kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
", "aboutText": "### Pembangunan berpanjangan dengan output pantas\n\n`kimi-for-coding-highspeed` menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira **5–6 kali lebih pantas**.\n\nPengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.\n\n### Penaakulan dikekalkan antara langkah\n\nDalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.\n\n### Seni bina dan input\n\nK2.7 Code dibina sebagai campuran pakar dengan **1 trilion parameter** keseluruhan dan **32 bilion parameter aktif**. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah **262 144 token**.\n\nDalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.", "editorialOverlay": { "copy_fields": { "practical_html": "Contoh teknikal dalam bahasa Inggeris
Remove repeated lookups in a data-processing loop\n\nReview this pseudocode: for each order, fetch_customer(order.customer_id), then append the customer name to its export row. Many orders share a customer, and repeated fetches dominate runtime. Propose a scoped improvement that preserves row order and handles missing customers. Give a test with three orders sharing two customer IDs; do not claim execution.Revised pseudocode, an explanation of lookup reuse and tests for shared IDs and missing customers.The shared-ID test requires at most one lookup per distinct customer ID and unchanged export-row order.kimi-for-coding-highspeedKimi K2.7 Code yang dipercepat untuk pengaturcaraan berbilang langkah dan kerja projek besar.
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
POST /v1/messagestext, imagetext| Medan | Jenis | Keperluan | Nilai & had | Lalai |
|---|---|---|---|---|
Medanmodel | Jenisstring | KeperluanDiperlukan | Nilai & had kimi-for-coding-highspeed | Lalai— |
Medanmessages | Jenismessage[] | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
Medanmessages[].role | Jenisstring | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
Medanmessages[].content | Jenisstring|content_block[] | KeperluanDiperlukan | Nilai & had | Lalai— |
Medansystem | Jenisstring|content_block[] | KeperluanPilihan | Nilai & had | Lalai— |
Medanmax_tokens | Jenisinteger | KeperluanDiperlukan | Nilai & had Minimum: 1 Had terpakai pada: had maksimum tepat bagi model/kad yang dipilih | Lalai— |
Medanstream | Jenisboolean | KeperluanPilihan | Nilai & had | Lalaifalse |
Medantemperature | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantop_p | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanstop_sequences | Jenisstring[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools | Jenistool[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools[].name | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: alat dibekalkan | Lalai— |
Medantools[].description | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medantools[].input_schema | JenisJSON_schema | KeperluanPilihan | Nilai & had | Lalai— |
Medantool_choice | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanthinking.type | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanthinking.budget_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanoutput_config.effort | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanmetadata | Jenisobject | KeperluanPilihan | Nilai & had | Lalai— |
Medancache_control | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
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 | Kontrak |
|---|---|
Parametermaterial_types | Kontraktext, image |
Parameterrequired | Kontrakmodel, messages, max_tokens |
Parameteroptional_controls | Kontraknull |
Parametercontent_type | Kontrakapplication/json |
Parametertext_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.
POST /v1/messagesAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-for-coding-highspeed", "max_tokens": 1024, "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-for-coding-highspeed", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="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\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nimport anthropic\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nmsg = client.messages.create(\n model="kimi-for-coding-highspeed",\n max_tokens=1024,\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(msg.to_dict(mode="json"))\nimport Anthropic from "@anthropic-ai/sdk";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n model: "kimi-for-coding-highspeed",\n max_tokens: 1024,\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n 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;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(msg);\nimport anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.messages.stream(model='kimi-for-coding-highspeed',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_message()\n save_result(final.to_dict(mode="json"),"stream-result")\njson atau SSE
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.
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
| Medan | Jenis |
|---|---|
Medanid | Jenisstring |
Medanmodel | Jenisstring |
Medancontent[] | Jenistext|thinking|tool_use|other content block |
Medanstop_reason | Jenisstring|null |
Medanusage | Jenisobject |
| 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. |
Ailoot kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Gunakan laluan kaedah yang dipaparkan di atas.
kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
kimi-for-coding-highspeedKimi K2.7 Code yang dipercepat untuk pengaturcaraan berbilang langkah dan kerja projek besar.
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
POST /v1/responsestext, imagetext| Medan | Jenis | Keperluan | Nilai & had | Lalai |
|---|---|---|---|---|
Medanmodel | Jenisstring | KeperluanDiperlukan | Nilai & had kimi-for-coding-highspeed | Lalai— |
Medaninput | Jenisstring|input_item[] | KeperluanDiperlukan | Nilai & had | Lalai— |
Medaninstructions | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medaninput[].type | Jenisstring | KeperluanPilihan | Nilai & had message, reasoning, function_call, function_call_output | Lalai— |
Medaninput[].content | Jenisstring|content_part[] | KeperluanPilihan | Nilai & had | Lalai— |
Medaninput[].call_id | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: function_call_output; kekalkan call_id sebenar yang dipulangkan | Lalai— |
Medaninput[].output | Jenisstring|content_part[] | KeperluanPilihan | Nilai & had Terpakai apabila: function_call_output | Lalai— |
Medanmax_output_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
Medanstream | Jenisboolean | KeperluanPilihan | Nilai & had | Lalaifalse |
Medantemperature | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantop_p | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools | Jenistool[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantool_choice | Jenisstring|object | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanparallel_tool_calls | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning.effort | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning.summary | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantext.format | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantext.verbosity | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medaninclude | Jenisstring[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanstore | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprevious_response_id | Jenisstring | KeperluanPilihan | Nilai & had Keperluan ID: Hanya ID respons sebenar daripada penerusan yang disokong Bergantung pada model | Lalai— |
Medanservice_tier | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprompt_cache_key | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprompt_cache_options | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Teks · Teks UTF8
Teks input atau bahagian input_text
Teks + imej
{type:input_image,image_url}
| Parameter | Kontrak |
|---|---|
Parametermaterial_types | Kontraktext, image |
Parameterrequired | Kontrakmodel, input |
Parameteroptional_controls | Kontraknull |
Parametercontent_type | Kontrakapplication/json |
Parametertext_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.
