prices synced 2026-09-11

Gemma 3 4B

Google · Multimodal · Released Mar 2025

Compare

Gemma 3 4B is Google's 4-billion-parameter open-weight text model with a 131K token context window.

Strengths
Small parameter count makes it lightweight and efficient for resource-constrained inference while retaining a large context window for most tasks.
Best for
Local deployment, serverless inference, or any scenario where model size and latency matter more than raw reasoning capability.
Limitations
Smaller parameter count means less capability on complex reasoning or knowledge-intensive tasks compared to larger Gemma variants like Gemma 3 12B or 27B.

Input / 1M

$0.05

Output / 1M

$0.1

Cached input / 1M

Context window

131K

Price history

Price per 1M tokens over timeOutput $0.1; Input $0.05 as of Jun 2026.$0$0.02$0.04$0.06$0.08$0.1Output on 11 Jun 2026: $0.1Out $0.1Input on 11 Jun 2026: $0.05In $0.05Jun 2026

Snapshots

Effective Input Output Cached in Note Source
11 Jun 2026 $0.05 $0.1 Imported from OpenRouter openrouter.ai

More from Google

Report a problem