Sử dụng định dạng API gốc của Gemini thông qua CometAPI để tạo văn bản, đầu vào multimodal, thinking/reasoning, function calling, Google Search grounding, chế độ JSON và streaming.
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>"
}| Thiết lập | Mặc định của Google | CometAPI |
|---|---|---|
| Base URL | generativelanguage.googleapis.com | api.cometapi.com |
| API Key | $GEMINI_API_KEY | $COMETAPI_KEY |
x-goog-api-key và Authorization: Bearer đều được hỗ trợ để xác thực.thinkingLevel để kiểm soát độ sâu lập luận. Các mức khả dụng: 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"}
}
}'
thinkingBudget để kiểm soát chi tiết ở mức Token:0 — tắt thinking-1 — động (model tự quyết định, mặc định)> 0 — ngân sách Token cụ thể (ví dụ: 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}
}
}'
thinkingLevel với các model Gemini 2.5 (hoặc thinkingBudget với các model Gemini 3) có thể gây lỗi. Hãy dùng đúng tham số cho phiên bản model của bạn.streamGenerateContent?alt=sse làm operator để nhận Server-Sent Events khi model tạo nội dung. Mỗi sự kiện SSE chứa một dòng data: với một đối tượng JSON 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"}]}]
}'
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."}]
}
}'
responseMimeType. Bạn có thể tùy chọn cung cấp responseSchema để xác thực schema nghiêm ngặt:
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"
}
}'
googleSearch:
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": {}}]
}'
groundingMetadata với URL nguồn và điểm độ tin cậy.
{
"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"
}
thoughtsTokenCount trong usageMetadata cho biết mô hình đã dùng bao nhiêu token cho suy luận nội bộ, ngay cả khi đầu ra suy nghĩ không được đưa vào phản hồi.| Tính năng | Gemini Native (/v1beta/models/...) | OpenAI-Compatible (/v1/chat/completions) |
|---|---|---|
| Điều khiển suy nghĩ | thinkingConfig với thinkingLevel / thinkingBudget | Không khả dụng |
| Google Search grounding | tools: [\{"google_search": \{\}\}] | Không khả dụng |
| Google Maps grounding | tools: [\{"googleMaps": \{\}\}] | Không khả dụng |
| Phương thức tạo ảnh | responseModalities: ["IMAGE"] | Không khả dụng |
| Header xác thực | x-goog-api-key hoặc Bearer | Chỉ Bearer |
| Định dạng phản hồi | Định dạng native của Gemini (candidates, parts) | Định dạng OpenAI (choices, message) |
Your CometAPI key passed via the x-goog-api-key header. Bearer token authentication (Authorization: Bearer <key>) is also supported.
The Gemini model ID to use. See the Models page for current Gemini model IDs.
"gemini-2.5-flash"
The operation to perform. Use generateContent for synchronous responses, or streamGenerateContent?alt=sse for Server-Sent Events streaming.
generateContent, streamGenerateContent?alt=sse "generateContent"
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
System instructions that guide the model's behavior across the entire conversation. Text only.
Show child attributes
Tools the model may use to generate responses. Supports function declarations, Google Search, Google Maps, and code execution.
Show child attributes
Configuration for tool usage, such as function calling mode.
Show child attributes
Safety filter settings. Override default thresholds for specific harm categories.
Show child attributes
Configuration for model generation behavior including temperature, output length, and response format.
Show child attributes
The name of cached content to use as context. Format: cachedContents/{id}. See the Gemini context caching documentation for details.
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
Feedback on the prompt, including safety blocking information.
Show child attributes
Token usage statistics for the request.
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.
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>"
}