784; imej besar dikecilkan sebelum analisis. Sokongan fail dan parameter bergantung pada kaedah aplikasi.
Tugasan ini menunjukkan gabungan analisis dan kejuruteraan: imej boleh digunakan sebagai bahan, manakala hasil teks sebagai kod atau penerangan penyelesaian. Pelaksanaan simulasi, pembinaan grafik dan penghasilan fail siap memerlukan alat persekitaran; model tidak mempunyai output imej atau video terbina dalam yang berasingan.
#### Kedalaman yang boleh dikawal
Penaakulan adaptif diaktifkan secara lalai, dengan tahap standard `effort` — `high`. `low`, `medium`, `high`, `xhigh` dan `max` disokong. Pada tahap `high` dan ke bawah, penaakulan boleh dimatikan, manakala pada `xhigh` dan `max` penaakulan wajib digunakan. extended thinking manual dengan bajet berasingan tidak disediakan bagi versi ini.
Perubahan tahap usaha mempengaruhi jumlah penaakulan, tetapi bukan cara yang boleh dipercayai untuk menentukan panjang teks yang kelihatan. Jika respons ringkas atau struktur tertentu diperlukan, nyatakannya dalam arahan itu sendiri. Konteks ialah **1 juta token**, dengan respons maksimum dalam mod biasa sebanyak **128 ribu token**; analisis mendalam memerlukan ruang untuk penaakulan dan kandungan akhir.
#### Tugasan saintifik dan sensitif
Batas pengetahuan terbina dalam yang boleh dipercayai ialah **Mei 2026**. Antara bidang saintifik yang diterangkan oleh Anthropic ialah biologi struktur, kimia organik dan bioinformatik. Namun, pengeluar menyatakan batasan ketara dalam penyelidikan biologi kendiri yang panjang; keupayaan membincangkan bahan saintifik tidak bermaksud setiap penyelidikan boleh diselesaikan secara autonomi.
Mekanisme perlindungan membenarkan pencarian ralat dalam kod sumber, tetapi mengehadkan sesetengah tugasan sensitif. Maklumat semasa memerlukan bahan yang diberikan atau carian, manakala hasil teknikal dan saintifik perlu diperiksa dalam persekitaran bidang berkenaan.
Tugas praktikal
### Tugas praktikal
Contoh teknikal dalam bahasa Inggeris
```
Diagnose an ambiguous date parser
A parser uses date.split('/').map(Number) and interprets every value as month/day/year. Requirements: the import format is day/month/year, and impossible dates must be rejected. For inputs 13/02/2026, 02/03/2026 and 31/02/2026, propose a corrected parser and a test table. Explain how validation avoids silent date rollover.
```
#### Hasil yang dijangka
```
Corrected code, a three-row expected-outcome table and a brief explanation of calendar validation.
```
#### Semak hasil
```
Verify the invalid February date is rejected and the ambiguous valid date means 2 March.
```
**Ailoot · Anthropic Messages** `POST /v1/messages` `claude-opus-5`
[`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=messages)
Anthropic /`claude-opus-5`
### Pengenalan
Claude Opus 5 direka untuk pembangunan yang teliti, analisis maklumat dan kerja profesional berbilang langkah. Menyokong penaakulan adaptif dan pemeriksaan hasil menggunakan alat aplikasi.
Input yang diterima
Teks · Imej
Hasil
Teks
### Tersedia di Ailoot · input & kaedah
**Ailoot · Anthropic Messages** `POST /v1/messages`
Input
`text`, `image`
Output
`text`
Konteks
1,000,000 tokens
Output maksimum
131,072 tokens
Format output
json atau SSE
| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had claude-opus-5 | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
| Medan`messages[].content` | Jenis`string\|content_block[]` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`system` | Jenis`string\|content_block[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanDiperlukan | Nilai & had Minimum: 1 Had terpakai pada: had maksimum tepat bagi model/kad yang dipilih | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`stop_sequences` | Jenis`string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].name` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: alat dibekalkan | Lalai— |
| Medan`tools[].description` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tools[].input_schema` | Jenis`JSON_schema` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tool_choice` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`thinking.type` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`thinking.budget_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`output_config.effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`metadata` | Jenis`object` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`cache_control` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Gabungan bahan input
**Teks** · Teks UTF8
`messages[].content atau blok type=text`
**Teks + imej**
`{type:image,source:{type:base64,media_type,data}} atau sumber dengan type=url`
Parameter kaedah dan kitar hayat
| Parameter | Kontrak |
| --- | --- |
| Parameter`material_types` | Kontraktext, image |
| Parameter`required` | Kontrakmodel, messages, max\_tokens |
| Parameter`optional_controls` | Kontraknull |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`text_file_material` | Kontrakkandungan UTF-8 sebenar dimasukkan sebagai teks; ID fail atau alamat URL (URLs) memerlukan sokongan tepat yang berasingan |
Kitar hayat: `exact retained published method`
Struktur kaedah dan ID adalah tepat; keupayaan pembekal berasingan daripada penerimaan permintaan.
### Pelan harga
#### Kadar kaedah Ailoot
Input
USD 0.005 */ 1K*
Output
USD 0.025 */ 1K*
Bacaan cache
USD 0.0005 */ 1K*
Penulisan cache
USD 0.00625 */ 1K*
Penulisan cache, 5 minit
USD 0.00625 */ 1K tokens*
Penulisan cache, 1 jam
USD 0.01 */ 1K tokens*
web\_search\_call
USD 0.01 *bagi setiap panggilan*
Panggilan maksimum web\_search\_call
8
Pengganda fast
×2
Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)
#### Butiran tarif rujukan
Jadual rujukan peringkat model tidak mengubah pemilihan kaedah, sebut harga atau caj. Caj aktif menggunakan kadar kaedah Ailoot yang dipilih.