POST /v1/responsesAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-for-coding-highspeed", "input": ""}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["input"]="Summarize this material and quote supporting source passages.\\n\\n"+text\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-for-coding-highspeed", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="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\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.responses.create(model="kimi-for-coding-highspeed", input="Explain the difference between an observation and a hypothesis in three sentences.")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: "kimi-for-coding-highspeed", input: "Explain the difference between an observation and a hypothesis in three sentences." });\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n 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;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nwith client.responses.stream(model="kimi-for-coding-highspeed", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_response()\n save_result(final.to_dict(mode="json"),"stream-result")\njson atau SSE
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.
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
| Medan | Jenis |
|---|---|
Medanid | Jenisstring |
Medanstatus | Jenisstring |
Medanoutput[] | Jenismessage|reasoning|function_call|other item |
Medanoutput[].content[] | Jeniscontent part |
Medanusage | Jenisobject |
| 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. |
Ailoot kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Gunakan laluan kaedah yang dipaparkan di atas.
kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
kimi-for-coding-highspeedKimi K2.7 Code yang dipercepat untuk pengaturcaraan berbilang langkah dan kerja projek besar.
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
POST /v1/chat/completionstext, imagetext| Medan | Jenis | Keperluan | Nilai & had | Lalai |
|---|---|---|---|---|
Medanmodel | Jenisstring | KeperluanDiperlukan | Nilai & had kimi-for-coding-highspeed | Lalai— |
Medanmessages | Jenismessage[] | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
Medanmessages[].role | Jenisstring | 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— |
Medanmessages[].content | Jenisstring|content_part[]|null | KeperluanPilihan | Nilai & had | Lalai— |
Medanmessages[].tool_calls | Jenistool_call[] | KeperluanPilihan | Nilai & had | Lalai— |
Medanmessages[].tool_call_id | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: role=tool; gunakan ID sebenar yang dipulangkan | Lalai— |
Medanmessages[].name | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medanmessages[].reasoning_content | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: Hantar semula penaakulan sebenar yang dipulangkan apabila model ini menggunakannya | Lalai— |
Medanmessages[].reasoning_details | Jenisobject|array | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanmax_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
Medanmax_completion_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
Medanstream | Jenisboolean | KeperluanPilihan | Nilai & had | Lalaifalse |
Medanstream_options.include_usage | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantemperature | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantop_p | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanstop | Jenisstring|string[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools | Jenisfunction_tool[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools[].type | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools[].function.name | Jenisstring | KeperluanDiperlukan | Nilai & had Terpakai apabila: alat fungsi dibekalkan | Lalai— |
Medantools[].function.description | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medantools[].function.parameters | JenisJSON_schema | KeperluanPilihan | Nilai & had | Lalai— |
Medantool_choice | Jenisstring|object | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanparallel_tool_calls | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanresponse_format | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning_effort | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanservice_tier | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medaninstructions | Jenisstring | KeperluanPilihan | Nilai & had Medan keserasian | Lalai— |
Medanfunctions | Jenisfunction[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanfunction_call | Jenisstring|object | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprompt_cache_options | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Teks · Teks UTF8
messages[].content
Teks + imej
{type:image_url,image_url:{url,detail}}
| Parameter | Kontrak |
|---|---|
Parametermaterial_types | Kontraktext, image |
Parameterrequired | Kontrakmodel, messages |
Parameteroptional_controls | Kontraknull |
Parametercontent_type | Kontrakapplication/json |
Parametertext_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.
POST /v1/chat/completionsAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-for-coding-highspeed", "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-for-coding-highspeed", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="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\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.chat.completions.create(\n model="kimi-for-coding-highspeed",\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n model: "kimi-for-coding-highspeed",\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n 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;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='kimi-for-coding-highspeed',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson atau SSE
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.
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
| Medan | Jenis |
|---|---|
Medanchoices[].index | Jenisinteger |
Medanchoices[].message.content | Jenisstring|null |
Medanchoices[].message.tool_calls | Jenistool_call[] |
Medanchoices[].message.reasoning_content | Jenisstring |
Medanchoices[].message.reasoning_details | Jenisobject|array |
Medanchoices[].finish_reason | Jenisstring|null |
Medanusage | Jenisobject |
| 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. |
Ailoot kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Gunakan laluan kaedah yang dipaparkan di atas.
kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
kimi-highspeedKimi K2.7 Code yang dipercepat untuk pengaturcaraan berbilang langkah dan kerja projek besar.
