Responses API

POST https://api.shannon-ai.com/v1/responses

Eng kichik so'rov — model id va matn. So'ramasangiz, javob oqimsiz bo'ladi.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/v1",
)

response = client.responses.create(
    model="shannon-3",
    input="Say hello in one sentence.",
)

print(response.output_text)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.shannon-ai.com/v1",
});

const response = await client.responses.create({
  model: "shannon-3",
  input: "Say hello in one sentence.",
});

console.log(response.output_text);

curl https://api.shannon-ai.com/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "shannon-3",
    "input": "Say hello in one sentence."
  }'

Javob — response obyekti. Uning outputi, model mulohaza qilgan bo'lsa, mulohazani va xabarni o'z ichiga oladi:

{
  "id": "resp_5f0c1e7a9b3d4c62a8e1f07d2b46c9a3",
  "object": "response",
  "created_at": 1791625200,
  "model": "shannon-3",
  "status": "completed",
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "metadata": {},
  "parallel_tool_calls": true,
  "temperature": null,
  "tool_choice": "auto",
  "tools": [],
  "top_p": null,
  "output": [
    {
      "id": "rs_8a2e6c1f4b7d4e03b9c5a1d70f3e2b64",
      "type": "reasoning",
      "summary": [
        {
          "type": "summary_text",
          "text": "The user wants a greeting in one sentence. Keep it short and friendly."
        }
      ]
    },
    {
      "id": "msg_1c7b9e3a5d2f4a86b0e4c8d19a6f7e25",
      "type": "message",
      "role": "assistant",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "Hello, it is good to meet you.",
          "annotations": []
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 1184,
    "output_tokens": 46,
    "total_tokens": 1230
  }
}

So'rov maydonlari

So'rovga model va input kerak. Qo'llaydi ustuni maydon javobni o'zgartiradigan modellarni nomlaydi. Xostingdagi open-weight modellar — model ro'yxatidagi o'n ikkita id; Shannon 3 oilasi — shannon-3, shannon-3-pro, shannon-3.1 va shannon-3.1-pro. Modellar va narxlar

previous_response_id, store, metadata, parallel_tool_calls, truncation, include, user va prompt_cache_key mavjud mijoz kodi o'zgarishsiz ishlashi uchun qabul qilinadi. Ular javobni o'zgartirmaydi. Suhbat saqlanmagani uchun keyingi so'rov oldingi navbatlarni inputda olib keladi.

Kirish elementlari

Kirish elementi — role va contentli xabar yoki tool chaqiruvini yoxud uning natijasini olib keladigan turli element. content — satr yoki qismlar massivi.

Ko'rsatmalarni instructions maydoniga qo'ying. Shannon 3 oilasi id'sida bajarilishi shart bo'lgan ko'rsatmalarni user xabariga qo'ying.

Javob outputidagi elementlarni inputga o'zgartirmay qaytarish mumkin: message va function_call elementlari o'qiladi, reasoning elementlari o'tkazib yuboriladi.

Kontent qismlari

Shannon darajalarida rasmlar va fayllar inputning oxirgi user elementidan o'qiladi. O'lchamlar va limitlar alohida sahifada. Rasmlar va fayllar

Ko'rsatmalar va parametrlar bilan so'rov

Bu so'rov ko'rsatmalar, kirish elementlari sifatida suhbat, chiqish limiti, temperatura va mulohaza darajasini yuboradi. U xostingdagi open-weight modeldan foydalanadi, u hammasini qo'llaydi.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/v1",
)

response = client.responses.create(
    model="DeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP",
    instructions="You are a physics teacher. Answer in two sentences.",
    input=[
        {"role": "user", "content": "Why is the sky blue?"},
        {"role": "assistant", "content": "Air scatters blue light more than red light."},
        {"role": "user", "content": "And why are sunsets red?"},
    ],
    max_output_tokens=512,
    temperature=0.3,
    reasoning={"effort": "low"},
)

