Gemini Content genereren

Gebruik het native API-formaat van Gemini via CometAPI voor tekstgeneratie, multimodale input, thinking/reasoning, function calling, Google Search-grounding, JSON mode en Streaming.

POST /v1beta/models/{model}:{operator}

Python

Basic

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)

200

{
  "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>"
}

​

Overzicht

CometAPI ondersteunt het native API-formaat van Gemini, waardoor je volledige toegang krijgt tot Gemini-specifieke functies zoals controle over thinking, Google Search-grounding, native modalities voor afbeeldingsgeneratie en meer. Gebruik dit endpoint wanneer je mogelijkheden nodig hebt die niet beschikbaar zijn via het OpenAI-compatible chat endpoint.

​

Snelstart

Vervang de base URL en API key in elke Gemini SDK of HTTP-client:

Instelling	Google-standaard	CometAPI
Base URL	generativelanguage.googleapis.com	api.cometapi.com
API Key	$GEMINI_API_KEY	$COMETAPI_KEY

Zowel x-goog-api-key als Authorization: Bearer-headers worden ondersteund voor authenticatie.

​

Thinking (Reasoning)

Gemini-modellen kunnen interne reasoning uitvoeren voordat ze een antwoord genereren. De manier van aansturen hangt af van de modelgeneratie.

Gemini 3 (thinkingLevel)

Gemini 3-modellen gebruiken thinkingLevel om de diepte van reasoning te regelen. Beschikbare niveaus: 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 (thinkingBudget)

Gemini 2.5-modellen gebruiken thinkingBudget voor fijnmazige controle op tokenniveau:

• 0 — thinking uitschakelen
• -1 — dynamisch (het model beslist, standaard)
• > 0 — specifiek Token-budget (bijv. 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}
    }
  }'

Het gebruik van thinkingLevel met Gemini 2.5-modellen (of thinkingBudget met Gemini 3-modellen) kan fouten veroorzaken. Gebruik de juiste parameter voor jouw modelversie.

---

​

Streaming

Gebruik streamGenerateContent?alt=sse als operator om Server-Sent Events te ontvangen terwijl het model content genereert. Elke SSE-event bevat een data:-regel met een JSON-GenerateContentResponse-object.

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"}]}]
  }'

---

​

Systeeminstructies

Stuur het gedrag van het model gedurende het hele gesprek aan met 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

Forceer gestructureerde JSON-uitvoer met responseMimeType. Geef optioneel een responseSchema op voor strikte schema-validatie:

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

Schakel realtime zoeken op het web in door een googleSearch tool toe te voegen:

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": {}}]
  }'

De response bevat groundingMetadata met bron-URL’s en betrouwbaarheidsscores.

---

​

Response Example

Een typische response van CometAPI’s Gemini-endpoint:

{
  "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"
}

Het veld thoughtsTokenCount in usageMetadata laat zien hoeveel tokens het model heeft besteed aan interne redenering, zelfs wanneer de denkuitvoer niet in de response is opgenomen.

---

​

Belangrijkste verschillen met het OpenAI-Compatible endpoint

Functie	Gemini Native (/v1beta/models/...)	OpenAI-Compatible (/v1/chat/completions)
Thinking-besturing	thinkingConfig met thinkingLevel / thinkingBudget	Niet beschikbaar
Google Search-grounding	tools: [\{"google_search": \{\}\}]	Niet beschikbaar
Google Maps-grounding	tools: [\{"googleMaps": \{\}\}]	Niet beschikbaar
Modality voor afbeeldingsgeneratie	responseModalities: ["IMAGE"]	Niet beschikbaar
Auth-header	x-goog-api-key of Bearer	Alleen Bearer
Response-indeling	Gemini native (candidates, parts)	OpenAI-indeling (choices, message)

Autorisaties

x-goog-api-key · string · header · vereist

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

Padparameters

model · string · vereist

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

Voorbeeld:

"gemini-2.5-flash"

operator · enum<string> · vereist

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

Beschikbare opties: generateContent, streamGenerateContent?alt=sse

Voorbeeld:

"generateContent"

Body

application/json

contents · object[] · vereist

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.

Respons

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.