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
POST /v1/messagestext, imagetext| Medan | Jenis | Keperluan | Nilai & had | Lalai |
|---|---|---|---|---|
Medanmodel | Jenisstring | KeperluanDiperlukan | Nilai & had kimi-highspeed | Lalai— |
Medanmessages | Jenismessage[] | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
Medanmessages[].role | Jenisstring | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
Medanmessages[].content | Jenisstring|content_block[] | KeperluanDiperlukan | Nilai & had | Lalai— |
Medansystem | Jenisstring|content_block[] | KeperluanPilihan | Nilai & had | Lalai— |
Medanmax_tokens | Jenisinteger | KeperluanDiperlukan | Nilai & had Minimum: 1 Had terpakai pada: had maksimum tepat bagi model/kad yang dipilih | Lalai— |
Medanstream | Jenisboolean | KeperluanPilihan | Nilai & had | Lalaifalse |
Medantemperature | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantop_p | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanstop_sequences | Jenisstring[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools | Jenistool[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools[].name | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: alat dibekalkan | Lalai— |
Medantools[].description | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medantools[].input_schema | JenisJSON_schema | KeperluanPilihan | Nilai & had | Lalai— |
Medantool_choice | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanthinking.type | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanthinking.budget_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanoutput_config.effort | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanmetadata | Jenisobject | KeperluanPilihan | Nilai & had | Lalai— |
Medancache_control | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
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 | Kontrak |
|---|---|
Parametermaterial_types | Kontraktext, image |
Parameterrequired | Kontrakmodel, messages, max_tokens |
Parameteroptional_controls | Kontraknull |
Parametercontent_type | Kontrakapplication/json |
Parametertext_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.
POST /v1/messagesAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-highspeed", "max_tokens": 1024, "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-highspeed", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="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\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nimport anthropic\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nmsg = client.messages.create(\n model="kimi-highspeed",\n max_tokens=1024,\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(msg.to_dict(mode="json"))\nimport Anthropic from "@anthropic-ai/sdk";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n model: "kimi-highspeed",\n max_tokens: 1024,\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n 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;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(msg);\nimport anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.messages.stream(model='kimi-highspeed',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_message()\n save_result(final.to_dict(mode="json"),"stream-result")\njson atau SSE
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.
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
| Medan | Jenis |
|---|---|
Medanid | Jenisstring |
Medanmodel | Jenisstring |
Medancontent[] | Jenistext|thinking|tool_use|other content block |
Medanstop_reason | Jenisstring|null |
Medanusage | Jenisobject |
| 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. |
Ailoot kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Gunakan laluan kaedah yang dipaparkan di atas.
kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
kimi-highspeedKimi K2.7 Code yang dipercepat untuk pengaturcaraan berbilang langkah dan kerja projek besar.
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
POST /v1/responsestext, imagetext| Medan | Jenis | Keperluan | Nilai & had | Lalai |
|---|---|---|---|---|
Medanmodel | Jenisstring | KeperluanDiperlukan | Nilai & had kimi-highspeed | Lalai— |
Medaninput | Jenisstring|input_item[] | KeperluanDiperlukan | Nilai & had | Lalai— |
Medaninstructions | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medaninput[].type | Jenisstring | KeperluanPilihan | Nilai & had message, reasoning, function_call, function_call_output | Lalai— |
Medaninput[].content | Jenisstring|content_part[] | KeperluanPilihan | Nilai & had | Lalai— |
Medaninput[].call_id | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: function_call_output; kekalkan call_id sebenar yang dipulangkan | Lalai— |
Medaninput[].output | Jenisstring|content_part[] | KeperluanPilihan | Nilai & had Terpakai apabila: function_call_output | Lalai— |
Medanmax_output_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
Medanstream | Jenisboolean | KeperluanPilihan | Nilai & had | Lalaifalse |
Medantemperature | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantop_p | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools | Jenistool[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantool_choice | Jenisstring|object | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanparallel_tool_calls | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning.effort | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning.summary | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantext.format | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantext.verbosity | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medaninclude | Jenisstring[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanstore | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprevious_response_id | Jenisstring | KeperluanPilihan | Nilai & had Keperluan ID: Hanya ID respons sebenar daripada penerusan yang disokong Bergantung pada model | Lalai— |
Medanservice_tier | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprompt_cache_key | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprompt_cache_options | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Teks · Teks UTF8
Teks input atau bahagian input_text
Teks + imej
{type:input_image,image_url}
| Parameter | Kontrak |
|---|---|
Parametermaterial_types | Kontraktext, image |
Parameterrequired | Kontrakmodel, input |
Parameteroptional_controls | Kontraknull |
Parametercontent_type | Kontrakapplication/json |
Parametertext_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.
POST /v1/responsesAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-highspeed", "input": ""}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["input"]="Summarize this material and quote supporting source passages.\\n\\n"+text\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-highspeed", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="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\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.responses.create(model="kimi-highspeed", input="Explain the difference between an observation and a hypothesis in three sentences.")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: "kimi-highspeed", input: "Explain the difference between an observation and a hypothesis in three sentences." });\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n 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;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nwith client.responses.stream(model="kimi-highspeed", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_response()\n save_result(final.to_dict(mode="json"),"stream-result")\njson atau SSE
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.
