AI model comparison

LFM3-1.7B vs Gemma 4 31B

Side by side comparison of LFM3-1.7B and Gemma 4 31B on pricing, benchmark scores, context window, and more.

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers.

Input / 1M
$0.08
Output / 1M
$0.20
Context
262K

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.

Input / 1M
$0.20
Output / 1M
$0.40
Context
262K

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

liquid logo

LFM3-1.7B

2.3x cheaper for a typical chat

Higher intelligence score

liquid logo

LFM3-1.7B

6 vs 4.4 on Artificial Analysis

Larger context window

Tie

262K vs 262K tokens

Newer release

liquid logo

LFM3-1.7B

Released November 6, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

liquid logoLFM3-1.7B6
google logoGemma 4 31B4.4

Coding index

liquid logoLFM3-1.7BNot available
google logoGemma 4 31B43.4

Agentic index

liquid logoLFM3-1.7BNot available
google logoGemma 4 31B4.2

Pricing

LFM3-1.7B vs Gemma 4 31B API pricing

Per-token API rates. Cheaper option highlighted.

Metricliquid logoLFM3-1.7Bgoogle logoGemma 4 31B
Input tokensPer 1M tokens$0.08$0.20
Output tokensPer 1M tokens$0.20$0.40
Cached input (read)Per 1M tokens$0.02Not available
Cache writePer 1M tokensNot availableNot available

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

liquid logoLFM3-1.7B$0.26
google logoGemma 4 31B$0.60

Coding task

30K in, 4K out

liquid logoLFM3-1.7B$3.20$1.40 cached
google logoGemma 4 31B$7.60

Long document summary

150K in, 2K out

liquid logoLFM3-1.7B$12.40$3.40 cached
google logoGemma 4 31B$30.80

Specs

Context window and capabilities

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

Metricliquid logoLFM3-1.7Bgoogle logoGemma 4 31B
Context window262K tokens262K tokens
Max output8K tokens16K tokens
Input typesTextImage, Text, Video
Output typesTextText
Reasoning effort levelsNot availableNot available
Default reasoning effortNot availableNot available
Release dateNovember 6, 2026April 2, 2026

Features

Supported features

API features available for each model.

Metricliquid logoLFM3-1.7Bgoogle logoGemma 4 31B
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

LFM3-1.7B is 2.3x cheaper for a typical chat. LFM3-1.7B scores higher on the Artificial Analysis Intelligence Index (6 vs 4.4). 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 LFM3-1.7B or Gemma 4 31B cheaper?

LFM3-1.7B is cheaper for a typical chat (2K input tokens and 500 output tokens). LFM3-1.7B costs $0.08 per 1M input tokens and $0.20 per 1M output tokens, while Gemma 4 31B costs $0.20 per 1M input tokens and $0.40 per 1M output tokens.

Which has a bigger context window, LFM3-1.7B or Gemma 4 31B?

LFM3-1.7B supports up to 262K tokens of context, compared with 262K for Gemma 4 31B.

Is LFM3-1.7B smarter than Gemma 4 31B?

On the Artificial Analysis Intelligence Index, LFM3-1.7B scores 6 and Gemma 4 31B scores 4.4, putting LFM3-1.7B ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use LFM3-1.7B and Gemma 4 31B at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see LFM3-1.7B and Gemma 4 31B answer side by side and keep the better response.

liquid logogoogle logo

Why choose? Ask both.

Send one prompt to LFM3-1.7B and Gemma 4 31B at the same time. Compare the answers side by side and keep the best one.