Jadual rujukan model
#### Harga mengikut konfigurasi
Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.
| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiOpenAI Chat · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiOpenAI Chat · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiAnthropic Messages · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiAnthropic Messages · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
### Contoh permintaan
#### Ailoot · Anthropic Messages
Contoh teksInput, imejPython SDKNode.js SDKPenstriman Python
```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "claude-opus-5", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
-H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```
```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "claude-opus-5", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
-H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```
```python
import anthropic
import os
if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
model="claude-opus-5",
max_tokens=1024,
messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
save_result(msg.to_dict(mode="json"))
```
```js
import Anthropic from "@anthropic-ai/sdk";
if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
model: "claude-opus-5",
max_tokens: 1024,
messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";
function saveResult(data, stem = "result") {
writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
console.log(JSON.stringify(data, null, 2));
const saveBlob = (encoded, suffix, label) => {
const raw = Buffer.from(encoded, "base64");
const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
const file = `${stem}-${label}.${ext}`;
writeFileSync(file, raw); console.log("Saved", file);
};
for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
for (const [i, item] of (data.output || []).entries()) {
console.log("Output", i, JSON.stringify(item));
if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
}
for (const [ci, candidate] of (data.candidates || []).entries()) {
for (const [pi, part] of (candidate.content?.parts || []).entries()) {
console.log("Candidate/part", ci, pi, JSON.stringify(part));
const blob = part.inlineData || part.inline_data;
if (blob?.data) {
const mime = blob.mimeType || blob.mime_type;
const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
}
}
}
}
saveResult(msg);
```
```python
import anthropic,os
from pathlib import Path
if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
with client.messages.stream(model='claude-opus-5',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
for event in stream:
payload=event.to_dict(mode="json")
log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
print(json.dumps(payload,ensure_ascii=False))
final=stream.get_final_message()
save_result(final.to_dict(mode="json"),"stream-result")
```
### Terima dan simpan hasil
#### Ailoot · Anthropic Messages
json atau SSE
##### Simpan semua hasil yang selesai
Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.
Kekalkan semua blok kandungan, tandatangan penaakulan dan ID penggunaan alat sebenar. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan output.
##### Jika respons asal perlu disemak
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
Medan respons
| Medan | Jenis |
| --- | --- |
| Medan`id` | Jenisstring |
| Medan`model` | Jenisstring |
| Medan`content[]` | Jenistext\|thinking\|tool\_use\|other content block |
| Medan`stop_reason` | Jenisstring\|null |
| Medan`usage` | Jenisobject |
Ralat dan langkah seterusnya
| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |
### Alias
#### Alias model
Ailoot [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=messages)
**Ailoot Ultra** [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=messages), [`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=messages)
#### Alias laluan kaedah
`/chat/completions`
#### ID pemanggil berkaitan
[`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=messages), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=messages), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=messages)
**Ailoot · OpenAI Responses** `POST /v1/responses` `claude-opus-5`
[`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=responses)
Anthropic /`claude-opus-5`
### Pengenalan
Claude Opus 5 direka untuk pembangunan yang teliti, analisis maklumat dan kerja profesional berbilang langkah. Menyokong penaakulan adaptif dan pemeriksaan hasil menggunakan alat aplikasi.
Input yang diterima
Teks · Imej
Hasil
Teks
### Tersedia di Ailoot · input & kaedah
**Ailoot · OpenAI Responses** `POST /v1/responses`
Input
`text`, `image`
Output
`text`
Konteks
1,000,000 tokens
Output maksimum
131,072 tokens
Format output
json atau SSE
| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had claude-opus-5 | Lalai— |
| Medan`input` | Jenis`string\|input_item[]` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`instructions` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`input[].type` | Jenis`string` | KeperluanPilihan | Nilai & had message, reasoning, function\_call, function\_call\_output | Lalai— |
| Medan`input[].content` | Jenis`string\|content_part[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`input[].call_id` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: function\_call\_output; kekalkan call\_id sebenar yang dipulangkan | Lalai— |
| Medan`input[].output` | Jenis`string\|content_part[]` | KeperluanPilihan | Nilai & had Terpakai apabila: function\_call\_output | Lalai— |
| Medan`max_output_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tool_choice` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`parallel_tool_calls` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning.effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning.summary` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`text.format` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`text.verbosity` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`include` | Jenis`string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`store` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`previous_response_id` | Jenis`string` | KeperluanPilihan | Nilai & had Keperluan ID: Hanya ID respons sebenar daripada penerusan yang disokong Bergantung pada model | Lalai— |
| Medan`service_tier` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`prompt_cache_key` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`prompt_cache_options` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Gabungan bahan input
**Teks** · Teks UTF8
`Teks input atau bahagian input_text`
**Teks + imej**
`{type:input_image,image_url}`
Parameter kaedah dan kitar hayat
| Parameter | Kontrak |
| --- | --- |
| Parameter`material_types` | Kontraktext, image |
| Parameter`required` | Kontrakmodel, input |
| Parameter`optional_controls` | Kontraknull |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`text_file_material` | Kontrakkandungan UTF-8 sebenar dimasukkan sebagai teks; ID fail atau alamat URL (URLs) memerlukan sokongan tepat yang berasingan |
Kitar hayat: `exact retained published method`
Struktur kaedah dan ID adalah tepat; keupayaan pembekal berasingan daripada penerimaan permintaan.