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
| Medan | Jenis |
|---|---|
Medanid | Jenisstring |
Medanstatus | Jenisstring |
Medanoutput[] | Jenismessage|reasoning|function_call|other item |
Medanoutput[].content[] | Jeniscontent part |
Medanusage | Jenisobject |
| 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. |
Ailoot kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Gunakan laluan kaedah yang dipaparkan di atas.
kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
kimi-highspeedKimi K2.7 Code yang dipercepat untuk pengaturcaraan berbilang langkah dan kerja projek besar.
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
POST /v1/chat/completionstext, imagetext| Medan | Jenis | Keperluan | Nilai & had | Lalai |
|---|---|---|---|---|
Medanmodel | Jenisstring | KeperluanDiperlukan | Nilai & had kimi-highspeed | Lalai— |
Medanmessages | Jenismessage[] | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
Medanmessages[].role | Jenisstring | 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— |
Medanmessages[].content | Jenisstring|content_part[]|null | KeperluanPilihan | Nilai & had | Lalai— |
Medanmessages[].tool_calls | Jenistool_call[] | KeperluanPilihan | Nilai & had | Lalai— |
Medanmessages[].tool_call_id | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: role=tool; gunakan ID sebenar yang dipulangkan | Lalai— |
Medanmessages[].name | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medanmessages[].reasoning_content | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: Hantar semula penaakulan sebenar yang dipulangkan apabila model ini menggunakannya | Lalai— |
Medanmessages[].reasoning_details | Jenisobject|array | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanmax_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
Medanmax_completion_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
Medanstream | Jenisboolean | KeperluanPilihan | Nilai & had | Lalaifalse |
Medanstream_options.include_usage | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantemperature | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantop_p | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanstop | Jenisstring|string[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools | Jenisfunction_tool[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools[].type | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools[].function.name | Jenisstring | KeperluanDiperlukan | Nilai & had Terpakai apabila: alat fungsi dibekalkan | Lalai— |
Medantools[].function.description | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medantools[].function.parameters | JenisJSON_schema | KeperluanPilihan | Nilai & had | Lalai— |
Medantool_choice | Jenisstring|object | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanparallel_tool_calls | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanresponse_format | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning_effort | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanservice_tier | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medaninstructions | Jenisstring | KeperluanPilihan | Nilai & had Medan keserasian | Lalai— |
Medanfunctions | Jenisfunction[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanfunction_call | Jenisstring|object | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprompt_cache_options | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Teks · Teks UTF8
messages[].content
Teks + imej
{type:image_url,image_url:{url,detail}}
| Parameter | Kontrak |
|---|---|
Parametermaterial_types | Kontraktext, image |
Parameterrequired | Kontrakmodel, messages |
Parameteroptional_controls | Kontraknull |
Parametercontent_type | Kontrakapplication/json |
Parametertext_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.
POST /v1/chat/completionsAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-highspeed", "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-highspeed", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="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\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.chat.completions.create(\n model="kimi-highspeed",\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n model: "kimi-highspeed",\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n 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;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='kimi-highspeed',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson atau SSE
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.
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
| Medan | Jenis |
|---|---|
Medanchoices[].index | Jenisinteger |
Medanchoices[].message.content | Jenisstring|null |
Medanchoices[].message.tool_calls | Jenistool_call[] |
Medanchoices[].message.reasoning_content | Jenisstring |
Medanchoices[].message.reasoning_details | Jenisobject|array |
Medanchoices[].finish_reason | Jenisstring|null |
Medanusage | Jenisobject |
| 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. |
Ailoot kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Gunakan laluan kaedah yang dipaparkan di atas.
kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
kimi-highspeed-latestKimi K2.7 Code yang dipercepat untuk pengaturcaraan berbilang langkah dan kerja projek besar.
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
POST /v1/messagestext, imagetext| Medan | Jenis | Keperluan | Nilai & had | Lalai |
|---|---|---|---|---|
Medanmodel | Jenisstring | KeperluanDiperlukan | Nilai & had kimi-highspeed-latest | Lalai— |
Medanmessages | Jenismessage[] | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
Medanmessages[].role | Jenisstring | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
Medanmessages[].content | Jenisstring|content_block[] | KeperluanDiperlukan | Nilai & had | Lalai— |
Medansystem | Jenisstring|content_block[] | KeperluanPilihan | Nilai & had | Lalai— |
Medanmax_tokens | Jenisinteger | KeperluanDiperlukan | Nilai & had Minimum: 1 Had terpakai pada: had maksimum tepat bagi model/kad yang dipilih | Lalai— |
Medanstream | Jenisboolean | KeperluanPilihan | Nilai & had | Lalaifalse |
Medantemperature | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantop_p | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanstop_sequences | Jenisstring[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools | Jenistool[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools[].name | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: alat dibekalkan | Lalai— |
Medantools[].description | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medantools[].input_schema | JenisJSON_schema | KeperluanPilihan | Nilai & had | Lalai— |
Medantool_choice | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanthinking.type | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanthinking.budget_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanoutput_config.effort | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanmetadata | Jenisobject | KeperluanPilihan | Nilai & had | Lalai— |
Medancache_control | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
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 | Kontrak |
|---|---|
Parametermaterial_types | Kontraktext, image |
Parameterrequired | Kontrakmodel, messages, max_tokens |
Parameteroptional_controls | Kontraknull |
Parametercontent_type | Kontrakapplication/json |
Parametertext_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.
