modelgrep
G

Google: Gemma 3 27B

google/gemma-3-27b-it

169th smartest of 180Cheaper than 86% of paidToolsJSONVision
Use via OpenRouter ↗
Intelligence
10.3
169th of 180
Design Elo
Speed
40
203rd fastest
Latency
538ms
first token
Input price
$0.080
41st cheapest
Context
131K
16K max out

How it compares

Smarter than6%
of all ranked models
Faster than34%
of all ranked models
Cheaper than86%
of all ranked models

Overview

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Benchmarks

independent · via OpenRouter
Artificial Analysis8th percentile
Intelligence Index
10.3
Coding Index
9.6
Agentic Index
3.5
GPQA Diamond
43%
Humanity's Last Exam
5%
SciCode
21%
Tau²-Bench (agentic)
11%

Providers & pricing (5)

ProviderIn $/MOut $/MUptime
DeepInfrafp8$0.080$0.160
Parasailfp8$0.080$0.45099.9%
Nebiusfp8$0.100$0.30066.8%
Novitabf16$0.119$0.20082.7%
Phala$0.150$0.46088.9%

Specifications

Context window131K
Max output16K
Knowledge cutoffAug 2024
Input modalitiestext, image
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Gemma 3 27B FAQ

How much does Gemma 3 27B cost?

Gemma 3 27B costs $0.080 per million input tokens and $0.160 per million output tokens via OpenRouter, making it 41st cheapest of 298 paid models.

How smart is Gemma 3 27B?

Gemma 3 27B scores 10.3 on the Artificial Analysis Intelligence Index, ranking 169th of 180 benchmarked models, with a GPQA Diamond score of 43%.

How fast is Gemma 3 27B?

Gemma 3 27B generates around 40 tokens per second with 538ms time-to-first-token (p50), the 203rd fastest tracked model.

What is Gemma 3 27B's context window?

Gemma 3 27B supports a 131K-token context window and can output up to 16K tokens. It accepts text, image input.

Compare head-to-head