Gemma 3 12B — pricing & specs
Gemma 3 12B is a nano model from Google, at capability tier 2 of 8. Live $/M-token pricing and specs from the Mintok catalog.
$/M-token pricing
Open-weights model — no per-token list price. Size your self-host $/M-token →
Specifications
- Vendor
- Family
- Gemma 3
- Capability tier
- 2 / 8
- Size class
- NANO
- Category
- GENERAL
- Parameters
- 12B total · 12B active (MoE)
- Context window
- 131,072 tokens
- Licensing
- Proprietary
Carbon footprint (modeled)
Modeled decode on a reference NVIDIA Rubin Ultra VR300 at 50% MBU, batch 32, global-avg grid. Compare all models & grids →
Alternatives at tier 2
Same capability tier, sorted by output price — the cheaper-capable options.
- Qwen 3 30B (MoE)Alibaba$0.50/M out
- LLaMA 3 8BMetaopen/M out
- Mistral 7BMistralopen/M out
- Llama 3.1 8BMetaopen/M out
FAQ
How much does Gemma 3 12B cost per token?
Gemma 3 12B is distributed as open weights — there is no per-token list price; you self-host it. Use the Mintok sizing report to estimate your $/M-token at your volume.
What is Gemma 3 12B's context window?
Gemma 3 12B supports a 131,072-token context window.
What capability tier is Gemma 3 12B?
Gemma 3 12B sits at capability tier 2 of 8 on the Mintok scale (NANO size class).
Is Gemma 3 12B open-source or proprietary?
Gemma 3 12B is a proprietary model from Google, accessed via API.
Put Gemma 3 12B to work
Benchmark it on your prompts, or size a deployment and compare $/M-token against alternatives.
Pricing and specs are maintained by Mintok's catalog watchers from public sources. Not investment advice. Methodology.