### Pelan harga
#### Kadar kaedah Ailoot
Input
USD 0.005 */ 1K*
Output
USD 0.025 */ 1K*
Bacaan cache
USD 0.0005 */ 1K*
Penulisan cache
USD 0.00625 */ 1K*
Penulisan cache, 5 minit
USD 0.00625 */ 1K tokens*
Penulisan cache, 1 jam
USD 0.01 */ 1K tokens*
web\_search\_call
USD 0.01 *bagi setiap panggilan*
Panggilan maksimum web\_search\_call
8
Pengganda fast
×2
Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)
#### Butiran tarif rujukan
Jadual rujukan peringkat model tidak mengubah pemilihan kaedah, sebut harga atau caj. Caj aktif menggunakan kadar kaedah Ailoot yang dipilih.
Jadual rujukan model
#### Harga mengikut konfigurasi
Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.
| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiOpenAI Chat · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiOpenAI Chat · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiAnthropic Messages · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiAnthropic Messages · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
### Contoh permintaan
#### Ailoot · OpenAI Responses
Contoh teksInput, imejPython SDKNode.js SDKPenstriman Python
```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "claude-opus-5", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
-H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```
```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "claude-opus-5", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
-H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```
```python
from openai import OpenAI
import os
if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="claude-opus-5", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
save_result(resp.to_dict(mode="json"))
```
```js
import OpenAI from "openai";
if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "claude-opus-5", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";
function saveResult(data, stem = "result") {
writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
console.log(JSON.stringify(data, null, 2));
const saveBlob = (encoded, suffix, label) => {
const raw = Buffer.from(encoded, "base64");
const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
const file = `${stem}-${label}.${ext}`;
writeFileSync(file, raw); console.log("Saved", file);
};
for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
for (const [i, item] of (data.output || []).entries()) {
console.log("Output", i, JSON.stringify(item));
if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
}
for (const [ci, candidate] of (data.candidates || []).entries()) {
for (const [pi, part] of (candidate.content?.parts || []).entries()) {
console.log("Candidate/part", ci, pi, JSON.stringify(part));
const blob = part.inlineData || part.inline_data;
if (blob?.data) {
const mime = blob.mimeType || blob.mime_type;
const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
}
}
}
}
saveResult(resp);
```
```python
from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="claude-opus-5", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
for event in stream:
payload=event.to_dict(mode="json")
log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
print(json.dumps(payload,ensure_ascii=False))
final=stream.get_final_response()
save_result(final.to_dict(mode="json"),"stream-result")
```
### Terima dan simpan hasil
#### Ailoot · OpenAI Responses
json atau SSE
##### Simpan semua hasil yang selesai
Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.
Kekalkan setiap item output dan bahagian kandungan, call\_id fungsi sebenar, penaakulan disulitkan serta data penggunaan. Semasa penstriman, kekalkan identiti peristiwa/item yang lengkap.
##### Jika respons asal perlu disemak
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
Medan respons
| Medan | Jenis |
| --- | --- |
| Medan`id` | Jenisstring |
| Medan`status` | Jenisstring |
| Medan`output[]` | Jenismessage\|reasoning\|function\_call\|other item |
| Medan`output[].content[]` | Jeniscontent part |
| Medan`usage` | Jenisobject |
Ralat dan langkah seterusnya
| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |
### Alias
#### Alias model
Ailoot [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=responses)
**Ailoot Ultra** [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5), [`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5)
#### Alias laluan kaedah
`/chat/completions`
#### ID pemanggil berkaitan
[`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=responses), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5)
**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `claude-opus-5`
[`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=chat)
Anthropic /`claude-opus-5`
### Pengenalan
Claude Opus 5 direka untuk pembangunan yang teliti, analisis maklumat dan kerja profesional berbilang langkah. Menyokong penaakulan adaptif dan pemeriksaan hasil menggunakan alat aplikasi.
Input yang diterima
Teks · Imej
Hasil
Teks
### Tersedia di Ailoot · input & kaedah
**Ailoot · OpenAI Chat** `POST /v1/chat/completions`
Input
`text`, `image`
Output
`text`
Konteks
1,000,000 tokens
Output maksimum
131,072 tokens
Format output
json atau SSE
| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had claude-opus-5 | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had Contoh: system, user, assistant, tool, function Syarat: Peranan ini diwakili secara eksplisit oleh jenis keserasian dalam kod sumber; set peranan model yang tepat kekal khusus untuk setiap model. Bergantung pada model | Lalai— |
| Medan`messages[].content` | Jenis`string\|content_part[]\|null` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_calls` | Jenis`tool_call[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_call_id` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: role=tool; gunakan ID sebenar yang dipulangkan | Lalai— |
| Medan`messages[].name` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].reasoning_content` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: Hantar semula penaakulan sebenar yang dipulangkan apabila model ini menggunakannya | Lalai— |
| Medan`messages[].reasoning_details` | Jenis`object\|array` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`max_completion_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`stream_options.include_usage` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`stop` | Jenis`string\|string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`function_tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].type` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].function.name` | Jenis`string` | KeperluanDiperlukan | Nilai & had Terpakai apabila: alat fungsi dibekalkan | Lalai— |
| Medan`tools[].function.description` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tools[].function.parameters` | Jenis`JSON_schema` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tool_choice` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`parallel_tool_calls` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`response_format` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning_effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`service_tier` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`instructions` | Jenis`string` | KeperluanPilihan | Nilai & had Medan keserasian | Lalai— |
| Medan`functions` | Jenis`function[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`function_call` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`prompt_cache_options` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Gabungan bahan input
**Teks** · Teks UTF8
`messages[].content`
**Teks + imej**
`{type:image_url,image_url:{url,detail}}`
Parameter kaedah dan kitar hayat
| Parameter | Kontrak |
| --- | --- |
| Parameter`material_types` | Kontraktext, image |
| Parameter`required` | Kontrakmodel, messages |
| Parameter`optional_controls` | Kontraknull |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`text_file_material` | Kontrakkandungan UTF-8 sebenar dimasukkan sebagai teks; ID fail atau alamat URL (URLs) memerlukan sokongan tepat yang berasingan |
Kitar hayat: `exact retained published method`
Struktur kaedah dan ID adalah tepat; keupayaan pembekal berasingan daripada penerimaan permintaan.
