Skip to content
LLMs
Google logo

Google: Gemma 3 27B

by Google

Google: Gemma 3 27B is a large language model from Google. It costs $0.080 per million input tokens and $0.450 per million output tokens. Its context window is 131K tokens.

Tool callingStructured outputPrompt cachingOpen weightsimage input
Input / 1M tokens
$0.080
Output / 1M tokens
$0.450
Cached input / 1M
$0.040

On repeated prefixes

Context window
131K

tokens

Who serves it cheapest

4 hosts serve Gemma 3 27B. Same weights, same API - the price difference is pure margin and routing.

Providers serving Google: Gemma 3 27B, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
DeepInfraCheapestfp8$0.080$0.160131K-99.6%
Novitabf16$0.119$0.20098K-92.5%
Nebiusfp8$0.100$0.300110K-76.3%
Parasailfp8$0.080$0.450131K-99.7%

The spread between DeepInfra and Parasail is 1.7× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
4.9
Coding index
10.1
Agentic index
0.1

About Gemma 3 27B

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,...

Specifications

Google: Gemma 3 27B specifications
Model IDgoogle/gemma-3-27b-it
ProviderGoogle
Context window131K tokens
Max output118K tokens
Input modalitiestext, image
Output modalitiestext
Knowledge cutoff2024-08-31
Open weightsYes - google/gemma-3-27b-it
ReleasedMarch 12, 2025

Cheaper alternatives

Models that cost less than Gemma 3 27B while keeping at least half its context window and every input modality it supports.

Gemma 4 31B

$0.090 in · $0.340 out

1.1× cheaper

Ministral 3 8B 2512

$0.150 in · $0.150 out

1.1× cheaper

Llama 4 Scout

$0.100 in · $0.300 out

1.1× cheaper

Gemma 4 26B A4B

$0.090 in · $0.300 out

1.2× cheaper

GPT-5 Nano

$0.050 in · $0.400 out

1.3× cheaper

Frequently asked

How much does Google: Gemma 3 27B cost?

$0.080 per million input tokens and $0.450 per million output tokens. Cached input reads cost $0.040 per million tokens.

What is the context window of Google: Gemma 3 27B?

131K tokens, with up to 118K tokens of output per request.

Which provider serves Google: Gemma 3 27B cheapest?

DeepInfra at $0.080 per million input tokens - 1.7× cheaper than Parasail, the most expensive of the 4 hosts serving it.

Confirm against the source: Google official pricing.