I-Responses API

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

Isicelo esincane kunazo zonke siyi-id ye-model nombhalo. Impendulo ayiyi-stream ngaphandle kokuba uyicele.

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."
  }'

Impendulo iyi-response object. I-output yayo iphethe ukucabanga, uma i-model icabangile, nomlayezo:

{
  "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
  }
}

Ama-field esicelo

I-model ne-input yilokho isicelo esikudingayo. Ikholomu ethi Applied by ibhala ama-model lapho i-field ishintsha khona impendulo. Ama-model e-open-weight ahlinzekiwe ayishumi nambili, wonke ama-id aphelele ohlwini lwama-model; umndeni we-Shannon 3 yi-shannon-3, shannon-3-pro, shannon-3.1 ne-shannon-3.1-pro. Ama-model namanani

I-previous_response_id, store, metadata, parallel_tool_calls, truncation, include, user ne-prompt_cache_key ziyamukelwa ukuze ikhodi ye-client ekhona isebenze ngaphandle kokushintshwa. Azishintshi impendulo. Ngoba ayikho ingxoxo egciniwe, isicelo esilandelayo siphatha izikhathi zangaphambilini ku-input.

Izinto zokufakwayo

Into yokufakwayo ngumlayezo, ene-role ne-content, noma into ehlobile ephethe isicelo sethuluzi noma umphumela waso. I-content iyi-string noma i-array yezingxenye.

Faka iziqondiso ku-field ye-instructions. Nge-id yomndeni we-Shannon 3, faka iziqondiso okufanele ziphumelele emlayezweni we-user.

Izinto ze-output yempendulo zingabuyela ku-input njengoba zinjalo: izinto ze-message ne-function_call ziyafundwa, izinto ze-reasoning ziyeqiwa.

Izingxenye zokuqukethwe

Ezigabeni ze-Shannon izithombe namafayela afundwa ento yokugcina ye-user ye-input. Osayizi nemikhawulo kunekhasi lazo. Izithombe namafayela

Isicelo esineziqondiso nezinketho

Lesi sicelo sithumela iziqondiso, ingxoxo njengezinto zokufakwayo, umkhawulo wokuphumayo, i-temperature ne-effort yokucabanga. Sisebenzisa i-model e-open-weight ehlinzekiwe, ezisebenzisa zonke.

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"}
  }'

Impendulo ye-model e-open-weight ehlinzekiwe inayo i-id, object, model, created_at, status, output ne-usage. I-usage yayo yengeza ama-token afundwe ku-cache nama-token asetshenziselwe ukucabanga:

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

I-response object

I-id, object, status, output ne-usage ikho kuyo yonke impendulo. Yakha ikhodi yakho kulokho.

Izinto zokuphumayo

Ama-SDK e-OpenAI akuhlanganisela umbhalo womlayezo ku-response.output_text.

I-streaming

Setha i-stream ibe true ukuthola i-server-sent events. I-frame ngayinye inomugqa we-event: onegama lomcimbi nomugqa we-data: one-JSON object; i-object iphindaphinda igama ku-type. Fanisa ama-delta nento yawo nge-output_index.

Nge-SDK ye-OpenAI, funda imicimbi ngohlobo lwayo (type):

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
  }'

Imicimbi ifika ngalokhu kulandelana. Amaqembu okucabanga, umlayezo nezicelo zamathuluzi avela kuphela uma impendulo inawo.

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}, …}}

I-stream ehlulekayo

Ezigabeni ze-Shannon impendulo ehlulekile iphela nge-response.failed esikhundleni se-response.completed. I-response.status yayo iyi-failed futhi i-response.error iphethe i-code, rate_limit_exceeded noma server_error, ne-message.

Kuma-model e-open-weight ahlinzekiwe ukwehluleka kuwumcimbi we-error ene-code api_error ne-message. I-response.completed isalandela.

Thatha i-stream njengehlulekile uma iphethe umcimbi we-response.failed noma we-error, bese uphinda uthumele isicelo.

