Context
256K
Max output
256K
Serving providers
1
Cheapest input
$0.13 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Headline indices
39.3
of 100
11.0
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%reasoning: false
EvalComputeProxy456.9default
GDPval761.3default
GPQA Diamond79%default
Humanity's Last Exam18%default
IFBench72%default
IT-Bench SRE24%default
Long-Context Reasoning56%default
MMMU-Pro69%default
Omniscience-48.1default
SciCode40%default
TerminalBench Hard25%reasoning: false
TerminalBench v2.139%default
τ-bench Banking12%default
τ²-bench44%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Amazon BedrockCheapest$0.13$0.401
ComponentUnitStandardBatchCached
Text input/1M tok$0.1300
Text output/1M tok$0.4000

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.100$0.200$0.300$0.400Jun 12Jun 22$0.400$0.130

Cost calculator

estimate your monthly spend on this model
$58
estimated / month

Model IDs

copy the exact identifier for your platform
bedrock_mantle/google.gemma-4-26b-a4b

Frequently asked questions

Gemma 4 26B A4b pricing, context and availability

How much does Gemma 4 26B A4b cost?

Gemma 4 26B A4b costs $0.13 per 1M input tokens and $0.40 per 1M output tokens at its cheapest provider via Amazon Bedrock.

What is the context window of Gemma 4 26B A4b?

Gemma 4 26B A4b accepts up to 256K tokens of context and can return up to 256K output tokens.

What can Gemma 4 26B A4b do?

Gemma 4 26B A4b supports image input (vision), tool use and reasoning.

Other Google models

compare pricing across the Google lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI