Gemma 3 12B pricing & benchmarks
Gemma 3 12B is available from Google at $0.050 per million input tokens and $0.150 per million output tokens ($0.075 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$0.050
Output$0.150
Blended (3:1)$0.075
Specification
google/gemma-3-12b-it
Context window131K
Max output16K
ReleasedMar 2025
LicenceOpen weights
Modalitiesin:text, in:image, out:text
No independently-run benchmark scores are published for Gemma 3 12B yet. We show nothing rather than reprinting an unverified figure.
Where to run Gemma 3 12B
4 options across 2 providers · 2.0× 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.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfra (bf16/flex) | $0.060 | $0.040 / $0.120 | 131K | bf16 | 100.0% |
| DeepInfra | $0.075 | $0.050 / $0.150 | 131K | bf16 | 100.0% |
| DeepInfra (bf16/priority) | $0.112 | $0.075 / $0.225 | 131K | bf16 | 100.0% |
| NextBit | $0.119 | $0.100 / $0.175 | 131K | int4 | 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 12B
FAQ
How much does Gemma 3 12B cost?
Gemma 3 12B costs $0.050 per million input tokens and $0.150 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.075 per million tokens.
What is Gemma 3 12B's context window?
Gemma 3 12B accepts up to 131,072 tokens of context, and can generate up to 16,384 output tokens.