Responses API

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

Request diki kwazvo i-model id ne-text. Mhinduro haisi streamed kunze kwekunge wainokumbira.

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."
  }'

Mhinduro i-response object. output yayo ine reasoning, kana model yakafunga, ne-message:

{
  "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
  }
}

Request fields

model ne-input ndizvo zvinodiwa ne-request. Column ye-Applied by inotaura ma-model apo field inochinja mhinduro. Hosted open-weight models ndiwo ma-id gumi nemaviri e-model list; mhuri ye-Shannon 3 ndi-shannon-3, shannon-3-pro, shannon-3.1 ne-shannon-3.1-pro. Ma-model nemitengo

previous_response_id, store, metadata, parallel_tool_calls, truncation, include, user ne-prompt_cache_key dzinogamuchirwa kuti client code iripo ishande isina kuchinjwa. Hadzichinji mhinduro. Nekuti hapana hurukuro inochengetwa, request inotevera inotakura ma-turn ekare mu-input.

Input items

Input item i-message, ine role ne-content, kana item ine type inotakura tool call kana mhedzisiro yayo. content i-string kana array ye-parts.

Isa mirayiro mu-instructions field. Ne-id yemhuri ye-Shannon 3, isa mirayiro inofanira kuchengetwa mu-user message.

Items dze-output yemhinduro dzinogona kudzokera mu-input sezvadziri: message ne-function_call items dzinoverengwa, reasoning items dzinosiiwa.

Content parts

Pa-Shannon tiers mifananidzo ne-files zvinoverengwa kubva ku-user item yekupedzisira ye-input. Sizes ne-limits zvine peji razvo. Mifananidzo ne-files

Request ine instructions ne-options

Request iyi inotumira instructions, hurukuro se-input items, output limit, temperature ne-reasoning effort. Inoshandisa hosted open-weight model, inoshandisa zvese izvi.

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"}
  }'

Mhinduro ye-hosted open-weight model ine id, object, model, created_at, status, output ne-usage. usage yayo inowedzera tokens dzakaverengwa kubva ku-cache ne-tokens dzakashandiswa pa-reasoning:

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

Response object

id, object, status, output ne-usage zviri pamhinduro imwe neimwe. Vaka code yako pazvo.

Output items

OpenAI SDKs dzinokubatanidzira text ye-message mu-response.output_text.

Streaming

Isa stream ku-true kuti uwane server-sent events. Frame imwe neimwe ine mutsara we-event: une zita re-event nemutsara we-data: une JSON object; object inodzokorora zita mu-type. Enzanisa deltas ne-item yadzo ne-output_index.

Ne-OpenAI SDK, verenga ma-event nemhando yawo mu-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
  }'

Ma-event anouya nenzira iyi. Mapoka e-reasoning, message ne-tool calls anooneka chete kana mhinduro ichiaita.

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}, …}}

Stream inokundikana

Pa-Shannon tiers mhinduro yakundikana inopera ne-response.failed panzvimbo pe-response.completed. response.status yayo i-failed uye response.error ine code, rate_limit_exceeded kana server_error, ne-message.

Pa-hosted open-weight models kundikana i-error event ine code api_error ne-message. response.completed inoteverazve.

Tora stream seyakundikana kana ine response.failed kana error event, uye utumire request zvakare.

Tools

Tool i-function inomhanywa ne-code yako. Itsanangure mu-tools; kana model ichiida, mhinduro ine function_call item panzvimbo kana padivi pe-message.

Tool definition mu-tools:

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

output yemhinduro inoidanidzira:

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

Mhanyisa function, wotumira request zvakare ine call nemhedzisiro yayo yawedzerwa mu-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\"}"
  }
]

Tools dze-type function chete ndidzo dzinoverengwa. Pa-shannon-1.6-*, shannon-2-* ne-shannon-coder-1 parameters schema inoderedzwa kuita JSON Schema keywords dzakajairika: oneOf inoverengwa se-anyOf, uye keywords dzakaita se-$ref, additionalProperties, const, default ne-title hadzipiwi kuna model.

tool_choice values required ne-function yakatumidzwa dzinoshandiswa ne-hosted open-weight models.

Tool loop yakatsanangurwa zvizere papeji rayo. Kudanwa kwemabasa

Structured output

Format iyi inonyora structured output se-text.format. Schema iri zvakananga mu-format, padivi pe-name ne-strict, kwete pasi pe-json_schema member sepa-Chat Completions.

• {"type": "json_object"} inokumbira chero JSON object.
• {"type": "json_schema", "name", "schema", "strict"} inokumbira JSON inotevera schema yako. strict i-true kana ukaisiya kunze.

{
  "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 inouya se-text mu-output_text part ye-message; i-parse iwe pachako. Hosted open-weight model isina structured output inodzosa 400.

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

Kuti model ipi inogamuchira form ipi kunoratidzwa papeji rayo. Zvinobuda zvakarongeka

Reasoning

Model inofunga inodzosa reasoning yayo se-output item ye-type reasoning, pamberi pe-message. Mu-stream inouya se-response.reasoning_summary_text.delta events.

Hosted open-weight models dzinoshandisa reasoning.effort: off, low, medium kana high, ne-high kana usina kutumira chinhu. off haidzosi reasoning item. Itumire se-object; string chete haiverengwi pa-endpoint iyi.

Ma-effort anotsanangurwa papeji rawo. Reasoning effort

Output limit

max_output_tokens i-4,096 kana usina kuitumira. Ndiyo huwandu hwe-tokens hunochengetwa mu-balance yako request payinotanga; mhinduro kana yapera, huwandu uhwu hunotsiviwa nezvakashandiswa ne-request. Value isingakwani mu-balance yasara inodzosa 429 Quota exceeded.

Inogumira kureba kwemhinduro pa-shannon-1.6-*, shannon-2-* ne-shannon-coder-1, uye kureba kwe-text yemhinduro pa-hosted open-weight models.

Pa-endpoint iyi shannon-coder-1 inobhadharwa mu-tokens kubva mu-balance yako, semamwe ma-model ese.

Request body inogona kusvika ku-32 MiB. Limits ne-balance

Errors

Errors dzinoshandisa OpenAI error body: error object ine type ne-message; mamwe anotakurawo code ne-param ine value null. Tafura inoratidza zvinodzoserwa nguva dzakawanda ne-endpoint iyi. Rondedzero yakazara, ine zvekuedza zvakare, ine peji rayo. Zvikanganiso