Amathuluzi

Ithuluzi ngumsebenzi oqhutshwa yikhodi yakho. Yichaze ku-tools; lapho i-model iyifuna, impendulo iphatha into ye-function_call esikhundleni somlayezo, noma eceleni kwawo.

Incazelo yethuluzi ku-tools:

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

I-output yempendulo ebiza lowo msebenzi:

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

Qhuba umsebenzi, bese uphinda uthumele isicelo ngokungeza ukubiza nomphumela wako ku-input:

[
  {
    "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\"}"
  }
]

Amathuluzi ohlobo function kuphela afundwa. Ku-shannon-1.6-*, shannon-2-* ne-shannon-coder-1 i-schema ye-parameters inciphiswa ibe amagama abalulekile e-JSON Schema avamile: i-oneOf ifundwa njenge-anyOf, futhi amagama anjenge-$ref, additionalProperties, const, default ne-title awadluliselwa ku-model.

Amanani e-tool_choice ethi required nomsebenzi onegama asetshenziswa ama-model e-open-weight ahlinzekiwe.

Umjikelezo wamathuluzi uchazwe ngokugcwele ekhasini lawo. Ukubiza umsebenzi

Okuphumayo okuhlelekile

Lesi simo sibhala okuphumayo okuhlelekile njenge-text.format. I-schema ihlala ngqo ku-format, eduze kwe-name ne-strict, hhayi ngaphansi kwelungu le-json_schema njengase-Chat Completions.

• {"type": "json_object"} icela noma iyiphi i-JSON object.
• {"type": "json_schema", "name", "schema", "strict"} icela i-JSON elandela i-schema yakho. I-strict iyi-true uma uyishiya ngaphandle.

{
  "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"
        ]
      }
    }
  }
}

I-JSON ifika njengombhalo engxenyeni ye-output_text yomlayezo; yihlaziye wena. I-model e-open-weight ehlinzekiwe engenakho ukuphumayo okuhlelekile ibuyisa 400.

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

Ukuthi iyiphi i-model yamukela yiphi indlela kubhalwe ekhasini layo. Imiphumela ehlanganisiwe

Ukucabanga

I-model ecabangayo ibuyisa ukucabanga kwayo njengento yokuphumayo yohlobo reasoning, ngaphambi komlayezo. Ku-stream kufika njengemicimbi ye-response.reasoning_summary_text.delta.

Ama-model e-open-weight ahlinzekiwe asebenzisa i-reasoning.effort: off, low, medium noma high, kube high uma ungathumeli lutho. I-off ayibuyisi into yokucabanga. Yithumele njenge-object; i-string yodwa ayifundwa kule-endpoint.

Ama-effort achazwe ekhasini lawo. Umzamo wokucabanga

Umkhawulo wokuphumayo

I-max_output_tokens ingu-4,096 uma ungayithumeli. Yinani lama-token abekwa eceleni ku-balance yakho lapho isicelo siqala; lapho impendulo iphelele, leli nani lishintshwa yilokho isicelo esikusebenzisile. Inani elingafaneleki ku-balance yakho esele libuyisa 429 Quota exceeded.

Inqamula ubude bempendulo ku-shannon-1.6-*, shannon-2-* ne-shannon-coder-1, nobude bombhalo wempendulo kuma-model e-open-weight ahlinzekiwe.

Kule-endpoint i-shannon-coder-1 ikhokhiswa ngama-token e-balance yakho, njengawo wonke amanye ama-model.

Umzimba wesicelo ungafika ku-32 MiB. Imikhawulo ne-balance

Amaphutha

Amaphutha asebenzisa umzimba wephutha we-OpenAI: into ye-error ene-type ne-message; amanye aphinde aphathe i-code ne-param enani elithi null. Ithebula libhala lokho le-endpoint eyibuyisa kakhulu. Uhlu olugcwele, nokuthi yini okufanele iphindwe, lunekhasi lalo. Ukuphathwa kwamaphutha