POST /v1/messagesAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-highspeed-latest", "max_tokens": 1024, "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-highspeed-latest", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="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\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nimport anthropic\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nmsg = client.messages.create(\n model="kimi-highspeed-latest",\n max_tokens=1024,\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(msg.to_dict(mode="json"))\nimport Anthropic from "@anthropic-ai/sdk";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n model: "kimi-highspeed-latest",\n max_tokens: 1024,\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n 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;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(msg);\nimport anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.messages.stream(model='kimi-highspeed-latest',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_message()\n save_result(final.to_dict(mode="json"),"stream-result")\njson atau SSE
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.
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
| Medan | Jenis |
|---|---|
Medanid | Jenisstring |
Medanmodel | Jenisstring |
Medancontent[] | Jenistext|thinking|tool_use|other content block |
Medanstop_reason | Jenisstring|null |
Medanusage | Jenisobject |
| 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. |
Ailoot kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Gunakan laluan kaedah yang dipaparkan di atas.
kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
kimi-highspeed-latestKimi K2.7 Code yang dipercepat untuk pengaturcaraan berbilang langkah dan kerja projek besar.
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
POST /v1/responsestext, imagetext| Medan | Jenis | Keperluan | Nilai & had | Lalai |
|---|---|---|---|---|
Medanmodel | Jenisstring | KeperluanDiperlukan | Nilai & had kimi-highspeed-latest | Lalai— |
Medaninput | Jenisstring|input_item[] | KeperluanDiperlukan | Nilai & had | Lalai— |
Medaninstructions | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medaninput[].type | Jenisstring | KeperluanPilihan | Nilai & had message, reasoning, function_call, function_call_output | Lalai— |
Medaninput[].content | Jenisstring|content_part[] | KeperluanPilihan | Nilai & had | Lalai— |
Medaninput[].call_id | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: function_call_output; kekalkan call_id sebenar yang dipulangkan | Lalai— |
Medaninput[].output | Jenisstring|content_part[] | KeperluanPilihan | Nilai & had Terpakai apabila: function_call_output | Lalai— |
Medanmax_output_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
Medanstream | Jenisboolean | KeperluanPilihan | Nilai & had | Lalaifalse |
Medantemperature | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantop_p | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools | Jenistool[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantool_choice | Jenisstring|object | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanparallel_tool_calls | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning.effort | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning.summary | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantext.format | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantext.verbosity | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medaninclude | Jenisstring[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanstore | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprevious_response_id | Jenisstring | KeperluanPilihan | Nilai & had Keperluan ID: Hanya ID respons sebenar daripada penerusan yang disokong Bergantung pada model | Lalai— |
Medanservice_tier | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprompt_cache_key | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprompt_cache_options | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Teks · Teks UTF8
Teks input atau bahagian input_text
Teks + imej
{type:input_image,image_url}
| Parameter | Kontrak |
|---|---|
Parametermaterial_types | Kontraktext, image |
Parameterrequired | Kontrakmodel, input |
Parameteroptional_controls | Kontraknull |
Parametercontent_type | Kontrakapplication/json |
Parametertext_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.
POST /v1/responsesAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-highspeed-latest", "input": ""}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["input"]="Summarize this material and quote supporting source passages.\\n\\n"+text\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-highspeed-latest", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="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\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.responses.create(model="kimi-highspeed-latest", input="Explain the difference between an observation and a hypothesis in three sentences.")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: "kimi-highspeed-latest", input: "Explain the difference between an observation and a hypothesis in three sentences." });\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n 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;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nwith client.responses.stream(model="kimi-highspeed-latest", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_response()\n save_result(final.to_dict(mode="json"),"stream-result")\njson atau SSE
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.
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
| Medan | Jenis |
|---|---|
Medanid | Jenisstring |
Medanstatus | Jenisstring |
Medanoutput[] | Jenismessage|reasoning|function_call|other item |
Medanoutput[].content[] | Jeniscontent part |
Medanusage | Jenisobject |
| 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. |
Ailoot kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Gunakan laluan kaedah yang dipaparkan di atas.
kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
kimi-highspeed-latestKimi K2.7 Code yang dipercepat untuk pengaturcaraan berbilang langkah dan kerja projek besar.
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
POST /v1/chat/completionstext, imagetext| Medan | Jenis | Keperluan | Nilai & had | Lalai |
|---|---|---|---|---|
Medanmodel | Jenisstring | KeperluanDiperlukan | Nilai & had kimi-highspeed-latest | Lalai— |
Medanmessages | Jenismessage[] | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
Medanmessages[].role | Jenisstring | 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— |
Medanmessages[].content | Jenisstring|content_part[]|null | KeperluanPilihan | Nilai & had | Lalai— |
Medanmessages[].tool_calls | Jenistool_call[] | KeperluanPilihan | Nilai & had | Lalai— |
Medanmessages[].tool_call_id | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: role=tool; gunakan ID sebenar yang dipulangkan | Lalai— |
Medanmessages[].name | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medanmessages[].reasoning_content | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: Hantar semula penaakulan sebenar yang dipulangkan apabila model ini menggunakannya | Lalai— |
Medanmessages[].reasoning_details | Jenisobject|array | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanmax_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
Medanmax_completion_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
Medanstream | Jenisboolean | KeperluanPilihan | Nilai & had | Lalaifalse |
Medanstream_options.include_usage | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantemperature | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantop_p | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanstop | Jenisstring|string[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools | Jenisfunction_tool[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools[].type | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools[].function.name | Jenisstring | KeperluanDiperlukan | Nilai & had Terpakai apabila: alat fungsi dibekalkan | Lalai— |
Medantools[].function.description | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medantools[].function.parameters | JenisJSON_schema | KeperluanPilihan | Nilai & had | Lalai— |
Medantool_choice | Jenisstring|object | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanparallel_tool_calls | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanresponse_format | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning_effort | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanservice_tier | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medaninstructions | Jenisstring | KeperluanPilihan | Nilai & had Medan keserasian | Lalai— |
Medanfunctions | Jenisfunction[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanfunction_call | Jenisstring|object | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprompt_cache_options | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Teks · Teks UTF8
messages[].content
Teks + imej
{type:image_url,image_url:{url,detail}}
| Parameter | Kontrak |
|---|---|
Parametermaterial_types | Kontraktext, image |
Parameterrequired | Kontrakmodel, messages |
Parameteroptional_controls | Kontraknull |
Parametercontent_type | Kontrakapplication/json |
Parametertext_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.
