token.app › Google › Gemma 3 4B

Gemma 3 4B pricing & benchmarks

Gemma 3 4B is available from Google at $0.040 per million input tokens and $0.050 per million output tokens ($0.042 blended at 3:1). It accepts up to 131,072 tokens of context. Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Pricing
Per million tokens · OpenRouter
Input$0.040
Output$0.050
Blended (3:1)$0.042
Specification
google/gemma-3-4b-it
Context window131K
Max output118K
ReleasedMar 2025
LicenceOpen weights
Modalitiesin:text, in:image, out:text
No independently-run benchmark scores are published for Gemma 3 4B yet. We show nothing rather than reprinting an unverified figure.
Where to run Gemma 3 4B
2 hosts · 1.5× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
HostBlended $/1MIn / OutContextWeightsUptime 24h
Parasail $0.042 $0.040 / $0.050 131K bf16 99.8%
DeepInfra $0.063 $0.050 / $0.100 131K bf16 100.0%
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Gemma 3 4B
Gemma 3 4B vs Grok 4.6 Gemma 3 4B vs DeepSeek V4 Flash 0731 Gemma 3 4B vs Inkling Small Gemma 3 4B vs Qwen3.7 Flash Gemma 3 4B vs Claude Opus 5 Gemma 3 4B vs Inkling Gemma 3 4B vs Kimi K3 Gemma 3 4B vs GPT-5.6 Luna
FAQ
How much does Gemma 3 4B cost?
Gemma 3 4B costs $0.040 per million input tokens and $0.050 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.042 per million tokens.
What is Gemma 3 4B's context window?
Gemma 3 4B accepts up to 131,072 tokens of context, and can generate up to 117,964 output tokens.