for item in response.output:
    if item.type == "reasoning":
        print("reasoning:", item.summary[0].text)
    elif item.type == "message":
        print("answer:", item.content[0].text)
print(response.usage)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.shannon-ai.com/v1",
});

const response = await client.responses.create({
  model: "DeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP",
  instructions: "You are a physics teacher. Answer in two sentences.",
  input: [
    { role: "user", content: "Why is the sky blue?" },
    { role: "assistant", content: "Air scatters blue light more than red light." },
    { role: "user", content: "And why are sunsets red?" },
  ],
  max_output_tokens: 512,
  temperature: 0.3,
  reasoning: { effort: "low" },
});

for (const item of response.output) {
  if (item.type === "reasoning") console.log("reasoning:", item.summary[0].text);
  if (item.type === "message") console.log("answer:", item.content[0].text);
}
console.log(response.usage);

curl https://api.shannon-ai.com/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "DeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP",
    "instructions": "You are a physics teacher. Answer in two sentences.",
    "input": [
      {"role": "user", "content": "Why is the sky blue?"},
      {"role": "assistant", "content": "Air scatters blue light more than red light."},
      {"role": "user", "content": "And why are sunsets red?"}
    ],
    "max_output_tokens": 512,
    "temperature": 0.3,
    "reasoning": {"effort": "low"}
  }'

Xostingdagi open-weight model javobida id, object, model, created_at, status, output va usage bor. Uning usage'i keshdan o'qilgan tokenlar va mulohazaga sarflangan tokenlarni qo'shadi:

{
  "usage": {
    "input_tokens": 58,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 67,
    "output_tokens_details": {
      "reasoning_tokens": 19
    },
    "total_tokens": 125
  }
}

Response obyekti

id, object, status, output va usage har bir javobda bor. Kodingizni shularga asoslang.

Chiqish elementlari

OpenAI SDK'lar xabar matnini sizning o'rningizga response.output_textda birlashtiradi.

Streaming

Server-sent events uchun streamni true qiling. Har bir freymda hodisa nomi bilan event: satri va JSON obyekti bilan data: satri bor; obyekt nomni typeda takrorlaydi. Deltalarni o'z elementiga output_index bo'yicha moslang.

OpenAI SDK bilan hodisalarni type bo'yicha o'qing:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/v1",
)

stream = client.responses.create(
    model="shannon-3",
    input="Explain server-sent events in three sentences.",
    stream=True,
)

for event in stream:
    kind = getattr(event, "type", "error")     # an event without a type is an error event
    if kind == "response.reasoning_summary_text.delta":
        pass                                   # a piece of reasoning: event.delta
    elif kind == "response.output_text.delta":
        print(event.delta, end="", flush=True)
    elif kind == "response.output_item.done" and event.item.type == "function_call":
        print("\ntool call:", event.item.name, event.item.arguments)
    elif kind == "response.completed":
        print("\n", event.response.usage)
    elif kind in ("response.failed", "error"):
        raise RuntimeError("the stream failed, send the request again")

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.shannon-ai.com/v1",
});

const stream = await client.responses.create({
  model: "shannon-3",
  input: "Explain server-sent events in three sentences.",
  stream: true,
});

for await (const event of stream) {
  if (event.type === "response.reasoning_summary_text.delta") {
    // a piece of reasoning: event.delta
  } else if (event.type === "response.output_text.delta") {
    process.stdout.write(event.delta);
  } else if (event.type === "response.output_item.done" && event.item.type === "function_call") {
    console.log("\ntool call:", event.item.name, event.item.arguments);
  } else if (event.type === "response.completed") {
    console.log("\n", event.response.usage);
  } else if (event.type === "response.failed" || event.type === "error") {
    throw new Error("the stream failed, send the request again");
  }
}

curl -N https://api.shannon-ai.com/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "shannon-3",
    "input": "Explain server-sent events in three sentences.",
    "stream": true
  }'

