Справочник API
Руководства по интеграции
Библиотеки
Цены и оплата
Текстовые модели
Gemini Generating Content
Используйте нативный формат API Gemini через CometAPI для генерации текста, Multimodal-ввода, thinking/reasoning, Function Calling, grounding через Google Search, режима JSON и Streaming.
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-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
}
]
},
"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>"
}CometAPI поддерживает нативный формат API Gemini, предоставляя вам полный доступ к функциям, специфичным для Gemini, таким как управление thinking, grounding через Google Search, нативные modality генерации изображений и многое другое. Используйте этот endpoint, когда вам нужны возможности, недоступные через чат-эндпоинт, совместимый с OpenAI.
Ответ включает
Для аутентификации поддерживаются оба заголовка:
x-goog-api-key и Authorization: Bearer.Быстрый старт
Чтобы использовать любой SDK Gemini или HTTP-клиент с CometAPI, замените базовый URL и API key:| Setting | Google Default | CometAPI |
|---|---|---|
| Base URL | generativelanguage.googleapis.com | api.cometapi.com |
| API Key | $GEMINI_API_KEY | $COMETAPI_KEY |
Настройка thinking (reasoning)
Модели Gemini могут выполнять внутреннее reasoning перед генерацией ответа. Метод управления зависит от поколения модели.- Gemini 3 (thinkingLevel)
- Gemini 2.5 (thinkingBudget)
Модели Gemini 3 используют
thinkingLevel для управления глубиной reasoning. Доступные уровни: MINIMAL, LOW, MEDIUM, HIGH.Используйте gemini-3-flash-preview как модель-пример по умолчанию, если вам не нужен конкретный другой вариант Gemini 3.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"}
}
}'
Модели Gemini 2.5 используют
thinkingBudget для точного управления на уровне Token:0— отключить thinking-1— динамически (модель решает сама, по умолчанию)> 0— конкретный бюджет Token (например,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}
}
}'
Использование
thinkingLevel с моделями Gemini 2.5 (или thinkingBudget с моделями Gemini 3) может вызывать ошибки. Используйте правильный параметр для версии вашей модели.Потоковые ответы
Чтобы получать Server-Sent Events по мере генерации контента моделью, используйтеstreamGenerateContent?alt=sse в качестве operator. Каждое SSE-событие содержит строку data: с JSON-объектом 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"}]}]
}'
Задание system instructions
Чтобы направлять поведение модели на протяжении всего разговора, используйтеsystemInstruction:
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."}]
}
}'
Запрос вывода в JSON
Чтобы принудительно получить структурированный JSON-вывод, задайтеresponseMimeType. При необходимости можно также указать responseSchema для строгой валидации схемы:
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 через Google Search
Чтобы включить веб-поиск в реальном времени, добавьте инструментgoogleSearch:
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": {}}]
}'
groundingMetadata с URL-адресами источников и оценками уверенности.
Пример ответа
Типичный ответ от endpoint Gemini в 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"
}
Поле
thoughtsTokenCount в usageMetadata показывает, сколько Token модель потратила на внутреннее reasoning, даже если thinking-вывод не включён в ответ.Сравнение с endpoint, совместимым с OpenAI
| Feature | Gemini Native (/v1beta/models/...) | OpenAI-Compatible (/v1/chat/completions) |
|---|---|---|
| Thinking control | thinkingConfig with thinkingLevel / thinkingBudget | Недоступно |
| Google Search grounding | tools: [\{"google_search": \{\}\}] | Недоступно |
| Google Maps grounding | tools: [\{"googleMaps": \{\}\}] | Недоступно |
| Image generation modality | responseModalities: ["IMAGE"] | Недоступно |
| Auth header | x-goog-api-key or Bearer | Только Bearer |
| Response format | Gemini native (candidates, parts) | Формат OpenAI (choices, message) |
Авторизации
Your CometAPI key passed via the x-goog-api-key header. Bearer token authentication (Authorization: Bearer <key>) is also supported.
Параметры пути
Gemini model ID. Example: gemini-3-flash-preview, gemini-2.5-pro. See the Models page for current options.
The operation to perform. Use generateContent for synchronous responses, or streamGenerateContent?alt=sse for Server-Sent Events streaming.
Доступные опции:
generateContent, streamGenerateContent?alt=sse Тело
application/json
Show child attributes
Show child attributes
System instructions that guide the model's behavior across the entire conversation. Text only.
Show child attributes
Show child attributes
Tools the model may use to generate responses. Supports function declarations, Google Search, Google Maps, and code execution.
Show child attributes
Show child attributes
Configuration for tool usage, such as function calling mode.
Show child attributes
Show child attributes
Safety filter settings. Override default thresholds for specific harm categories.
Show child attributes
Show child attributes
Configuration for model generation behavior including temperature, output length, and response format.
Show child attributes
Show child attributes
The name of cached content to use as context. Format: cachedContents/{id}. See the Gemini context caching documentation for details.
Ответ
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:.
The generated response candidates.
Show child attributes
Show child attributes
Feedback on the prompt, including safety blocking information.
Show child attributes
Show child attributes
Token usage statistics for the request.
Show child attributes
Show child attributes
The model version that generated this response.
The timestamp when this response was created (ISO 8601 format).
Unique identifier for this response.
⌘I
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-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
}
]
},
"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>"
}