Generate content

POST

v1beta

models

{model}

{operator}

import os
from google import genai

client = genai.Client(
    api_key=os.environ["COMETAPI_KEY"],
    http_options={"api_version": "v1beta", "base_url": "https://api.cometapi.com"},
)

response = client.models.generate_content(
    model="gemini-3-flash-preview",
    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
          }
        ]
      },
      "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": {
    "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>"
}

CometAPI mendukung format API native Gemini, memberi Anda akses penuh ke fitur khusus Gemini seperti kontrol thinking, Google Search grounding, modalitas pembuatan gambar native, dan lainnya. Gunakan endpoint ini ketika Anda membutuhkan kapabilitas yang tidak tersedia melalui endpoint chat yang kompatibel dengan OpenAI.

Gunakan referensi API GenerateContent resmi Google sebagai sumber utama untuk field permintaan lengkap, skema respons, dan perilaku khusus model Gemini. Halaman CometAPI ini menjelaskan cara mengirim bentuk permintaan native tersebut melalui CometAPI.

Parameter permintaan Gemini dan field respons dapat berubah saat Google memperbarui API native. Periksa dokumentasi pembuatan teks Gemini untuk daftar parameter lengkap terbaru dan perilaku khusus penyedia.

Header x-goog-api-key dan Authorization: Bearer keduanya didukung untuk autentikasi.

Quick start

Untuk menggunakan SDK Gemini atau klien HTTP apa pun dengan CometAPI, ganti base URL dan API key:

Setting	Default Google	CometAPI
Base URL	`generativelanguage.googleapis.com`	`api.cometapi.com`
API key	`$GEMINI_API_KEY`	`$COMETAPI_KEY`

Kirim input video

Gemini generateContent menerima video sebagai bagian konten. Pilih bentuk input berdasarkan tempat video disimpan:

Sumber video	Bagian request	Digunakan saat
File video lokal	`inlineData`	Video cukup kecil untuk dikirim sebagai base64 dalam request JSON.
URL video publik	`fileData.fileUri`	Video tersedia melalui URL HTTPS publik yang tidak memerlukan autentikasi.

Untuk request REST dan curl, gunakan nama field camelCase Gemini seperti inlineData.mimeType dan fileData.fileUri. Jangan kirim media URL sebagai file_data.file_uri.

Contoh ini membaca file MP4 lokal, mengodekannya sebagai base64, lalu mengirimkannya dalam body request:

read -rsp "CometAPI API key: " COMETAPI_KEY
printf '\n'
export COMETAPI_KEY
VIDEO_PATH="./your_video.mp4"
VIDEO_B64=$(base64 < "$VIDEO_PATH" | tr -d '\n')

curl -X POST \
  "https://api.cometapi.com/v1beta/models/gemini-3.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  --data-binary @- <<EOF
{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "inlineData": {
            "mimeType": "video/mp4",
            "data": "${VIDEO_B64}"
          }
        },
        {
          "text": "Analyze this video and list the key scenes."
        }
      ]
    }
  ],
  "generationConfig": {
    "maxOutputTokens": 512,
    "thinkingConfig": {"thinkingLevel": "MINIMAL"}
  }
}
EOF

Contoh ini mengirim URL MP4 publik dengan fileData.fileUri:

read -rsp "CometAPI API key: " COMETAPI_KEY
printf '\n'
export COMETAPI_KEY
VIDEO_URL="https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4"

curl -X POST \
  "https://api.cometapi.com/v1beta/models/gemini-3.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  --data-binary @- <<EOF
{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "fileData": {
            "mimeType": "video/mp4",
            "fileUri": "${VIDEO_URL}"
          }
        },
        {
          "text": "Analyze this video and list the key scenes."
        }
      ]
    }
  ],
  "generationConfig": {
    "maxOutputTokens": 512,
    "thinkingConfig": {"thinkingLevel": "MINIMAL"}
  }
}
EOF

CometAPI tidak merekomendasikan alur upload Gemini Files API terpisah untuk endpoint ini. Kirim media di dalam request generateContent itu sendiri menggunakan inlineData atau fileData.fileUri.

Konfigurasikan thinking (reasoning)

Model Gemini dapat melakukan reasoning internal sebelum menghasilkan respons. Metode kontrolnya bergantung pada generasi model.

