Skip to content
Sovyron

Gemma 3 4B IT

gemma131k context131k max outputreleased Mar 12, 2025Open weightsTool calling

As of Oct 4, 2026, the cheapest Gemma 3 4B IT API price is $0.04 per 1M input tokens (Amazon Bedrock) and $0.08 per 1M output tokens (Amazon Bedrock). Gemma 3 4B IT is offered by 8 providers in the gemma family, open weights. One provider lists it as a free-tier offer.

Cheapest input
$0.04
Cheapest output
$0.08
Official
—
output per 1M tokens
Providers
8
offering this model
Spread
2.5×
max / min output

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.

Gemma 3 4B IT API prices by provider in USD per 1M tokens, updated Oct 4, 2026
Provider1M input1M output1M cache read1M cache writeContext
Amazon BedrockopenCheapest$0.04Cheapest$0.08——131k
Eden AIopen$0.04$0.08——128k
Deep Infraopen$0.05$0.1——131k
Eden AIopen$0.05$0.1——131k
Hugging Faceopen$0.05$0.1——131k
Kilo Gatewayopen$0.05$0.1——131k
OpenRouteropen$0.05$0.1——131k
NanoGPTopen$0.2006$0.2006$0.1003—128k
Nvidiafreefreefree——131k

Gemma 3 4B IT pricing FAQ

What is the cheapest Gemma 3 4B IT API?

As of Oct 4, 2026, Amazon Bedrock has the lowest Gemma 3 4B IT output price at $0.08 per 1M tokens, and Amazon Bedrock has the lowest input price at $0.04 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer Gemma 3 4B IT?

8 providers list Gemma 3 4B IT on Sovyron; 8 of them sell it at a metered per-token price.

Is Gemma 3 4B IT free?

1 provider(s) list a free-tier offer: Nvidia. Free tiers usually have rate limits.

What is the context window of Gemma 3 4B IT?

Gemma 3 4B IT supports a 131k-token context window and up to 131k output tokens.