What is Gemini 3.5 Flash Lite API?
Gemini 3.5 Flash Lite is Google's most cost-efficient GA model, optimized for high-volume agentic tasks, translation and simple data processing, with multimodal text, image, video and audio input.
Technical Specifications
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Supported inputs: Audio, Image, Text, Video
- Output: Audio, Text
Gemini 3.5 Flash Lite API Pricing
- Input: $0.39 / 1M tokens
- Output: $3.25 / 1M tokens
- Cached input: $0.039 / 1M tokens
- Google Search grounding: $0.0455 per call
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Use Gemini 3.5 Flash-Lite for high-volume, latency-sensitive tasks such as translation and document processing.
It is documented as suited to agentic workflows, including subagent tasks and lightweight autonomous workflows that need fast inference at minimal cost.
It is also suited to coding-related work, including simple coding tasks and code-generation workflows.
For multimodal workloads, it is described as useful for complex video reasoning and receipt translation and summarization at scale.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "google/gemini-3.5-flash-lite", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "google/gemini-3.5-flash-lite", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"google/gemini-3.5-flash-lite","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Google Search grounding billed separately at $0.0455 per call. Cached input priced at $0.039/1M.
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 22.7 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Coding | 49.3 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Gemini 3.5 Flash Lite This page | High-volume, cost-efficient agentic tasks | |||
| Reasoning + agents | ||||
| Reasoning + agents | ||||
| Fast, high-volume tasks | ||||
| Agentic coding + high-efficiency reasoning |
Gemini 3.5 Flash Lite has a 1,048,576 tokens context window and can return up to 65,536 tokens.
Gemini 3.5 Flash Lite takes audio, image, text, video as input and returns audio, text.
Use google/gemini-3.5-flash-lite as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Gemini 3.5 Flash Lite became available on July 21, 2026.
Gemini 3.5 Flash Lite is priced at input $0.39 / 1M tokens, output $3.25 / 1M tokens, cached input $0.039 / 1M tokens.
Yes, Gemini 3.5 Flash Lite can stream responses as they are generated.
Yes, Gemini 3.5 Flash Lite accepts image input alongside text.
Gemini 3.5 Flash Lite was built by Google.
It suits high-volume agentic tasks, translation, and simple data processing where cost efficiency matters.
Not enough information to compare these two models.
Yes, it supports tools, function calling, and parallel tool calls.