POST /v1/chat/completionsAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-highspeed-latest", "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-highspeed-latest", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="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\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.chat.completions.create(\n model="kimi-highspeed-latest",\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n model: "kimi-highspeed-latest",\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n 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;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='kimi-highspeed-latest',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson atau SSE
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.
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
| Medan | Jenis |
|---|---|
Medanchoices[].index | Jenisinteger |
Medanchoices[].message.content | Jenisstring|null |
Medanchoices[].message.tool_calls | Jenistool_call[] |
Medanchoices[].message.reasoning_content | Jenisstring |
Medanchoices[].message.reasoning_details | Jenisobject|array |
Medanchoices[].finish_reason | Jenisstring|null |
Medanusage | Jenisobject |
| 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. |
Ailoot kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Gunakan laluan kaedah yang dipaparkan di atas.
kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
kimi-k2.7-code-highspeedKimi K2.7 Code yang dipercepat untuk pengaturcaraan berbilang langkah dan kerja projek besar.
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
POST /v1/messagestext, imagetext| Medan | Jenis | Keperluan | Nilai & had | Lalai |
|---|---|---|---|---|
Medanmodel | Jenisstring | KeperluanDiperlukan | Nilai & had kimi-k2.7-code-highspeed | Lalai— |
Medanmessages | Jenismessage[] | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
Medanmessages[].role | Jenisstring | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
Medanmessages[].content | Jenisstring|content_block[] | KeperluanDiperlukan | Nilai & had | Lalai— |
Medansystem | Jenisstring|content_block[] | KeperluanPilihan | Nilai & had | Lalai— |
Medanmax_tokens | Jenisinteger | KeperluanDiperlukan | Nilai & had Minimum: 1 Had terpakai pada: had maksimum tepat bagi model/kad yang dipilih | Lalai— |
Medanstream | Jenisboolean | KeperluanPilihan | Nilai & had | Lalaifalse |
Medantemperature | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantop_p | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanstop_sequences | Jenisstring[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools | Jenistool[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools[].name | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: alat dibekalkan | Lalai— |
Medantools[].description | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medantools[].input_schema | JenisJSON_schema | KeperluanPilihan | Nilai & had | Lalai— |
Medantool_choice | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanthinking.type | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanthinking.budget_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanoutput_config.effort | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanmetadata | Jenisobject | KeperluanPilihan | Nilai & had | Lalai— |
Medancache_control | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
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 | Kontrak |
|---|---|
Parametermaterial_types | Kontraktext, image |
Parameterrequired | Kontrakmodel, messages, max_tokens |
Parameteroptional_controls | Kontraknull |
Parametercontent_type | Kontrakapplication/json |
Parametertext_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.
POST /v1/messagesAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-k2.7-code-highspeed", "max_tokens": 1024, "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-k2.7-code-highspeed", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="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\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nimport anthropic\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nmsg = client.messages.create(\n model="kimi-k2.7-code-highspeed",\n max_tokens=1024,\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(msg.to_dict(mode="json"))\nimport Anthropic from "@anthropic-ai/sdk";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n model: "kimi-k2.7-code-highspeed",\n max_tokens: 1024,\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n 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;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(msg);\nimport anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.messages.stream(model='kimi-k2.7-code-highspeed',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_message()\n save_result(final.to_dict(mode="json"),"stream-result")\njson atau SSE
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.
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
| Medan | Jenis |
|---|---|
Medanid | Jenisstring |
Medanmodel | Jenisstring |
Medancontent[] | Jenistext|thinking|tool_use|other content block |
Medanstop_reason | Jenisstring|null |
Medanusage | Jenisobject |
| 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. |
Ailoot kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Gunakan laluan kaedah yang dipaparkan di atas.
kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
kimi-k2.7-code-highspeedKimi K2.7 Code yang dipercepat untuk pengaturcaraan berbilang langkah dan kerja projek besar.