### Pelan harga
#### Kadar kaedah Ailoot
Input
USD 0.005 */ 1K*
Output
USD 0.025 */ 1K*
Bacaan cache
USD 0.0005 */ 1K*
Penulisan cache
USD 0.00625 */ 1K*
Penulisan cache, 5 minit
USD 0.00625 */ 1K tokens*
Penulisan cache, 1 jam
USD 0.01 */ 1K tokens*
web\_search\_call
USD 0.01 *bagi setiap panggilan*
Panggilan maksimum web\_search\_call
8
Pengganda fast
×2
Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)
#### Butiran tarif rujukan
Jadual rujukan peringkat model tidak mengubah pemilihan kaedah, sebut harga atau caj. Caj aktif menggunakan kadar kaedah Ailoot yang dipilih.
Jadual rujukan model
#### Harga mengikut konfigurasi
Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.
| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiOpenAI Chat · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiOpenAI Chat · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiAnthropic Messages · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiAnthropic Messages · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
### Contoh permintaan
#### Ailoot · OpenAI Chat
Contoh teksInput, imejPython SDKNode.js SDKPenstriman Python
```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "claude-opus-5", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
-H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```
```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "claude-opus-5", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
-H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```
```python
from openai import OpenAI
import os
if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
model="claude-opus-5",
messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
save_result(resp.to_dict(mode="json"))
```
```js
import OpenAI from "openai";
if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
model: "claude-opus-5",
messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";
function saveResult(data, stem = "result") {
writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
console.log(JSON.stringify(data, null, 2));
const saveBlob = (encoded, suffix, label) => {
const raw = Buffer.from(encoded, "base64");
const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
const file = `${stem}-${label}.${ext}`;
writeFileSync(file, raw); console.log("Saved", file);
};
for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
for (const [i, item] of (data.output || []).entries()) {
console.log("Output", i, JSON.stringify(item));
if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
}
for (const [ci, candidate] of (data.candidates || []).entries()) {
for (const [pi, part] of (candidate.content?.parts || []).entries()) {
console.log("Candidate/part", ci, pi, JSON.stringify(part));
const blob = part.inlineData || part.inline_data;
if (blob?.data) {
const mime = blob.mimeType || blob.mime_type;
const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
}
}
}
}
saveResult(resp);
```
```python
from openai import OpenAI
import os
from pathlib import Path
if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
with client.chat.completions.stream(model='claude-opus-5',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
for event in stream:
payload=event.to_dict(mode="json")
log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
print(json.dumps(payload,ensure_ascii=False))
final=stream.get_final_completion()
save_result(final.to_dict(mode="json"),"stream-result")
```
### Terima dan simpan hasil
#### Ailoot · OpenAI Chat
json atau SSE
##### Simpan semua hasil yang selesai
Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.
Kekalkan setiap pilihan jawapan bersama kandungan, panggilan alat dan penaakulannya. Dalam SSE, gabungkan delta mengikut indeks pilihan jawapan/alat dan kekalkan sebab penamatan akhir serta data penggunaan.
##### Jika respons asal perlu disemak
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
Medan respons
| Medan | Jenis |
| --- | --- |
| Medan`choices[].index` | Jenisinteger |
| Medan`choices[].message.content` | Jenisstring\|null |
| Medan`choices[].message.tool_calls` | Jenistool\_call\[\] |
| Medan`choices[].message.reasoning_content` | Jenisstring |
| Medan`choices[].message.reasoning_details` | Jenisobject\|array |
| Medan`choices[].finish_reason` | Jenisstring\|null |
| Medan`usage` | Jenisobject |
Ralat dan langkah seterusnya
| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |
### Alias
#### Alias model
Ailoot [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=chat)
**Ailoot Ultra** [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=chat), [`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=chat)
#### Alias laluan kaedah
`/chat/completions`
#### ID pemanggil berkaitan
[`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=chat), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=chat), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=chat)
**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `claude-opus-5`
[`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=chat)
Anthropic /`claude-opus-5`
ID model
- `claude-opus-5`
- `anthropic/claude-opus-5`
### Pengenalan
Claude Opus 5 direka untuk pembangunan yang teliti, analisis maklumat dan kerja profesional berbilang langkah. Menyokong penaakulan adaptif dan pemeriksaan hasil menggunakan alat aplikasi.
Input yang diterima
Teks
Hasil
Teks
### Tersedia di Ailoot · input & kaedah
**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions`
Input
`text`
Output
`text`
Format output
json atau SSE
| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had claude-opus-5 | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had Bergantung pada model | Lalai— |
| Medan`messages[].content` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: Perbualan teks | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
Gabungan bahan input
**Teks** · Teks UTF8
`messages[].content`
Parameter kaedah dan kitar hayat
| Parameter | Kontrak |
| --- | --- |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`required` | Kontrakmodel, messages |
| Parameter`material_types` | Kontraktext |
| Parameter`messages` | Kontraktatasusunan mesej dengan struktur role/content |
| Parameter`file_material` | Kontrakdokumen UTF-8 sebenar dimasukkan sebagai teks literal; ID fail tidak diandaikan |
| Parameter`optional_controls` | Kontrakstream |
| Parameter`control_scope` | KontrakPerbualan teks; stream ialah nilai boolean dengan false sebagai lalai. |
| Parameter`output_modalities` | Kontraktext |
| Parameter`hosted_operations` | Kontrakfalse |
| Parameter`multimodal_input_binding` | Kontraknull |
Alias kaedah: `/chat/completions`
Kitar hayat: `synchronous_or_streamed`
Hantar ID model yang tepat bersama messages.
