Gemini 2.5 Pro (Stream) - Anyfast

Gemini 2.5 Pro (Stream) provides streaming text generation using Google’s Gemini 2.5 Pro model via Anyfast. Responses are delivered in real-time using Server-Sent Events (SSE).

Key capabilities

SSE Streaming — Real-time token-by-token response delivery
Thinking mode — Supports thinking configuration for enhanced reasoning
Multi-turn conversations — Handles complex dialogue with system instructions
Safety settings — Configurable content safety filters

Quick example

curl "https://www.anyfast.ai/v1beta/models/gemini-2.5-pro:streamGenerateContent?key=YOUR_API_KEY&alt=sse" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [{ "text": "Write a short poem about the ocean." }]
      }
    ],
    "generationConfig": {
      "temperature": 1,
      "topP": 1,
      "thinkingConfig": {
        "includeThoughts": true,
        "thinkingBudget": 26240
      }
    }
  }'

Parameters

Parameter	Type	Required	Description
`key`	string	Yes	API key (query parameter)
`alt`	string	No	Set to `sse` for SSE streaming
`contents`	array	Yes	Array of `{ role, parts }` objects
`systemInstruction`	object	No	System instruction with `parts` array
`generationConfig.temperature`	float	No	`0`–`2`. Controls randomness. Default: `1`
`generationConfig.topP`	float	No	Nucleus sampling threshold. Default: `1`
`generationConfig.thinkingConfig`	object	No	Thinking mode configuration
`safetySettings`	array	No	Content safety filter settings

API Reference

View the interactive API playground for Gemini 2.5 Pro (Stream).

Gemini 2.5 Pro Gemini 2.5 Flash