Gemini Content generieren

POST

v1beta

models

{model}

{operator}

from google import genai

client = genai.Client(
    api_key="<COMETAPI_KEY>",
    http_options={"api_version": "v1beta", "base_url": "https://api.cometapi.com"},
)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Explain how AI works in a few words",
)

print(response.text)

{
  "candidates": [
    {
      "content": {
        "role": "<string>",
        "parts": [
          {
            "text": "<string>",
            "functionCall": {
              "name": "<string>",
              "args": {}
            },
            "inlineData": {
              "mimeType": "<string>",
              "data": "<string>"
            },
            "thought": true
          }
        ]
      },
      "finishReason": "STOP",
      "safetyRatings": [
        {
          "category": "<string>",
          "probability": "<string>",
          "blocked": true
        }
      ],
      "citationMetadata": {
        "citationSources": [
          {
            "startIndex": 123,
            "endIndex": 123,
            "uri": "<string>",
            "license": "<string>"
          }
        ]
      },
      "tokenCount": 123,
      "avgLogprobs": 123,
      "groundingMetadata": {
        "groundingChunks": [
          {
            "web": {
              "uri": "<string>",
              "title": "<string>"
            }
          }
        ],
        "groundingSupports": [
          {
            "groundingChunkIndices": [
              123
            ],
            "confidenceScores": [
              123
            ],
            "segment": {
              "startIndex": 123,
              "endIndex": 123,
              "text": "<string>"
            }
          }
        ],
        "webSearchQueries": [
          "<string>"
        ]
      },
      "index": 123
    }
  ],
  "promptFeedback": {
    "blockReason": "SAFETY",
    "safetyRatings": [
      {
        "category": "<string>",
        "probability": "<string>",
        "blocked": true
      }
    ]
  },
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 123,
    "totalTokenCount": 123,
    "trafficType": "<string>",
    "thoughtsTokenCount": 123,
    "promptTokensDetails": [
      {
        "modality": "<string>",
        "tokenCount": 123
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "<string>",
        "tokenCount": 123
      }
    ]
  },
  "modelVersion": "<string>",
  "createTime": "<string>",
  "responseId": "<string>"
}

Überblick

CometAPI unterstützt das native Gemini-API-Format und gibt Ihnen vollen Zugriff auf Gemini-spezifische Funktionen wie Thinking-Steuerung, Google Search Grounding, native Bildgenerierungsmodalitäten und mehr. Verwenden Sie diesen Endpoint, wenn Sie Funktionen benötigen, die nicht über den OpenAI-kompatiblen Chat-Endpoint verfügbar sind.

Schnellstart

Ersetzen Sie die Base-URL und den API-Key in einem beliebigen Gemini-SDK oder HTTP-Client:

Einstellung	Google-Standard	CometAPI
Base URL	`generativelanguage.googleapis.com`	`api.cometapi.com`
API Key	`$GEMINI_API_KEY`	`$COMETAPI_KEY`

Sowohl die Header x-goog-api-key als auch Authorization: Bearer werden für die Authentifizierung unterstützt.

Thinking (Reasoning)

Gemini-Modelle können internes Reasoning durchführen, bevor sie eine Antwort generieren. Die Steuerungsmethode hängt von der Modellgeneration ab.

Gemini 3 (thinkingLevel)
Gemini 2.5 (thinkingBudget)

Gemini 3-Modelle verwenden thinkingLevel, um die Tiefe des Reasoning zu steuern. Verfügbare Stufen: MINIMAL, LOW, MEDIUM, HIGH.

curl "https://api.cometapi.com/v1beta/models/gemini-3.1-pro-preview:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "Explain quantum physics simply."}]}],
    "generationConfig": {
      "thinkingConfig": {"thinkingLevel": "LOW"}
    }
  }'

Gemini 2.5-Modelle verwenden thinkingBudget für eine fein abgestufte Steuerung auf Token-Ebene:

0 — Thinking deaktivieren
-1 — dynamisch (das Modell entscheidet, Standard)
> 0 — spezifisches Token-Budget (z. B. 1024, 2048)

curl "https://api.cometapi.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "Solve this logic puzzle step by step."}]}],
    "generationConfig": {
      "thinkingConfig": {"thinkingBudget": 2048}
    }
  }'

Die Verwendung von thinkingLevel mit Gemini 2.5-Modellen (oder thinkingBudget mit Gemini 3-Modellen) kann Fehler verursachen. Verwenden Sie den richtigen Parameter für Ihre Modellversion.

