I-Responses API

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

Isicelo esincinci kakhulu yi-id yemodeli nombhalo. Impendulo ayiyi-stream-wa 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 yi-object yempendulo. I-output yayo iqulathe ukuqiqa, xa imodeli iqiqile, kunye nomyalezo:

{
  "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
  }
}

Iintsimi zesicelo

I-model kunye ne-input zizo ezifunekayo kwisicelo. Ikholamu ethi Isebenza kwi ibiza iimodeli apho intsimi itshintsha impendulo. Iimodeli ze-open-weight ezisingathiweyo zii-id ezilishumi elinambini zoluhlu lweemodeli; intsapho yeShannon 3 yi-shannon-3, i-shannon-3-pro, i-shannon-3.1 kunye ne-shannon-3.1-pro. Iimodeli namaxabiso

I-previous_response_id, i-store, i-metadata, i-parallel_tool_calls, i-truncation, i-include, i-user kunye ne-prompt_cache_key ziyamkelwa ukuze ikhowudi ye-client ekhoyo isebenze ngaphandle kotshintsho. Azitshintshi mpendulo. Ngenxa yokuba akukho ncoko igcinwayo, isicelo esilandelayo sithwala imijikelo yangaphambili kwi-input.

Iinto zokufaka

Into yokufaka ngumyalezo, kunye ne-role ne-content, okanye into enohlobo ethwala ubizo lwe-tool okanye isiphumo salo. I-content ngumtya okanye uluhlu lweenxalenye.

Beka imiyalelo kwintsimi ye-instructions. Nge-id yentsapho yeShannon 3, beka imiyalelo ekufuneka ihlale kumyalezo we-user.

Iinto ze-output yempendulo zinokubuyela kwi-input njengoko zinjalo: iinto ze-message kunye ne-function_call ziyafundwa, iinto ze-reasoning ziyatsitywa.

Iinxalenye zomxholo

Kumanqanaba eShannon imifanekiso neefayile zifundwa kwinto yokugqibela ye-user ye-input. Ubungakanani nemida inephepha lazo. Imifanekiso neefayile

Isicelo esinemiyalelo neenketho

Esi sicelo sithumela imiyalelo, incoko njengeento zokufaka, umda wokuphuma, ubushushu kunye nobunzulu bokuqiqa. Sisebenzisa imodeli ye-open-weight esingathiweyo, eyisebenzisa 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 yemodeli ye-open-weight esingathiweyo inayo i-id, i-object, i-model, i-created_at, i-status, i-output kunye ne-usage. I-usage yayo yongeza ii-token ezifundwe kwi-cache kunye nee-token ezisetyenziswe ekuqiqeni:

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

I-object yempendulo

I-id, i-object, i-status, i-output kunye ne-usage zikuyo yonke impendulo. Yakha ikhowudi yakho kuzo.

Iinto zokuphuma

Ii-OpenAI SDK zikudibanisela umbhalo womyalezo kwi-response.output_text.

Streaming

Misela i-stream ibe yi-true kwimisitho ethunyelwe yi-server. I-frame nganye inomgca we-event: onegama lomsitho kunye nomgca we-data: one-JSON object; i-object iphinda igama kwi-type. Dibanisa ii-delta neento zazo nge-output_index.

Nge-OpenAI SDK, funda imisitho ngo-type wayo:

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
  }'

Imisitho ifika ngolu landelelwano. Amaqela okuqiqa, omyalezo kunye nobizo lwee-tool avela kuphela xa 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 esilelayo

Kumanqanaba eShannon impendulo esilele iphela nge-response.failed endaweni ye-response.completed. I-response.status yayo yi-failed kwaye i-response.error iqulathe i-code, i-rate_limit_exceeded okanye i-server_error, kunye ne-message.

Kwiimodeli ze-open-weight ezisingathiweyo isilele ngumsitho we-error kunye ne-code api_error kunye ne-message. I-response.completed isalandela.

Thatha i-stream njengesilele xa iqulathe umsitho we-response.failed okanye we-error, uze uthumele isicelo kwakhona.

