AI model comparison

Gemini 3.5 Flash Lite vs Claude Haiku 4.5

Side by side comparison of Gemini 3.5 Flash Lite and Claude Haiku 4.5 on pricing, benchmark scores, context window, and more.

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities.

Input / 1M
$0.30
Output / 1M
$2.50
Context
1.05M

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.

Input / 1M
$1
Output / 1M
$5
Context
200K

Comparing image generators? Compare image models

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

google logo

Gemini 3.5 Flash Lite

2.4x cheaper for a typical chat

Higher intelligence score

google logo

Gemini 3.5 Flash Lite

11.7 vs 7.4 on Artificial Analysis

Larger context window

google logo

Gemini 3.5 Flash Lite

1.05M vs 200K tokens

Newer release

google logo

Gemini 3.5 Flash Lite

Released July 21, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

google logoGemini 3.5 Flash Lite11.7
anthropic logoClaude Haiku 4.57.4

Coding index

google logoGemini 3.5 Flash Lite49.3
anthropic logoClaude Haiku 4.543.9

Agentic index

google logoGemini 3.5 Flash Lite14.3
anthropic logoClaude Haiku 4.58

Pricing

Gemini 3.5 Flash Lite vs Claude Haiku 4.5 API pricing

Per-token API rates. Cheaper option highlighted.

Metricgoogle logoGemini 3.5 Flash Liteanthropic logoClaude Haiku 4.5
Input tokensPer 1M tokens$0.30$1
Output tokensPer 1M tokens$2.50$5
Cached input (read)Per 1M tokens$0.03$0.10
Cache writePer 1M tokens$0.08$1.25
Web searchPer request$0.014$0.01

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

google logoGemini 3.5 Flash Lite$1.85
anthropic logoClaude Haiku 4.5$4.50

Coding task

30K in, 4K out

google logoGemini 3.5 Flash Lite$19$10.90 cached
anthropic logoClaude Haiku 4.5$50$23 cached

Long document summary

150K in, 2K out

google logoGemini 3.5 Flash Lite$50$9.50 cached
anthropic logoClaude Haiku 4.5$160$25 cached

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metricgoogle logoGemini 3.5 Flash Liteanthropic logoClaude Haiku 4.5
Context window1.05M tokens200K tokens
Max output66K tokens64K tokens
Input typesAudio, File, Image, Text, VideoFile, Image, Text
Output typesTextText
Reasoning effort levelsHigh, Medium, Low, MinimalNot available
Default reasoning effortMinimalNot available
Release dateJuly 21, 2026October 15, 2025

Features

Supported features

API features available for each model.

Metricgoogle logoGemini 3.5 Flash Liteanthropic logoClaude Haiku 4.5
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedNot supported
Verbosity controlNot supportedNot supported

Our take

Gemini 3.5 Flash Lite is 2.4x cheaper for a typical chat. Gemini 3.5 Flash Lite scores higher on the Artificial Analysis Intelligence Index (11.7 vs 7.4). Gemini 3.5 Flash Lite has the larger context window (1.05M vs 200K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is Gemini 3.5 Flash Lite or Claude Haiku 4.5 cheaper?

Gemini 3.5 Flash Lite is cheaper for a typical chat (2K input tokens and 500 output tokens). Gemini 3.5 Flash Lite costs $0.30 per 1M input tokens and $2.50 per 1M output tokens, while Claude Haiku 4.5 costs $1 per 1M input tokens and $5 per 1M output tokens.

Which has a bigger context window, Gemini 3.5 Flash Lite or Claude Haiku 4.5?

Gemini 3.5 Flash Lite supports up to 1.05M tokens of context, compared with 200K for Claude Haiku 4.5.

Is Gemini 3.5 Flash Lite smarter than Claude Haiku 4.5?

On the Artificial Analysis Intelligence Index, Gemini 3.5 Flash Lite scores 11.7 and Claude Haiku 4.5 scores 7.4, putting Gemini 3.5 Flash Lite ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Gemini 3.5 Flash Lite and Claude Haiku 4.5 at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Gemini 3.5 Flash Lite and Claude Haiku 4.5 answer side by side and keep the better response.

google logoanthropic logo

Why choose? Ask both.

Send one prompt to Gemini 3.5 Flash Lite and Claude Haiku 4.5 at the same time. Compare the answers side by side and keep the best one.