Streaming

Verwenden Sie streamGenerateContent?alt=sse als Operator, um Server-Sent Events zu empfangen, während das Modell Content generiert. Jedes SSE-Ereignis enthält eine data:-Zeile mit einem JSON-Objekt vom Typ GenerateContentResponse.

curl "https://api.cometapi.com/v1beta/models/gemini-2.5-flash:streamGenerateContent?alt=sse" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  --no-buffer \
  -d '{
    "contents": [{"parts": [{"text": "Write a short poem about the stars"}]}]
  }'

Systemanweisungen

Steuern Sie das Verhalten des Modells über die gesamte Konversation hinweg mit systemInstruction:

curl "https://api.cometapi.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "What is 2+2?"}]}],
    "systemInstruction": {
      "parts": [{"text": "You are a math tutor. Always show your work."}]
    }
  }'

JSON Mode

Erzwingen Sie strukturierte JSON-Ausgabe mit responseMimeType. Optional können Sie ein responseSchema für eine strikte Schema-Validierung angeben:

curl "https://api.cometapi.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "List 3 planets with their distances from the sun"}]}],
    "generationConfig": {
      "responseMimeType": "application/json"
    }
  }'

Google Search Grounding

Aktivieren Sie die Websuche in Echtzeit, indem Sie ein googleSearch-Tool hinzufügen:

curl "https://api.cometapi.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "Who won the euro 2024?"}]}],
    "tools": [{"google_search": {}}]
  }'

Die Antwort enthält groundingMetadata mit Quell-URLs und Konfidenzwerten.

Beispielantwort

Eine typische Antwort vom Gemini-Endpunkt von CometAPI:

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [{"text": "Hello"}]
      },
      "finishReason": "STOP",
      "avgLogprobs": -0.0023
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 5,
    "candidatesTokenCount": 1,
    "totalTokenCount": 30,
    "trafficType": "ON_DEMAND",
    "thoughtsTokenCount": 24,
    "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 5}],
    "candidatesTokensDetails": [{"modality": "TEXT", "tokenCount": 1}]
  },
  "modelVersion": "gemini-2.5-flash",
  "createTime": "2026-03-25T04:21:43.756483Z",
  "responseId": "CeynaY3LDtvG4_UP0qaCuQY"
}

Das Feld thoughtsTokenCount in usageMetadata zeigt, wie viele Tokens das Modell für internes Reasoning verwendet hat, selbst wenn die Thinking-Ausgabe nicht in der Antwort enthalten ist.

Wichtige Unterschiede zum OpenAI-kompatiblen Endpunkt

Funktion	Gemini Native (`/v1beta/models/...`)	OpenAI-Compatible (`/v1/chat/completions`)
Thinking-Steuerung	`thinkingConfig` mit `thinkingLevel` / `thinkingBudget`	Nicht verfügbar
Google Search Grounding	`tools: [\{"google_search": \{\}\}]`	Nicht verfügbar
Google Maps Grounding	`tools: [\{"googleMaps": \{\}\}]`	Nicht verfügbar
Modality für Bildgenerierung	`responseModalities: ["IMAGE"]`	Nicht verfügbar
Auth-Header	`x-goog-api-key` oder `Bearer`	Nur `Bearer`
Antwortformat	Gemini-native (`candidates`, `parts`)	OpenAI-Format (`choices`, `message`)

Autorisierungen

x-goog-api-key

string

header

erforderlich

Your CometAPI key passed via the x-goog-api-key header. Bearer token authentication (Authorization: Bearer <key>) is also supported.

Pfadparameter

model

string

erforderlich

The Gemini model ID to use. See the Models page for current Gemini model IDs.

Beispiel:

"gemini-2.5-flash"

operator

enum<string>

erforderlich

The operation to perform. Use generateContent for synchronous responses, or streamGenerateContent?alt=sse for Server-Sent Events streaming.

Verfügbare Optionen:

generateContent,

streamGenerateContent?alt=sse

Beispiel:

"generateContent"

Body

application/json

contents

object[]

erforderlich

The conversation history and current input. For single-turn queries, provide a single item. For multi-turn conversations, include all previous turns.

