Gemini 3.5 Flash-Lite

LLM Provider / Model · High-volume classification and extraction at 1M context

At a glance

Input price	$0.30
Output price	$2.50
Cache price	$0.03
Price tier	Budget
Context window	1M+
Max output	64K
Context tier	500K+
Speed tier	Fast
Latency	fast
Knowledge cutoff	Mar 2026
Modality	Multimodal (vision)
Model ID	gemini-3.5-flash-lite
Provider	Google
Benchmark	Cheapest current-generation 1M-context Gemini
Released	Jul 2026
Hosting	Closed/API
Capabilities	Vision, Tool use, Streaming, Function calling, Prompt caching

Vision, Tool use, Streaming, Function calling, Prompt caching

High-volume classification and extraction at 1M context

Trae's built-in model menu may not include Gemini 3.5 Flash-Lite — Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
Kiro's spec mode is tuned for Claude models — Gemini 3.5 Flash-Lite may work but spec-driven flows are best with Claude.
Cursor's built-in model menu may not include Gemini 3.5 Flash-Lite — verify it's available in your Cursor model picker.
OpenAI Codex (VS Code) is tied to OpenAI's hosted GPT-5 and Codex models — Gemini 3.5 Flash-Lite is not selectable inside this integration.
Claude Code only works with Claude models — your LLM is Gemini 3.5 Flash-Lite.
Devin uses Cognition's proprietary model internally — your selected Gemini 3.5 Flash-Lite will be ignored.
OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Gemini 3.5 Flash-Lite will be ignored.
The Claude Code SDK is tuned for Claude models — Gemini 3.5 Flash-Lite may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
Lovable uses a fixed internal model — your selected Gemini 3.5 Flash-Lite will be ignored.
Replit Agent 3 uses its own model selection internally — your selected Gemini 3.5 Flash-Lite will be ignored.

Build a full stack around Gemini 3.5 Flash-Lite — Flowpicker shows compatibility warnings before you commit.