Responses

The responses format: input and instructions in, typed output items out, with conversations continued by id.

Every response on this page was returned by the API when the page was built.

POST /v1/responses

Create a response.

The responses format: input and instructions in, output items out. previous_response_id continues a conversation for an hour. Streaming sends typed events from response.created to response.completed.

Request body

FieldTypeNotes
model Requiredstring
input Requiredstring or arrayA string, or a list of messages and items.
instructionsstring
max_output_tokensinteger At least 16.
temperaturenumber 0 to 2.
top_pnumber
streamboolean
previous_response_idstringContinue an earlier response; kept for an hour.
textobject
memory_scopestring
POST /v1/responsescurl
curl -X POST https://api.znsi.ai/v1/responses \
  -H "Authorization: Bearer $ZNSI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mugen-5-swift",
    "input": "What is a Shōgi pod?"
  }'
ResponseJSON
HTTP/1.1 200 OK
content-type: application/json
request-id: req_afe4e96d64d029ad042f3a0a
x-ratelimit-remaining-requests: 17
x-znsi-neurons: 1567000000

{
  "created_at": 1792991712,
  "error": null,
  "id": "resp_mNnhDsYJRaslDCl55E3D2sPd",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "metadata": {},
  "model": "mugen-5-swift",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "text": "KIRIN wafers are wafer-scale chips whose transistors are arranged as spiking neurons and whose synapses are memristors that change as they conduct. The weights are the hardware, and the hardware learns. KIRIN-9 has 7.2 billion neurons and 1.1 quadrillion synapses per wafer.",
          "type": "output_text"
        }
      ],
      "id": "msg_LZMnvv8rJPVCde80esWEjXJU",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "status": "completed",
  "store": true,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [],
  "top_p": 1,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 14,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 80,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 94
  }
}
Response with "stream": trueSSE
HTTP/1.1 200 OK
content-type: text/event-stream; charset=utf-8
request-id: req_e64e2c1e17f3660f79ba267d
x-ratelimit-remaining-requests: 16
x-znsi-neurons: 1395000000

event: response.created
data: {"response":{"created_at":1792991712,"error":null,"id":"resp_Qw81NjZVnpaxIUni82jyomJd","incomplete_details":null,"instructions":null,"max_output_tokens":null,"metadata":{},"model":"mugen-5-swift","object":"response","output":[],"parallel_tool_calls":true,"previous_response_id":null,"status":"in_progress","store":true,"temperature":1,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1,"truncation":"disabled","usage":null},"sequence_number":0,"type":"response.created"}

event: response.in_progress
data: {"response":{"created_at":1792991712,"error":null,"id":"resp_Qw81NjZVnpaxIUni82jyomJd","incomplete_details":null,"instructions":null,"max_output_tokens":null,"metadata":{},"model":"mugen-5-swift","object":"response","output":[],"parallel_tool_calls":true,"previous_response_id":null,"status":"in_progress","store":true,"temperature":1,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1,"truncation":"disabled","usage":null},"sequence_number":1,"type":"response.in_progress"}

event: response.output_item.added
data: {"item":{"content":[],"id":"msg_f3uETNyOHbaPxCsdjXNb35Jh","role":"assistant","status":"in_progress","type":"message"},"output_index":0,"sequence_number":2,"type":"response.output_item.added"}

event: response.content_part.added
data: {"content_index":0,"item_id":"msg_f3uETNyOHbaPxCsdjXNb35Jh","output_index":0,"part":{"annotations":[],"text":"","type":"output_text"},"sequence_number":3,"type":"response.content_part.added"}

… 29 more events …

event: response.output_item.done
data: {"item":{"content":[{"annotations":[],"text":"KIRIN tolerates defects by rerouting synapses around dead dies while it runs, so a wafer with flaws still serves. That matters when the chip is the size of a dinner plate and is never switched off.","type":"output_text"}],"id":"msg_f3uETNyOHbaPxCsdjXNb35Jh","role":"assistant","status":"completed","type":"message"},"output_index":0,"sequence_number":33,"type":"response.output_item.done"}

event: response.completed
data: {"response":{"created_at":1792991712,"error":null,"id":"resp_Qw81NjZVnpaxIUni82jyomJd","incomplete_details":null,"instructions":null,"max_output_tokens":null,"metadata":{},"model":"mugen-5-swift","object":"response","output":[{"content":[{"annotations":[],"text":"KIRIN tolerates defects by rerouting synapses around dead dies while it runs, so a wafer with flaws still serves. That matters when the chip is the size of a dinner plate and is never switched off.","type":"output_text"}],"id":"msg_f3uETNyOHbaPxCsdjXNb35Jh","role":"assistant","status":"completed","type":"message"}],"parallel_tool_calls":true,"previous_response_id":null,"status":"completed","store":true,"temperature":1,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1,"truncation":"disabled","usage":{"input_tokens":14,"input_tokens_details":{"cached_tokens":0},"output_tokens":56,"output_tokens_details":{"reasoning_tokens":0},"total_tokens":70}},"sequence_number":34,"type":"response.completed"}

Errors

  • 400 Invalid request: a missing or invalid parameter, named in param.
  • 401 No key, or a key that is malformed, expired or revoked.
  • 404 Unknown route or model.
  • 413 Request body larger than 10 MB.
  • 429 Rate limited, or MUGEN is declining this caller for a while. See retry-after.