これをいつ使用するか
generationConfig、thinkingConfig、またはモダリティ設定を転送する必要があります- 統合レイヤーでは Google 固有の機能を引き続き保持する必要があります
Example
{
"model": "gemini-2.5-flash",
"contents": [
{
"role": "user",
"parts": [{ "text": "Summarize this report." }]
}
],
"model_extra": {
"generationConfig": {
"thinkingConfig": { "thinkingBudget": 512 },
"responseMimeType": "application/json"
}
}
}
cURLの例
curl "https://maas.apigo.ai/v1beta/models/gemini-2.5-flash:generateContent" \
-H "Authorization: Bearer $YOUR API KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-2.5-flash",
"contents": [
{
"role": "user",
"parts": [{ "text": "Summarize this report." }]
}
],
"model_extra": {
"generationConfig": {
"thinkingConfig": { "thinkingBudget": 512 },
"responseMimeType": "application/json"
}
}
}'
Python の例
import requests
response = requests.post(
"https://maas.apigo.ai/v1beta/models/gemini-2.5-flash:generateContent",
headers={
"Authorization": "Bearer <YOUR API KEY>",
"Content-Type": "application/json",
},
json={
"model": "gemini-2.5-flash",
"contents": [
{
"role": "user",
"parts": [{"text": "Summarize this report."}],
}
],
"model_extra": {
"generationConfig": {
"thinkingConfig": {"thinkingBudget": 512},
"responseMimeType": "application/json",
}
},
},
)
print(response.json())
Node.js の例
const response = await fetch(
"https://maas.apigo.ai/v1beta/models/gemini-2.5-flash:generateContent",
{
method: "POST",
headers: {
Authorization: `Bearer ${process.env.YOUR API KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "gemini-2.5-flash",
contents: [
{
role: "user",
parts: [{ text: "Summarize this report." }]
}
],
model_extra: {
generationConfig: {
thinkingConfig: { thinkingBudget: 512 },
responseMimeType: "application/json"
}
}
}),
}
);
console.log(await response.json());
ベストプラクティス
- パススルーの前にネストされた構成オブジェクトを検証する
- 回帰追跡のためにモデル名と拡張パラメータの両方を記録します。