Show child attributes

systemInstruction

object

System instructions that guide the model's behavior across the entire conversation. Text only.

Show child attributes

tools

object[]

Tools the model may use to generate responses. Supports function declarations, Google Search, Google Maps, and code execution.

Show child attributes

toolConfig

object

Configuration for tool usage, such as function calling mode.

Show child attributes

safetySettings

object[]

Safety filter settings. Override default thresholds for specific harm categories.

Show child attributes

generationConfig

object

Configuration for model generation behavior including temperature, output length, and response format.

Show child attributes

cachedContent

string

The name of cached content to use as context. Format: cachedContents/{id}. See the Gemini context caching documentation for details.

Antwort

200 - application/json

Successful response. For streaming requests, the response is a stream of SSE events, each containing a GenerateContentResponse JSON object prefixed with data:.

candidates

object[]

The generated response candidates.

Show child attributes

promptFeedback

object

Feedback on the prompt, including safety blocking information.

Show child attributes

usageMetadata

object

Token usage statistics for the request.

Show child attributes

modelVersion

string

The model version that generated this response.

createTime

string

The timestamp when this response was created (ISO 8601 format).

responseId

string

Unique identifier for this response.

from google import genai

client = genai.Client(
    api_key="<COMETAPI_KEY>",
    http_options={"api_version": "v1beta", "base_url": "https://api.cometapi.com"},
)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Explain how AI works in a few words",
)

print(response.text)

{
  "candidates": [
    {
      "content": {
        "role": "<string>",
        "parts": [
          {
            "text": "<string>",
            "functionCall": {
              "name": "<string>",
              "args": {}
            },
            "inlineData": {
              "mimeType": "<string>",
              "data": "<string>"
            },
            "thought": true
          }
        ]
      },
      "finishReason": "STOP",
      "safetyRatings": [
        {
          "category": "<string>",
          "probability": "<string>",
          "blocked": true
        }
      ],
      "citationMetadata": {
        "citationSources": [
          {
            "startIndex": 123,
            "endIndex": 123,
            "uri": "<string>",
            "license": "<string>"
          }
        ]
      },
      "tokenCount": 123,
      "avgLogprobs": 123,
      "groundingMetadata": {
        "groundingChunks": [
          {
            "web": {
              "uri": "<string>",
              "title": "<string>"
            }
          }
        ],
        "groundingSupports": [
          {
            "groundingChunkIndices": [
              123
            ],
            "confidenceScores": [
              123
            ],
            "segment": {
              "startIndex": 123,
              "endIndex": 123,
              "text": "<string>"
            }
          }
        ],
        "webSearchQueries": [
          "<string>"
        ]
      },
      "index": 123
    }
  ],
  "promptFeedback": {
    "blockReason": "SAFETY",
    "safetyRatings": [
      {
        "category": "<string>",
        "probability": "<string>",
        "blocked": true
      }
    ]
  },
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 123,
    "totalTokenCount": 123,
    "trafficType": "<string>",
    "thoughtsTokenCount": 123,
    "promptTokensDetails": [
      {
        "modality": "<string>",
        "tokenCount": 123
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "<string>",
        "tokenCount": 123
      }
    ]
  },
  "modelVersion": "<string>",
  "createTime": "<string>",
  "responseId": "<string>"
}

Übersicht

API-Referenz

Integrationsleitfäden

Fehler

Preise & Abrechnung

Support

Überblick

Schnellstart

Thinking (Reasoning)

Streaming

Systemanweisungen

JSON Mode

Google Search Grounding

Beispielantwort

Wichtige Unterschiede zum OpenAI-kompatiblen Endpunkt

Autorisierungen

Pfadparameter

Body

Antwort

Übersicht

API-Referenz

Integrationsleitfäden

Fehler

Preise & Abrechnung

Support

​Überblick

​Schnellstart

​Thinking (Reasoning)

​Streaming

​Systemanweisungen

​JSON Mode

​Google Search Grounding

​Beispielantwort

​Wichtige Unterschiede zum OpenAI-kompatiblen Endpunkt

Autorisierungen

Pfadparameter

Body

Antwort

Überblick

Schnellstart

Thinking (Reasoning)

Streaming

Systemanweisungen

JSON Mode

Google Search Grounding

Beispielantwort

Wichtige Unterschiede zum OpenAI-kompatiblen Endpunkt