Hodisalar shu tartibda keladi. Mulohaza, xabar va tool chaqiruvlari guruhlari faqat javobda ular bo'lganda paydo bo'ladi.

event: response.created
data: {"type":"response.created","response":{"id":"resp_5f0c…","object":"response","status":"in_progress","output":[], …}}

event: response.in_progress
data: {"type":"response.in_progress","response":{"id":"resp_5f0c…","object":"response","status":"in_progress","output":[], …}}

event: response.output_item.added
data: {"type":"response.output_item.added","output_index":0,"item":{"id":"msg_1c7b…","type":"message","role":"assistant","status":"in_progress","content":[]}}

event: response.content_part.added
data: {"type":"response.content_part.added","output_index":0,"content_index":0,"part":{"type":"output_text","text":""}}

event: response.output_text.delta
data: {"type":"response.output_text.delta","output_index":0,"content_index":0,"delta":"Server-sent"}

event: response.output_text.delta
data: {"type":"response.output_text.delta","output_index":0,"content_index":0,"delta":" events let a server push text over one HTTP reply."}

event: response.output_text.done
data: {"type":"response.output_text.done","output_index":0,"content_index":0,"text":"Server-sent events let a server push text over one HTTP reply."}

event: response.content_part.done
data: {"type":"response.content_part.done","output_index":0,"content_index":0,"part":{"type":"output_text","text":"Server-sent events let a server push text over one HTTP reply."}}

event: response.output_item.done
data: {"type":"response.output_item.done","output_index":0,"item":{"id":"msg_1c7b…","type":"message","role":"assistant","status":"completed","content":[{"type":"output_text","text":"Server-sent events let a server push text over one HTTP reply.","annotations":[]}]}}

event: response.completed
data: {"type":"response.completed","response":{"id":"resp_5f0c…","object":"response","status":"completed","output":[…],"usage":{"input_tokens":1190,"output_tokens":18,"total_tokens":1208}, …}}

Muvaffaqiyatsiz oqim

Shannon darajalarida muvaffaqiyatsiz javob response.completed o'rniga response.failed bilan tugaydi. Uning response.statusi failed, response.error esa code (rate_limit_exceeded yoki server_error) va messageni o'z ichiga oladi.

Xostingdagi open-weight modellarda nosozlik code api_error va messageli error hodisasi. response.completed baribir undan keyin keladi.

Oqimda response.failed yoki error hodisasi bo'lsa, uni muvaffaqiyatsiz deb hisoblang va so'rovni qayta yuboring.

Tool'lar

Tool — kodingiz bajaradigan funksiya. Uni toolsda tasvirlang; model uni xohlasa, javobda xabar o'rnida yoki yonida function_call elementi bo'ladi.

tools ichidagi tool ta'rifi:

[
  {
    "type": "function",
    "name": "get_weather",
    "description": "Current weather for a city.",
    "parameters": {
      "type": "object",
      "properties": {
        "city": {
          "type": "string"
        }
      },
      "required": [
        "city"
      ]
    }
  }
]

Uni chaqiradigan javobning outputi:

[
  {
    "id": "call_3d9a7c1e5b2f4a60c8e1d7f09b24a6c5",
    "type": "function_call",
    "name": "get_weather",
    "call_id": "call_3d9a7c1e5b2f4a60c8e1d7f09b24a6c5",
    "arguments": "{\"city\":\"Paris\"}"
  }
]

Funksiyani bajaring, so'ng chaqiruv va uning natijasi inputga qo'shilgan holda so'rovni qayta yuboring:

[
  {
    "role": "user",
    "content": "What is the weather in Paris?"
  },
  {
    "type": "function_call",
    "call_id": "call_3d9a7c1e5b2f4a60c8e1d7f09b24a6c5",
    "name": "get_weather",
    "arguments": "{\"city\":\"Paris\"}"
  },
  {
    "type": "function_call_output",
    "call_id": "call_3d9a7c1e5b2f4a60c8e1d7f09b24a6c5",
    "output": "{\"temperature_c\": 18, \"sky\": \"cloudy\"}"
  }
]