Panjang konteks bukan had output.
Fail teks boleh membekalkan teks literal; input imej/audio/objek fail memerlukan pengikatan tepat.
### Pelan harga
Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.
Mod pantas
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
Usaha penaakulan · high
Kadar standard Apabila usaha penaakulan ditetapkan kepada high
Usaha penaakulan · low
Kadar standard Apabila usaha penaakulan ditetapkan kepada low
Usaha penaakulan · max
Kadar standard Apabila usaha penaakulan ditetapkan kepada max
Usaha penaakulan · medium
Kadar standard Apabila usaha penaakulan ditetapkan kepada medium
Usaha penaakulan · xhigh
Kadar standard Apabila usaha penaakulan ditetapkan kepada xhigh
#### Kadar Ailoot
#### Harga mengikut konfigurasi
Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.
| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiKadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiTahap panjang permintaan 1 | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)
### Contoh permintaan
#### Ailoot Ultra · OpenAI Chat
curlPython SDK
```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model":"claude-opus-5","messages":[{"role":"user","content":"hello"}],"stream":false}')
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
-H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("choices",[]):
if x.get("message",{}).get("content"): print(x["message"]["content"])
PY_RESULT
```
```python
from openai import OpenAI
import os
if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.chat.completions.create(model="claude-opus-5", messages=[{"role":"user","content":"hello"}], stream=False)
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
save_result(result.to_dict(mode="json"))
```
### Terima dan simpan hasil
#### Ailoot Ultra · OpenAI Chat
json atau SSE
##### Simpan semua hasil yang selesai
Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.
Kekalkan setiap pilihan jawapan bersama kandungan, panggilan alat dan penaakulannya. Dalam SSE, gabungkan delta mengikut indeks pilihan jawapan/alat dan kekalkan sebab penamatan akhir serta data penggunaan.
##### Jika respons asal perlu disemak
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
Medan respons
| Medan | Jenis |
| --- | --- |
| Medan`choices[].index` | Jenisinteger |
| Medan`choices[].message.content` | Jenisstring\|null |
| Medan`choices[].message.tool_calls` | Jenistool\_call\[\] |
| Medan`choices[].message.reasoning_content` | Jenisstring |
| Medan`choices[].message.reasoning_details` | Jenisobject\|array |
| Medan`choices[].finish_reason` | Jenisstring\|null |
| Medan`usage` | Jenisobject |
Ralat dan langkah seterusnya
| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |
### Alias
#### Alias model
Ailoot [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=chat)
**Ailoot Ultra** [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=chat), [`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=chat)
#### Alias laluan kaedah
`/chat/completions`
#### ID pemanggil berkaitan
[`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=chat), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=chat), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=chat)
**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `claude-opus-5`
[`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=messages)
Anthropic /`claude-opus-5`
ID model
- `claude-opus-5`
- `anthropic/claude-opus-5`
### Pengenalan
Claude Opus 5 direka untuk pembangunan yang teliti, analisis maklumat dan kerja profesional berbilang langkah. Menyokong penaakulan adaptif dan pemeriksaan hasil menggunakan alat aplikasi.
Input yang diterima
Teks
Hasil
json · sse
### Tersedia di Ailoot · input & kaedah
**Ailoot Ultra · Anthropic Messages** `POST /v1/messages`
Input
`text`
Output
`json`, `sse`
Format output
JSON atau SSE
| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had claude-opus-5 | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
| Medan`messages[].content` | Jenis`string` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
Gabungan bahan input
**Teks** · Teks UTF-8
`rentetan messages[].content`
Parameter kaedah dan kitar hayat
| Parameter | Kontrak |
| --- | --- |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`required` | Kontrakmodel, messages, max\_tokens |
| Parameter`optional_controls` | Kontrakstream |
| Parameter`material_types` | Kontraktext |
| Parameter`text_file_material` | KontrakBaca dokumen UTF-8 sebenar dan letakkan teksnya dalam rentetan input atau kandungan mesej yang ditunjukkan. |
Kitar hayat: `synchronous_or_streamed`
### Pelan harga
Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.
Mod pantas
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
Usaha penaakulan · high
Kadar standard Apabila usaha penaakulan ditetapkan kepada high
Usaha penaakulan · low
Kadar standard Apabila usaha penaakulan ditetapkan kepada low
Usaha penaakulan · max
Kadar standard Apabila usaha penaakulan ditetapkan kepada max
Usaha penaakulan · medium
Kadar standard Apabila usaha penaakulan ditetapkan kepada medium
Usaha penaakulan · xhigh
Kadar standard Apabila usaha penaakulan ditetapkan kepada xhigh
#### Kadar Ailoot
#### Harga mengikut konfigurasi
Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.
| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiKadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiTahap panjang permintaan 1 | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)
### Contoh permintaan
#### Ailoot Ultra · Anthropic Messages
Badan JSON minimum yang lengkapcurl · gunakan dokumen UTF-8 andaPython · simpan hasil lengkap
```json
{
"model": "claude-opus-5",
"max_tokens": 128,
"messages": [
{
"role": "user",
"content": "Summarize the incident report."
