Gemini 3.5 Flash-Lite

Gemini 3.5 Flash-Lite is Google’s fastest and lowest-cost model in the Gemini 3.5 family. It is designed for high-throughput subagent execution, document parsing, data extraction, routing, and classification through the native Gemini API.

Key capabilities

1M token context - Up to 1,048,576 input tokens and 65,536 output tokens
Multimodal input - Text, image, video, audio, and PDF input; text output
High throughput - Optimized for latency-sensitive document parsing and bulk extraction
Subagents - Improved tool reliability for code execution, search, and multi-step workflows
Structured extraction - Strong document understanding, tabular processing, and JSON output
Tools - Function calling, code execution, File Search, Google Search, Google Maps, URL context, and structured output
Thinking - minimal by default; use medium or high for autonomous tool use and multi-step reasoning

Quick example

curl "https://www.anyfast.ai/v1beta/models/gemini-3.5-flash-lite:generateContent?key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [{ "text": "Extract the invoice number, date, and total as JSON." }]
      }
    ],
    "generationConfig": {
      "thinkingConfig": {
        "thinkingLevel": "minimal"
      },
      "responseMimeType": "application/json",
      "maxOutputTokens": 1024
    }
  }'

import requests

response = requests.post(
    "https://www.anyfast.ai/v1beta/models/gemini-3.5-flash-lite:generateContent",
    params={"key": "YOUR_API_KEY"},
    json={
        "contents": [{
            "role": "user",
            "parts": [{"text": "Extract the invoice number, date, and total as JSON."}],
        }],
        "generationConfig": {
            "thinkingConfig": {"thinkingLevel": "minimal"},
            "responseMimeType": "application/json",
            "maxOutputTokens": 1024,
        },
    },
)
response.raise_for_status()
print(response.json()["candidates"][0]["content"]["parts"][0]["text"])

API changes

Do not send temperature, topP, or topK. Google has deprecated these sampling parameters for Gemini 3.6 Flash and Gemini 3.5 Flash-Lite. Also remove candidateCount and legacy thinkingBudget configurations.

Requests must not end with a non-empty model role turn. End the conversation with a non-empty user turn; otherwise the API returns HTTP 400.

Parameters

Parameter	Type	Required	Description
`key`	string	Yes	API key in the query string
`contents`	array	Yes	Conversation turns containing text or multimodal parts
`systemInstruction`	object	No	System instruction with a `parts` array
`generationConfig.thinkingConfig.thinkingLevel`	string	No	`minimal` (default), `medium`, or `high`
`generationConfig.maxOutputTokens`	integer	No	Maximum output tokens, up to 65,536
`generationConfig.responseMimeType`	string	No	Output MIME type, such as `application/json`
`generationConfig.responseSchema`	object	No	JSON schema used with structured output

API Reference

View the interactive API reference for Gemini 3.5 Flash-Lite.

Getting started

Model Introduction

Resources

Gemini 3.5 Flash-Lite

Key capabilities

Quick example

API changes

Parameters

API Reference

Official references

​Key capabilities

​Quick example

​API changes

​Parameters

API Reference

​Official references

Key capabilities

Quick example

API changes

Parameters

Official references