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
POST /v1/responsestext, imagetext| Medan | Jenis | Keperluan | Nilai & had | Lalai |
|---|---|---|---|---|
Medanmodel | Jenisstring | KeperluanDiperlukan | Nilai & had kimi-k2.7-code-highspeed | Lalai— |
Medaninput | Jenisstring|input_item[] | KeperluanDiperlukan | Nilai & had | Lalai— |
Medaninstructions | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medaninput[].type | Jenisstring | KeperluanPilihan | Nilai & had message, reasoning, function_call, function_call_output | Lalai— |
Medaninput[].content | Jenisstring|content_part[] | KeperluanPilihan | Nilai & had | Lalai— |
Medaninput[].call_id | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: function_call_output; kekalkan call_id sebenar yang dipulangkan | Lalai— |
Medaninput[].output | Jenisstring|content_part[] | KeperluanPilihan | Nilai & had Terpakai apabila: function_call_output | Lalai— |
Medanmax_output_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
Medanstream | Jenisboolean | KeperluanPilihan | Nilai & had | Lalaifalse |
Medantemperature | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantop_p | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools | Jenistool[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantool_choice | Jenisstring|object | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanparallel_tool_calls | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning.effort | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning.summary | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantext.format | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantext.verbosity | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medaninclude | Jenisstring[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanstore | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprevious_response_id | Jenisstring | KeperluanPilihan | Nilai & had Keperluan ID: Hanya ID respons sebenar daripada penerusan yang disokong Bergantung pada model | Lalai— |
Medanservice_tier | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprompt_cache_key | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprompt_cache_options | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Teks · Teks UTF8
Teks input atau bahagian input_text
Teks + imej
{type:input_image,image_url}
| Parameter | Kontrak |
|---|---|
Parametermaterial_types | Kontraktext, image |
Parameterrequired | Kontrakmodel, input |
Parameteroptional_controls | Kontraknull |
Parametercontent_type | Kontrakapplication/json |
Parametertext_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.
POST /v1/responsesAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-k2.7-code-highspeed", "input": ""}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["input"]="Summarize this material and quote supporting source passages.\\n\\n"+text\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-k2.7-code-highspeed", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="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\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(json.loads(Path("result.json").read_text(encoding="utf-8")))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.responses.create(model="kimi-k2.7-code-highspeed", input="Explain the difference between an observation and a hypothesis in three sentences.")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: "kimi-k2.7-code-highspeed", input: "Explain the difference between an observation and a hypothesis in three sentences." });\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n 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;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nwith client.responses.stream(model="kimi-k2.7-code-highspeed", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_response()\n save_result(final.to_dict(mode="json"),"stream-result")\njson atau SSE
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.
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
| Medan | Jenis |
|---|---|
Medanid | Jenisstring |
Medanstatus | Jenisstring |
Medanoutput[] | Jenismessage|reasoning|function_call|other item |
Medanoutput[].content[] | Jeniscontent part |
Medanusage | Jenisobject |
| 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. |
Ailoot kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Gunakan laluan kaedah yang dipaparkan di atas.
kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
kimi-k2.7-code-highspeedKimi K2.7 Code yang dipercepat untuk pengaturcaraan berbilang langkah dan kerja projek besar.
Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.
kimi-for-coding-highspeed menandakan Kimi K2.7 Code yang dipercepat. Model direka untuk tugasan yang diteruskan melalui beberapa tindakan: pemfaktoran semula pangkalan kod, pelaksanaan fungsi dalam fail berbeza dan pencarian ralat dalam sesi kejuruteraan panjang. Menurut Moonshot AI, varian dipercepat mengekalkan keupayaan K2.7 Code dan mengeluarkan respons kira-kira 5–6 kali lebih pantas.
Pengkhususan kod merangkumi sistem pelayan, infrastruktur, pengoptimuman prestasi, pengaturcaraan sistem, keselamatan, antara muka pengguna dan tugasan pemprosesan data. Model direka untuk mematuhi keperluan dalam konteks panjang dan menggunakan hasil alat secara berurutan.
Dalam K2.7 Code, penaakulan sentiasa diaktifkan. Model menggunakannya antara panggilan alat dan mengekalkannya dalam sejarah dialog berbilang langkah. Mod respons serta-merta tanpa penaakulan tidak disediakan bagi model ini. Aplikasi perlu mengembalikan mesej terdahulu yang lengkap supaya langkah seterusnya mengambil kira aliran kerja.
K2.7 Code dibina sebagai campuran pakar dengan 1 trilion parameter keseluruhan dan 32 bilion parameter aktif. Multi-head Latent Attention dan pengekod visual MoonViT digunakan di dalamnya. Konteks varian dipercepat yang dinyatakan ialah 262 144 token.
Dalam sistem pengeluar, pemahaman imej dan video dinyatakan bagi K2.7 Code; dalam panduan model, input video ditandakan sebagai mod eksperimen bagi kaedah akses berasingan. Teks dan imej tersedia pada kad ini. Model menghasilkan respons teks dan boleh mengarahkan fungsi yang disambungkan. Pelaksanaan arahan, penerapan perubahan dan pemeriksaan hasil dilakukan oleh persekitaran luaran. Output teks pantas mempengaruhi masa menunggu respons, tetapi tempoh keseluruhan tugasan turut bergantung pada tindakan ini.
