AiCostCompare

Gemma 2 27B

by Google · google/gemma-2-27b-it · #143 cheapest of 325 paid models

Prices updated Jul 22, 2026, 1:38 AM UTC · refreshed hourly

Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...

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

Pricing

Input

$0.65

per 1M tokens

Output

$0.65

per 1M tokens

Blended (3:1)

$0.65

3 input : 1 output

Cache read

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for Gemma 2 27B (no cache-read rate published — hits billed as normal input).

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.65$0.0669
50%$0.65$0.0669−0%
90%$0.65$0.0669−0%

*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$0.00052$0.52
Document summary8,0001,000$0.00585$5.85
Codebase question (RAG)30,0002,000$0.0208$20.80
Long-context analysis150,0005,000$0.1008$100.75

Specs

Context window

8K

tokens

Max output

2K

tokens

Input modalities

text

Tokenizer

Gemini