AiCostCompare

Gemma 3 27B

by Google · google/gemma-3-27b-it · #79 cheapest of 422 paid models

Prices updated Sep 19, 2026, 6:22 PM UTC · refreshed hourly

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,...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$0.08

per 1M tokens

Output

$0.45

per 1M tokens

Blended (3:1)

$0.172

3 input : 1 output

Cache read

$0.04

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for Gemma 3 27B with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.172$0.00861
50%$0.157$0.00661−23%
90%$0.145$0.00501−42%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.000175$0.175
Document summary8,0001,000$0.00109$1.09
Codebase question (RAG)30,0002,000$0.0033$3.30
Long-context analysis150,0005,000$0.0143$14.25

Performance

Intelligence Index

4.9

AA composite quality

Coding Index

10.1

Math Index

20.7

Agentic Index

0.1

Output speed

0 tok/s

median

Time to first token

0s

median

Time to first answer

0s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
MMLU-Pro66.9%
GPQA Diamond42.8%
Humanity's Last Exam4.4%
LiveCodeBench13.7%
SciCode23.3%
MATH-50088.3%
AIME25.3%
AIME 202520.7%
IFBench31.8%
AA-LCR (Long Context Reasoning)7.3%
Terminal-Bench Hard3.8%
Terminal-Bench 2.14.5%
τ²-Bench (Telecom)10.5%
τ³-Bench Banking0.8%

Specs

Context window

131K

tokens

Max output

118K

tokens

Input modalities

text, image

Tokenizer

Gemini