}
],
"stream": false
}
```
```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json, os
from pathlib import Path
source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
raise SystemExit('Choose a document containing text')
payload = {'model': 'claude-opus-5', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
-H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
PY_RESULT
```
```python
import json, os
from pathlib import Path
source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
raise SystemExit('Choose a document containing text')
payload = {'model': 'claude-opus-5', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
from urllib.request import Request, urlopen
from urllib.error import HTTPError
api_key = os.environ['AILOOT_API_KEY']
if not api_key.strip():
raise SystemExit('Set AILOOT_API_KEY before making a request')
headers = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}
headers['x-api-key'] = api_key
request = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')
try:
with urlopen(request, timeout=120) as response:
raw = response.read()
Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')
except HTTPError as error:
Path('result.json').write_bytes(error.read())
Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')
raise
Path('result.json').write_bytes(raw)
import json
from pathlib import Path
result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
```
### Terima dan simpan hasil
#### Ailoot Ultra · Anthropic Messages
JSON atau SSE
##### Simpan semua hasil yang selesai
Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.
Kekalkan semua blok kandungan, tandatangan penaakulan dan ID penggunaan alat sebenar. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan output.
##### Jika respons asal perlu disemak
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
Medan respons
| Medan | Jenis |
| --- | --- |
| Medan`id` | Jenisstring |
| Medan`model` | Jenisstring |
| Medan`content[]` | Jenistext\|thinking\|tool\_use\|other content block |
| Medan`stop_reason` | Jenisstring\|null |
| Medan`usage` | Jenisobject |
Ralat dan langkah seterusnya
| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |
### Alias
#### Alias model
Ailoot [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=messages)
**Ailoot Ultra** [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=messages), [`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=messages)
#### Alias laluan kaedah
`/chat/completions`
#### ID pemanggil berkaitan
[`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=messages), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=messages), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=messages)
**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `anthropic/claude-opus-5`
[`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=chat)
Anthropic /`anthropic/claude-opus-5`
ID model
- `claude-opus-5`
- `anthropic/claude-opus-5`
### Pengenalan
Claude Opus 5 direka untuk pembangunan yang teliti, analisis maklumat dan kerja profesional berbilang langkah. Menyokong penaakulan adaptif dan pemeriksaan hasil menggunakan alat aplikasi.
Input yang diterima
Teks
Hasil
Teks
### Tersedia di Ailoot · input & kaedah
**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions`
Input
`text`
Output
`text`
Format output
json atau SSE
| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had anthropic/claude-opus-5 | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had Contoh: system, user, assistant, tool, function Syarat: Peranan ini diwakili secara eksplisit oleh jenis keserasian dalam kod sumber; set peranan model yang tepat kekal khusus untuk setiap model. Bergantung pada model | Lalai— |
| Medan`messages[].content` | Jenis`string\|content_part[]\|null` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_calls` | Jenis`tool_call[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_call_id` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: role=tool; gunakan ID sebenar yang dipulangkan | Lalai— |
| Medan`messages[].name` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].reasoning_content` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: Hantar semula penaakulan sebenar yang dipulangkan apabila model ini menggunakannya | Lalai— |
| Medan`messages[].reasoning_details` | Jenis`object\|array` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`max_completion_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`stream_options.include_usage` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`stop` | Jenis`string\|string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`function_tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].type` | Jenis`string` | KeperluanPilihan | Nilai & had function Bergantung pada model | Lalai— |
| Medan`tools[].function.name` | Jenis`string` | KeperluanDiperlukan | Nilai & had Terpakai apabila: alat fungsi dibekalkan | Lalai— |
| Medan`tools[].function.description` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tools[].function.parameters` | Jenis`JSON_schema` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tool_choice` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`parallel_tool_calls` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`response_format` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning_effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`service_tier` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`instructions` | Jenis`string` | KeperluanPilihan | Nilai & had Medan keserasian | Lalai— |
| Medan`functions` | Jenis`function[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`function_call` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`prompt_cache_options` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`modalities` | Jenis`string[]` | KeperluanPilihan | Nilai & had text | Lalai— |
| Medan`provider` | Jenis`object` | KeperluanPilihan | Nilai & had Syarat: provider.options ditolak pada laluan teks Ultra ini | Lalai— |
| Medan`cache_control.ttl` | Jenis`string` | KeperluanPilihan | Nilai & had Syarat: 1h ditolak pada lokasi cache prompt yang digunakan | Lalai— |
Gabungan bahan input
**Teks** · Teks UTF8
`messages[].content`
Parameter kaedah dan kitar hayat
| Parameter | Kontrak |
| --- | --- |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`required` | Kontrakmodel, messages |
| Parameter`material_types` | Kontraktext |
| Parameter`messages` | Kontraktatasusunan mesej dengan struktur role/content |
| Parameter`file_material` | Kontrakdokumen UTF-8 sebenar dimasukkan sebagai teks literal; ID fail tidak diandaikan |
| Parameter`optional_controls` | Kontrakstream, temperature, top\_p, stop, max\_tokens, max\_completion\_tokens, reasoning, response\_format, tools, tool\_choice |
| Parameter`control_scope` | Kontrakkhusus model; alat fungsi pengguna berbeza daripada alat yang dihoskan |
| Parameter`output_modalities` | Kontraktext |
| Parameter`hosted_operations` | Kontrakfalse |
| Parameter`multimodal_input_binding` | Kontraknull |
Kitar hayat: `synchronous_or_streamed`
Hantar ID model yang tepat bersama messages.
Panjang konteks bukan had output.
Fail teks boleh membekalkan teks literal; input imej/audio/objek fail memerlukan pengikatan tepat.
### Pelan harga
Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.