POST /v1/chat/completionstext, imagetext| Medan | Jenis | Keperluan | Nilai & had | Lalai |
|---|---|---|---|---|
Medanmodel | Jenisstring | KeperluanDiperlukan | Nilai & had kimi-k2.7-code-highspeed | Lalai— |
Medanmessages | Jenismessage[] | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
Medanmessages[].role | Jenisstring | 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— |
Medanmessages[].content | Jenisstring|content_part[]|null | KeperluanPilihan | Nilai & had | Lalai— |
Medanmessages[].tool_calls | Jenistool_call[] | KeperluanPilihan | Nilai & had | Lalai— |
Medanmessages[].tool_call_id | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: role=tool; gunakan ID sebenar yang dipulangkan | Lalai— |
Medanmessages[].name | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medanmessages[].reasoning_content | Jenisstring | KeperluanPilihan | Nilai & had Terpakai apabila: Hantar semula penaakulan sebenar yang dipulangkan apabila model ini menggunakannya | Lalai— |
Medanmessages[].reasoning_details | Jenisobject|array | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanmax_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
Medanmax_completion_tokens | Jenisinteger | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
Medanstream | Jenisboolean | KeperluanPilihan | Nilai & had | Lalaifalse |
Medanstream_options.include_usage | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantemperature | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantop_p | Jenisnumber | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanstop | Jenisstring|string[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools | Jenisfunction_tool[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools[].type | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medantools[].function.name | Jenisstring | KeperluanDiperlukan | Nilai & had Terpakai apabila: alat fungsi dibekalkan | Lalai— |
Medantools[].function.description | Jenisstring | KeperluanPilihan | Nilai & had | Lalai— |
Medantools[].function.parameters | JenisJSON_schema | KeperluanPilihan | Nilai & had | Lalai— |
Medantool_choice | Jenisstring|object | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanparallel_tool_calls | Jenisboolean | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanresponse_format | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning_effort | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanreasoning | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanservice_tier | Jenisstring | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medaninstructions | Jenisstring | KeperluanPilihan | Nilai & had Medan keserasian | Lalai— |
Medanfunctions | Jenisfunction[] | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanfunction_call | Jenisstring|object | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Medanprompt_cache_options | Jenisobject | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
Teks · Teks UTF8
messages[].content
Teks + imej
{type:image_url,image_url:{url,detail}}
| Parameter | Kontrak |
|---|---|
Parametermaterial_types | Kontraktext, image |
Parameterrequired | Kontrakmodel, messages |
Parameteroptional_controls | Kontraknull |
Parametercontent_type | Kontrakapplication/json |
Parametertext_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.
POST /v1/chat/completionsAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-k2.7-code-highspeed", "messages": []}')\nf=Path(os.environ["AILOOT_TEXT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")\ntext=f.read_text(encoding="utf-8")\nif not text.strip():raise SystemExit("Source material must contain text")\np["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\\n\\n"+text}]\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "kimi-k2.7-code-highspeed", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')\nimport base64\nf=Path(os.environ["AILOOT_IMAGE_FILE"])\nif not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")\nraw=f.read_bytes()\nmime="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\nif not mime:raise SystemExit("Use PNG JPEG or WebP")\nb64=base64.b64encode(raw).decode()\np["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)\nresp = client.chat.completions.create(\n model="kimi-k2.7-code-highspeed",\n messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(resp.to_dict(mode="json"))\nimport OpenAI from "openai";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");\nconst client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n model: "kimi-k2.7-code-highspeed",\n messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],\n});\nimport { writeFileSync } from "node:fs";\n\nfunction saveResult(data, stem = "result") {\n writeFileSync(stem + ".json", JSON.stringify(data, null, 2));\n console.log(JSON.stringify(data, null, 2));\n const saveBlob = (encoded, suffix, label) => {\n const raw = Buffer.from(encoded, "base64");\n 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;\n const file = `${stem}-${label}.${ext}`;\n writeFileSync(file, raw); console.log("Saved", file);\n };\n for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));\n for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n for (const [i, item] of (data.output || []).entries()) {\n console.log("Output", i, JSON.stringify(item));\n if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);\n }\n for (const [ci, candidate] of (data.candidates || []).entries()) {\n for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n console.log("Candidate/part", ci, pi, JSON.stringify(part));\n const blob = part.inlineData || part.inline_data;\n if (blob?.data) {\n const mime = blob.mimeType || blob.mime_type;\n const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";\n saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n }\n }\n }\n}\n\nsaveResult(resp);\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='kimi-k2.7-code-highspeed',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson atau SSE
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.
Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.
| Medan | Jenis |
|---|---|
Medanchoices[].index | Jenisinteger |
Medanchoices[].message.content | Jenisstring|null |
Medanchoices[].message.tool_calls | Jenistool_call[] |
Medanchoices[].message.reasoning_content | Jenisstring |
Medanchoices[].message.reasoning_details | Jenisobject|array |
Medanchoices[].finish_reason | Jenisstring|null |
Medanusage | Jenisobject |
| 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. |
Ailoot kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Gunakan laluan kaedah yang dipaparkan di atas.
kimi-for-coding-highspeed, kimi-highspeed, kimi-highspeed-latest, kimi-k2.7-code-highspeed
Contoh teknikal dalam bahasa Inggeris
Remove repeated lookups in a data-processing loop\n\nReview this pseudocode: for each order, fetch_customer(order.customer_id), then append the customer name to its export row. Many orders share a customer, and repeated fetches dominate runtime. Propose a scoped improvement that preserves row order and handles missing customers. Give a test with three orders sharing two customer IDs; do not claim execution.Revised pseudocode, an explanation of lookup reuse and tests for shared IDs and missing customers.The shared-ID test requires at most one lookup per distinct customer ID and unchanged export-row order.