AiCostCompare

Gemma 4 26B A4B

by Google · google/gemma-4-26b-a4b-it · #43 cheapest of 325 paid models

Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

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

Pricing

Input

$0.07

per 1M tokens

Output

$0.34

per 1M tokens

Blended (3:1)

$0.138

3 input : 1 output

Cache read

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for Gemma 4 26B A4B (no cache-read rate published — hits billed as normal input).

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.138$0.00748
50%$0.138$0.00748−0%
90%$0.138$0.00748−0%

*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$0.000137$0.137
Document summary8,0001,000$0.0009$0.9
Codebase question (RAG)30,0002,000$0.00278$2.78
Long-context analysis150,0005,000$0.0122$12.20

Performance

Intelligence Index

25.7

AA composite quality

Coding Index

39.3

Math Index

Agentic Index

11

Output speed

0 tok/s

median

Time to first token

0s

median

Time to first answer

0s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
GPQA Diamond79.2%
Humanity's Last Exam18.3%
SciCode40.0%
IFBench72.4%
AA-LCR (Long Context Reasoning)55.7%
Terminal-Bench Hard13.6%
Terminal-Bench 2.139.0%
τ²-Bench (Telecom)43.6%
τ³-Bench Banking11.8%

Specs

Context window

262K

tokens

Max output

16K

tokens

Input modalities

image, text, video

Tokenizer

Gemma