Gemini 3 (thinkingLevel)
Gemini 2.5 (thinkingBudget)

Model Gemini 3 menggunakan thinkingLevel untuk mengontrol kedalaman reasoning. Level yang tersedia: MINIMAL, LOW, MEDIUM, HIGH.Gunakan gemini-3-flash-preview sebagai model contoh default kecuali Anda secara khusus memerlukan varian Gemini 3 yang berbeda.

curl "https://api.cometapi.com/v1beta/models/gemini-3-flash-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"}
    }
  }'

Model Gemini 2.5 menggunakan thinkingBudget untuk kontrol tingkat Token yang lebih terperinci:

0 — nonaktifkan thinking
-1 — dinamis (model yang menentukan, default)
> 0 — anggaran Token tertentu (misalnya, 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}
    }
  }'

Menggunakan thinkingLevel dengan model Gemini 2.5 (atau thinkingBudget dengan model Gemini 3) dapat menyebabkan error. Gunakan parameter yang benar untuk versi model Anda.

Stream respons

Untuk menerima Server-Sent Events saat model menghasilkan konten, gunakan streamGenerateContent?alt=sse sebagai operator. Setiap event SSE berisi baris data: dengan objek JSON GenerateContentResponse.

curl "https://api.cometapi.com/v1beta/models/gemini-3-flash-preview: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"}]}]
  }'

Atur instruksi sistem

Untuk memandu perilaku model di seluruh percakapan, gunakan systemInstruction:

curl "https://api.cometapi.com/v1beta/models/gemini-3-flash-preview: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."}]
    }
  }'

Minta output JSON

Untuk memaksa output JSON terstruktur, setel responseMimeType. Secara opsional, berikan responseSchema untuk validasi skema yang ketat:

curl "https://api.cometapi.com/v1beta/models/gemini-3-flash-preview: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"
    }
  }'

Grounding dengan Google Search

Untuk mengaktifkan pencarian web real-time, tambahkan tool googleSearch:

curl "https://api.cometapi.com/v1beta/models/gemini-3-flash-preview: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": {}}]
  }'

Respons mencakup groundingMetadata dengan URL sumber dan skor keyakinan.

Contoh response

Response umum dari endpoint Gemini 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-3-flash-preview",
  "createTime": "2026-03-25T04:21:43.756483Z",
  "responseId": "CeynaY3LDtvG4_UP0qaCuQY"
}

Field thoughtsTokenCount dalam usageMetadata menunjukkan berapa banyak token yang digunakan model untuk penalaran internal, bahkan ketika output pemikiran tidak disertakan dalam response.

Perbandingan dengan endpoint kompatibel OpenAI

Fitur	Gemini Native (`/v1beta/models/...`)	Kompatibel OpenAI (`/v1/chat/completions`)
Kontrol pemikiran	`thinkingConfig` dengan `thinkingLevel` / `thinkingBudget`	Tidak tersedia
Grounding Google Search	`tools: [\{"google_search": \{\}\}]`	Tidak tersedia
Grounding Google Maps	`tools: [\{"googleMaps": \{\}\}]`	Tidak tersedia
Modalitas pembuatan gambar	`responseModalities: ["IMAGE"]`	Tidak tersedia
Header auth	`x-goog-api-key` atau `Bearer`	Hanya `Bearer`
Format response	Format native Gemini (`candidates`, `parts`)	Format OpenAI (`choices`, `message`)

Otorisasi

x-goog-api-key

string

header

wajib

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

Parameter Path

model

string

wajib

Gemini model ID. Example: gemini-3-flash-preview, gemini-2.5-pro. See the Models page for current options.

operator

enum<string>

wajib

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

Opsi yang tersedia:

generateContent,

streamGenerateContent?alt=sse

Body

application/json

contents

object[]

Conversation content. Each entry has an optional role (user or model) and a parts array.

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.

Buat Message

Sebelumnya

API pembuatan dan pengeditan gambar

Selanjutnya

import os
from google import genai

client = genai.Client(
    api_key=os.environ["COMETAPI_KEY"],
    http_options={"api_version": "v1beta", "base_url": "https://api.cometapi.com"},
)

response = client.models.generate_content(
    model="gemini-3-flash-preview",
    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
          }
        ]
      },
      "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": {
    "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>"
}

Moderasi konten

Kunci API

Quick start

Kirim input video

Konfigurasikan thinking (reasoning)

Stream respons

Atur instruksi sistem

Minta output JSON

Grounding dengan Google Search

Contoh response

Perbandingan dengan endpoint kompatibel OpenAI

Otorisasi

Parameter Path

Body

Respons

​Quick start

​Kirim input video

​Konfigurasikan thinking (reasoning)

​Stream respons

​Atur instruksi sistem

​Minta output JSON

​Grounding dengan Google Search

​Contoh response

​Perbandingan dengan endpoint kompatibel OpenAI

Otorisasi

Parameter Path

Body

Respons

Quick start

Kirim input video

Konfigurasikan thinking (reasoning)

Stream respons

Atur instruksi sistem

Minta output JSON

Grounding dengan Google Search

Contoh response

Perbandingan dengan endpoint kompatibel OpenAI