Faqat function turidagi tool'lar o'qiladi. shannon-1.6-*, shannon-2-* va shannon-coder-1 da parameters sxemasi umumiy JSON Schema kalit so'zlarigacha qisqartiriladi: oneOf anyOf sifatida o'qiladi, $ref, additionalProperties, const, default va title kabi kalit so'zlar modelga uzatilmaydi.

tool_choice ning required qiymati va nomlangan funksiyani xostingdagi open-weight modellar qo'llaydi.

Tool sikli to'liq o'z sahifasida tasvirlangan. Funksiya chaqirish

Tuzilmali chiqish

Bu format tuzilmali chiqishni text.format deb yozadi. Sxema Chat Completions'dagidek json_schema a'zosi ostida emas, bevosita formatda, name va strict yonida turadi.

• {"type": "json_object"} istalgan JSON obyektini so'raydi.
• {"type": "json_schema", "name", "schema", "strict"} sxemangizga amal qiladigan JSON so'raydi. Qoldirsangiz, strict — true.

{
  "model": "shannon-1.6-lite",
  "input": "Extract the city and the date: 'The conference opens in Lisbon on 12 May 2027.'",
  "text": {
    "format": {
      "type": "json_schema",
      "name": "event",
      "strict": true,
      "schema": {
        "type": "object",
        "properties": {
          "city": {
            "type": "string"
          },
          "date": {
            "type": "string",
            "description": "ISO 8601 date"
          }
        },
        "required": [
          "city",
          "date"
        ]
      }
    }
  }
}

JSON xabarning output_text qismida matn sifatida keladi; uni o'zingiz parse qiling. Tuzilmali chiqishi yo'q xostingdagi open-weight model 400 qaytaradi.

{"city": "Lisbon", "date": "2027-05-12"}

Qaysi model qaysi shaklni qabul qilishi o'z sahifasida sanab o'tilgan. Tuzilgan chiqishlar

Mulohaza

Mulohaza qiladigan model o'z mulohazasini xabardan oldin reasoning turidagi chiqish elementi sifatida qaytaradi. Oqimda u response.reasoning_summary_text.delta hodisalari sifatida keladi.

Xostingdagi open-weight modellar reasoning.effortni qo'llaydi: off, low, medium yoki high, hech narsa yubormasangiz high. off mulohaza elementini qaytarmaydi. Uni obyekt sifatida yuboring; bu endpointda oddiy satr o'qilmaydi.

Darajalar o'z sahifasida tasvirlangan. Mulohaza darajasi

Chiqish limiti

max_output_tokens yubormasangiz 4,096. So'rov boshlanganda balansingizdan ajratib qo'yiladigan tokenlar soni shu; javob to'liq bo'lgach, bu miqdor so'rov ishlatgan miqdor bilan almashtiriladi. Qolgan balansingizga sig'maydigan qiymat 429 Quota exceeded qaytaradi.

U shannon-1.6-*, shannon-2-* va shannon-coder-1 da javob uzunligini, xostingdagi open-weight modellarda esa javob matni uzunligini cheklaydi.

Bu endpointda shannon-coder-1 boshqa har qanday model kabi balansingizdan token bilan hisoblanadi.

So'rov tanasi 32 MiB gacha bo'lishi mumkin. Limitlar va balans

Xatolar

Xatolar OpenAI xato tanasidan foydalanadi: type va messageli error obyekti; ba'zilari null qiymatli code va paramni ham olib keladi. Jadvalda bu endpoint eng ko'p qaytaradigan xatolar keltirilgan. To'liq ro'yxat, nimani qayta urinish kerakligi bilan, alohida sahifada. Xatolarni boshqarish