Ii-tool

I-tool ngumsebenzi ogqitywa yikhowudi yakho. Uchaze kwi-tools; xa imodeli iyifuna, impendulo iqulathe into ye-function_call endaweni yomyalezo, okanye ecaleni kwawo.

Uchazo lwe-tool kwi-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 yona:

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

Qhuba umsebenzi, uze uthumele isicelo kwakhona kunye nobizo nesiphumo salo songezwe kwi-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\"}"
  }
]

Ii-tool zohlobo function kuphela ziyafundwa. Kwi-shannon-1.6-*, i-shannon-2-* kunye ne-shannon-coder-1 i-schema ye-parameters incitshiswa ibe ngamagama angundoqo e-JSON Schema aqhelekileyo: i-oneOf ifundwa njenge-anyOf, kwaye amagama angundoqo anjenge-$ref, i-additionalProperties, i-const, i-default kunye ne-title awadluliselwa kwimodeli.

Amaxabiso e-tool_choice athi required nomsebenzi obizwe ngegama asetyenziswa ziimodeli ze-open-weight ezisingathiweyo.

Iluphu ye-tool ichazwe ngokupheleleyo kwiphepha layo. Umsebenzi Ukufowuna

Okuphuma okucwangcisiweyo

Le fomathi ibhala okuphuma okucwangcisiweyo njenge-text.format. I-schema ihlala ngqo kwi-format, ecaleni kwe-name kunye ne-strict, hayi phantsi kwelungu le-json_schema njengakwi-Chat Completions.

• {"type": "json_object"} icela nayiphi na i-JSON object.
• {"type": "json_schema", "name", "schema", "strict"} icela i-JSON elandela i-schema yakho. I-strict yi-true xa 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 kwinxalenye ye-output_text yomyalezo; ihlalutye ngokwakho. Imodeli ye-open-weight esingathiweyo engenakuphuma okucwangcisiweyo ibuyisa i-400.

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

Yeyiphi imodeli yamkela eyiphi ifomu idweliswe kwiphepha layo. Iziphumo ezicwangcisiweyo

Ukuqiqa

Imodeli eqiqayo ibuyisa ukuqiqa kwayo njengento yokuphuma yohlobo reasoning, phambi komyalezo. Kwi-stream ifika njengemisitho ye-response.reasoning_summary_text.delta.

Iimodeli ze-open-weight ezisingathiweyo zisebenzisa i-reasoning.effort: off, low, medium okanye high, kunye ne-high xa ungathumeli nto. I-off ayibuyisi nto yokuqiqa. Yithumele njenge-object; umtya nje awufundwa kule endpoint.

Amanqanaba obunzulu achazwe kwiphepha lawo. I-effort yokuqiqa

Umda wokuphuma

I-max_output_tokens yi-4,096 xa ungayithumeli. Linani lee-token ezigcinelwe kwibhalansi yakho xa isicelo siqala; xa impendulo igqityiwe, loo sixa sibuyiselwa yinto isicelo esiyisebenzisileyo. Ixabiso elingangeni kwibhalansi yakho eseleyo libuyisa i-429 Quota exceeded.

Ilinganisa ubude bempendulo kwi-shannon-1.6-*, i-shannon-2-* kunye ne-shannon-coder-1, kunye nobude bombhalo wempendulo kwiimodeli ze-open-weight ezisingathiweyo.

Kule endpoint i-shannon-coder-1 ihlawulwa ngee-token ezivela kwibhalansi yakho, njengayo yonke enye imodeli.

Umzimba wesicelo unokuba ngu-32 MiB ubuninzi. Imida nebhalansi

Iimpazamo

Iimpazamo zisebenzisa umzimba wempazamo we-OpenAI: i-object ye-error kunye ne-type ne-message; ezinye zikwathwala i-code kunye ne-param enexabiso elithi null. Itheyibhile idwelisa oko le endpoint ikubuyisa rhoqo. Uluhlu olupheleleyo, kunye nokuba yintoni ekufuneka uyizame kwakhona, lunephepha lalo. Ukuphatha imposiso