Mod pantas
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
Usaha penaakulan · high
Kadar standard Apabila usaha penaakulan ditetapkan kepada high
Usaha penaakulan · low
Kadar standard Apabila usaha penaakulan ditetapkan kepada low
Usaha penaakulan · max
Kadar standard Apabila usaha penaakulan ditetapkan kepada max
Usaha penaakulan · medium
Kadar standard Apabila usaha penaakulan ditetapkan kepada medium
Usaha penaakulan · xhigh
Kadar standard Apabila usaha penaakulan ditetapkan kepada xhigh
#### Kadar Ailoot
#### Harga mengikut konfigurasi
Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.
| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiKadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiTahap panjang permintaan 1 | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)
### Contoh permintaan
#### Ailoot Ultra · OpenAI Chat
curlPython SDKPenstriman Python
```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "anthropic/claude-opus-5", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
-H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("choices",[]):
if x.get("message",{}).get("content"): print(x["message"]["content"])
PY_RESULT
```
```python
from openai import OpenAI
import os
if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.chat.completions.create(model='anthropic/claude-opus-5',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
save_result(result.to_dict(mode="json"))
```
```python
from openai import OpenAI
import os
from pathlib import Path
if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
with client.chat.completions.stream(model='anthropic/claude-opus-5',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
for event in stream:
payload=event.to_dict(mode="json")
log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
print(json.dumps(payload,ensure_ascii=False))
final=stream.get_final_completion()
save_result(final.to_dict(mode="json"),"stream-result")
```
### Terima dan simpan hasil
#### Ailoot Ultra · OpenAI Chat
json atau SSE
##### Simpan semua hasil yang selesai
Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.
Kekalkan setiap pilihan jawapan bersama kandungan, panggilan alat dan penaakulannya. Dalam SSE, gabungkan delta mengikut indeks pilihan jawapan/alat dan kekalkan sebab penamatan akhir serta data penggunaan.
##### Jika respons asal perlu disemak
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
Medan respons
| Medan | Jenis |
| --- | --- |
| Medan`choices[].index` | Jenisinteger |
| Medan`choices[].message.content` | Jenisstring\|null |
| Medan`choices[].message.tool_calls` | Jenistool\_call\[\] |
| Medan`choices[].message.reasoning_content` | Jenisstring |
| Medan`choices[].message.reasoning_details` | Jenisobject\|array |
| Medan`choices[].finish_reason` | Jenisstring\|null |
| Medan`usage` | Jenisobject |
Ralat dan langkah seterusnya
| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |
### Alias
#### Alias model
Ailoot [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=chat)
**Ailoot Ultra** [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=chat), [`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=chat)
#### Alias laluan kaedah
`/chat/completions`
#### ID pemanggil berkaitan
[`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=chat), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=chat), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=chat)
**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `anthropic/claude-opus-5`
[`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=messages)
Anthropic /`anthropic/claude-opus-5`
ID model
- `claude-opus-5`
- `anthropic/claude-opus-5`
### Pengenalan
Claude Opus 5 direka untuk pembangunan yang teliti, analisis maklumat dan kerja profesional berbilang langkah. Menyokong penaakulan adaptif dan pemeriksaan hasil menggunakan alat aplikasi.
Input yang diterima
Teks
Hasil
json · sse
### Tersedia di Ailoot · input & kaedah
**Ailoot Ultra · Anthropic Messages** `POST /v1/messages`
Input
`text`
Output
`json`, `sse`
Format output
JSON atau SSE
| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had anthropic/claude-opus-5 | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
| Medan`messages[].content` | Jenis`string` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
Gabungan bahan input
**Teks** · Teks UTF-8
`rentetan messages[].content`
Parameter kaedah dan kitar hayat
| Parameter | Kontrak |
| --- | --- |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`required` | Kontrakmodel, messages, max\_tokens |
| Parameter`optional_controls` | Kontrakstream |
| Parameter`material_types` | Kontraktext |
| Parameter`text_file_material` | KontrakBaca dokumen UTF-8 sebenar dan letakkan teksnya dalam rentetan input atau kandungan mesej yang ditunjukkan. |
Kitar hayat: `synchronous_or_streamed`
### Pelan harga
Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.
Mod pantas
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
Usaha penaakulan · high
Kadar standard Apabila usaha penaakulan ditetapkan kepada high
Usaha penaakulan · low
Kadar standard Apabila usaha penaakulan ditetapkan kepada low
Usaha penaakulan · max
Kadar standard Apabila usaha penaakulan ditetapkan kepada max
Usaha penaakulan · medium
Kadar standard Apabila usaha penaakulan ditetapkan kepada medium
Usaha penaakulan · xhigh
Kadar standard Apabila usaha penaakulan ditetapkan kepada xhigh
#### Kadar Ailoot
#### Harga mengikut konfigurasi
Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.
| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiKadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
| KonfigurasiTahap panjang permintaan 1 | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.01** / 1K token Output · Token output **$0.05** / 1K token Input · Bacaan cache **$0.001** / 1K token Input · Penulisan cache **$0.0125** / 1K token Input · Penulisan cache, 1 jam **$0.02** / 1K token |
Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)
### Contoh permintaan
#### Ailoot Ultra · Anthropic Messages
Badan JSON minimum yang lengkapcurl · gunakan dokumen UTF-8 andaPython · simpan hasil lengkap
```json
{
"model": "anthropic/claude-opus-5",
"max_tokens": 128,
"messages": [
{
"role": "user",
"content": "Summarize the incident report."
