v1
latestOpenAPI 3.1.02026-07-224941145.6 KBText Generation (Streaming)
Generate model response in streaming mode via SSE.
post/v1beta/models/gemini-2.5-pro:streamGenerateContent
Query parameters
keystring required
API Key
altstring
Set to sse for Server-Sent Events streaming
Request body
Example request
{
"contents": [
{
"role": "user",
"parts": [
{
"text": "Hello, tell me about yourself."
}
]
}
],
"systemInstruction": {
"parts": [
{
"text": "You are a helpful assistant."
}
]
},
"generationConfig": {
"temperature": 1
}
}Response
Streaming response generated successfully
Example response
{
"candidates": [
{
"content": {
"parts": [
{
"inlineData": {
"mimeType": "image/jpeg"
},
"fileData": {
"mimeType": "application/pdf"
},
"executableCode": {
"language": "PYTHON"
},
"codeExecutionResult": {
"outcome": "OUTCOME_OK"
}
}
]
},
"finishReason": "STOP"
}
],
"usageMetadata": {
"serviceTier": "standard",
"promptTokensDetails": [
{
"modality": "TEXT"
}
],
"toolUsePromptTokensDetails": [
{
"modality": "TEXT"
}
]
},
"modelVersion": "gemini-3.6-flash"
}