Chat-Vervollständigungen

Basis-URL: https://app.neuroflash.com/api/ds-prototypes

Textvervollständigungen mit KI-Modellen generieren.

Chat-Vervollständigungen

POST/chat/completions

Chat-Vervollständigungen mit Wörteranalyse und Anbieter-Routing verarbeiten

Anfrage-Body

FeldTypErforderlichBeschreibung

messagesarray<object>JaListe von Nachrichten mit „role" und „content"

modelstringJaName des Modells

temperatureobjectNeinTemperatur des Modells

max_tokensobjectNeinAnzahl der zu generierenden Tokens begrenzen

reasoningobjectNeinParameter für den Reasoning-Modus

reasoning_effortobjectNeinStufe des Reasoning-Modus

toolsobjectNeinFür Tools und Funktionsaufrufe

tool_choiceobjectNeinTool-Auswahl beeinflussen

seedobjectNeinZufälliger Seed

response_formatobjectNeinFür strukturierte Ausgaben zur Definition eines JSON-Schemas

web_search_optionsobjectNeinZusätzliche Optionen für WEB-Suche

structured_outputsobjectNein

frequency_penaltyobjectNeinPenalisierungsoption

presence_penaltyobjectNeinPenalisierungsoption

repetition_penaltyobjectNeinPenalisierungsoption

stopobjectNeinStoppbedingung anpassen

streamobjectNeinStreaming-Modus aktivieren

Beispiel

Erforderlicher Header

Alle Anfragen an /api/ds-prototypes benötigen zusätzlich zu Authorization den Header x-workspace-id. Wird er weggelassen, gibt die API 400 Bad Request zurück.

cURL

curl -X POST "https://app.neuroflash.com/api/ds-prototypes/chat/completions" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "x-workspace-id: YOUR_WORKSPACE_ID" \
  -H "Content-Type: application/json" \
  -d '{
      "messages": [
        { "role": "user", "content": "Write a tagline for an AI content platform." }
      ],
      "model": "openai/gpt-4.1-mini",
      "temperature": 0.7
  }'

Python

import requests

response = requests.post(
    f"https://app.neuroflash.com/api/ds-prototypes/chat/completions",
    headers={"Authorization": f"Bearer {token}", "x-workspace-id": workspace_id, "Content-Type": "application/json"},
    json={
        "messages": [
            {"role": "user", "content": "Write a tagline for an AI content platform."}
        ],
        "model": "openai/gpt-4.1-mini",
        "temperature": 0.7
    },
).json()

Node.js

const response = await fetch(
  `https://app.neuroflash.com/api/ds-prototypes/chat/completions`,
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${token}`,
      "x-workspace-id": workspaceId,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      messages: [
        { role: "user", content: "Write a tagline for an AI content platform." }
      ],
      model: "openai/gpt-4.1-mini",
      temperature: 0.7,
    }),
  }
).then((r) => r.json());

Go

body, _ := json.Marshal(map[string]any{
        "messages": []map[string]string{
            {"role": "user", "content": "Write a tagline for an AI content platform."},
        },
        "model": "openai/gpt-4.1-mini",
        "temperature": 0.7,
    })

req, _ := http.NewRequest("POST", "https://app.neuroflash.com/api/ds-prototypes/chat/completions", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("x-workspace-id", workspaceID)
req.Header.Set("Content-Type", "application/json")

resp, _ := http.DefaultClient.Do(req)
defer resp.Body.Close()

Antwort:

{
  "id": "gen-1775000000-AbCdEfGh",
  "object": "chat.completion",
  "model": "openai/gpt-4.1-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Create smarter content, faster — powered by AI that knows your brand."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 12,
    "total_tokens": 26,
    "words_used": 9
  }
}