}
],
"stream": false
}
```
```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json, os
from pathlib import Path
source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
raise SystemExit('Choose a document containing text')
payload = {'model': 'anthropic/claude-opus-5', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
-H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
PY_RESULT
```
```python
import json, os
from pathlib import Path
source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
raise SystemExit('Choose a document containing text')
payload = {'model': 'anthropic/claude-opus-5', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
from urllib.request import Request, urlopen
from urllib.error import HTTPError
api_key = os.environ['AILOOT_API_KEY']
if not api_key.strip():
raise SystemExit('Set AILOOT_API_KEY before making a request')
headers = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}
headers['x-api-key'] = api_key
request = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')
try:
with urlopen(request, timeout=120) as response:
raw = response.read()
Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')
except HTTPError as error:
Path('result.json').write_bytes(error.read())
Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')
raise
Path('result.json').write_bytes(raw)
import json
from pathlib import Path
result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
```
### Terima dan simpan hasil
#### Ailoot Ultra · Anthropic Messages
JSON atau SSE
##### Simpan semua hasil yang selesai
Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.
Kekalkan semua blok kandungan, tandatangan penaakulan dan ID penggunaan alat sebenar. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan output.
##### Jika respons asal perlu disemak
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
Medan respons
| Medan | Jenis |
| --- | --- |
| Medan`id` | Jenisstring |
| Medan`model` | Jenisstring |
| Medan`content[]` | Jenistext\|thinking\|tool\_use\|other content block |
| Medan`stop_reason` | Jenisstring\|null |
| Medan`usage` | Jenisobject |
Ralat dan langkah seterusnya
| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |
### Alias
#### Alias model
Ailoot [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=messages)
**Ailoot Ultra** [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=messages), [`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=messages)
#### Alias laluan kaedah
`/chat/completions`
#### ID pemanggil berkaitan
[`anthropic/claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=anthropic%2Fclaude-opus-5&fmt=messages), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Core&caller=claude-opus-5&fmt=messages), [`claude-opus-5`](https://ailoot.ai/models/ms/#m=anthropic%2Fclaude-opus-5&route=Ultra&caller=claude-opus-5&fmt=messages)
FAQ · Anthropic: Claude Opus 5
Apakah input dan hasil yang tersedia?
`POST /v1/messages` · `claude-opus-5`: `text`, `image` → `text` `POST /v1/responses` · `claude-opus-5`: `text`, `image` → `text` `POST /v1/chat/completions` · `claude-opus-5`: `text`, `image` → `text` `POST /v1/chat/completions` · `claude-opus-5`: `text` → `text` `POST /v1/messages` · `claude-opus-5`: `text` → `json`, `sse` `POST /v1/chat/completions` · `anthropic/claude-opus-5`: `text` → `text` `POST /v1/messages` · `anthropic/claude-opus-5`: `text` → `json`, `sse`
Apakah medan yang digunakan oleh permintaan?
`POST /v1/messages` · `claude-opus-5`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/responses` · `claude-opus-5`: `model`, `input`, `instructions`, `stream` `POST /v1/chat/completions` · `claude-opus-5`: `model`, `messages`, `stream` `POST /v1/chat/completions` · `claude-opus-5`: `model`, `messages`, `stream` `POST /v1/messages` · `claude-opus-5`: `model`, `messages`, `max_tokens`, `stream` `POST /v1/chat/completions` · `anthropic/claude-opus-5`: `model`, `messages`, `stream`, `modalities`, `provider` `POST /v1/messages` · `anthropic/claude-opus-5`: `model`, `messages`, `max_tokens`, `stream`
Apakah had yang terpakai?
`POST /v1/messages` · `claude-opus-5`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/responses` · `claude-opus-5`: `ctx`: `1000000`; `max_out`: `131072` `POST /v1/chat/completions` · `claude-opus-5`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1` `POST /v1/chat/completions` · `claude-opus-5`: `messages.min_items`: `1` `POST /v1/chat/completions` · `anthropic/claude-opus-5`: `messages.min_items`: `1`
Sambungkan Ailoot kepada Claude Code, OpenCode, Hermes atau aplikasi anda.
## Syarikat dan portfolio projeknya
Syarikat dan portfolio projeknya: jutaan pelanggan; jualan bernilai berbilion setiap bulan.
## Beli token dengan diskaun.
Diskaun langganan untuk penggunaan berkala. Kod promosi — sehingga 50% bagi pembelian token.
Langganan
Pilih pelan berdiskaun untuk permintaan berkala anda.
Kod promosi sehingga 50%
Masukkan kod semasa pembelian. Harga dikira semula mengikut promosi semasa.
Perbelanjaan dalam sejarah
Model, token dan jumlah disimpan bagi setiap permintaan.
[Pilih langganan](https://ailoot.ai/docs/ms/billing/subscriptions/) · [Lihat harga model](https://ailoot.ai/models/ms/)
## Sambungkan API kepada produk yang anda jual.
SaaS, aplikasi dan bot — di bawah tawaran rasmi serta perjanjian lesen Ailoot. Untuk jualan semula, mohon lesen penjual semula.
Aplikasi komersial
Tambahkan penjanaan teks, imej, video dan audio pada ciri berbayar perkhidmatan anda.
Lesen penjual semula
Hantar keterangan projek dan susunan akses. Minta terma penggunaan serta jualan semula secara bertulis.
Dokumen pada laman
Tawaran, perjanjian lesen dan dasar pemprosesan data tersedia sebelum sambungan.
[Mohon lesen penjual semula](mailto:support@ailoot.ai) · [Tawaran dan perjanjian lesen](https://ailoot.ai/legal/offer?lang=ms)
## Ailoot · Syarikat dan portfolio projeknya
Ailoot berteraskan pengalaman operasi yang mantap, pangkalan pelanggan yang besar, perkhidmatan yang stabil dan pemantauan KPI berterusan.
Syarikat dan portfolio projeknya: jutaan pelanggan; jualan bernilai berbilion setiap bulan.
Ailoot menggunakan pengalaman operasi ini untuk akses API kepada ciri AI dalam produk pelanggan, ejen, aplikasi dan automasi.