Context
131K
Max output
131K
Serving providers
2
Cheapest input
$0.04 /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
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
EvalComputeProxy5.9default
GPQA Diamond29%default
Humanity's Last Exam5%default
IFBench28%default
LiveCodeBench11%default
Long-Context Reasoning6%default
MMLU-Pro42%default
MMMU-Pro30%default
Omniscience-83.3default
SciCode7%default
TerminalBench Hard1%default
TerminalBench v2.10%default
τ-bench Banking0%default
τ²-bench5%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
DeepInfraCheapest$0.04$0.081
ComponentUnitStandardBatchCached
Text input/1M tok$0.0400
Text output/1M tok$0.0800
Amazon BedrockCheapest$0.04$0.081

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.010$0.020$0.030$0.040Jul 30Sep 8Sep 10Jun 22$0.040$0.020

Cost calculator

estimate your monthly spend on this model
$14
estimated / month

Model IDs

copy the exact identifier for your platform
deepinfra/google/gemma-3-4b-itgoogle.gemma-3-4b-it

Frequently asked questions

Gemma 3 4B pricing, context and availability

How much does Gemma 3 4B cost?

Gemma 3 4B costs $0.04 per 1M input tokens and $0.08 per 1M output tokens at its cheapest provider via DeepInfra.

What is the context window of Gemma 3 4B?

Gemma 3 4B accepts up to 131K tokens of context and can return up to 131K output tokens.

Which providers serve Gemma 3 4B?

Gemma 3 4B is available from 2 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.

What can Gemma 3 4B do?

Gemma 3 4B supports image input (vision) and tool use.

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