← Model list
Gemma 3 12B
google·google/gemma-3-12b-it-2·GA·Open weights·gemma series
Open Gemma instruction model for efficient chat and self-hosted deployments
At a glance
Reference price$0.15 / $0.50 per 1M
Cache read — · Neon
Lowest paid$0.05 / $0.10
NovitaAI Gateway · 3× spread
Context131,072
Output limit8,192
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage
Knowledge cutoff2024-08-31
Released / updated2025-03-13 / 2025-03-13
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence5.5
Value88
Coding5.8
Agentic0.3
Output speed—
TTFT—
Cost per task$0
Value formulaIQ 5.5 ÷ min blended $0.063 = 88
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 3 providers3 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| NovitaAI google/gemma-3-12b-it | Gateway | $0.05 | $0.10 | — | — | 131,072 | 8,192 | |
| OpenRouter google/gemma-3-12b-it | Gateway | $0.05 | $0.15 | — | — | 131,072 | 16,384 | |
| Neon gemma-3-12b | Cloud | $0.15 | $0.50 | — | — | 131,072 | 8,192 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1NovitaAI$15.00
2OpenRouter$17.50
3Neon$55.00
The cheapest paid channel is the only channel.
Related models
Gemma 4 12B Instructsame series$0.06 / $0.30Gemma 4 26B A4Bsame series$0.13 / $0.40Google Gemma 3 27B Instructsame series$0.12 / $0.20Llama 3.2 1B Instructcheaper alternative$0.10 / $0.201Llama 4 Maverick 17B 128E Instruct FP8cheaper alternative$0 / $0Phi 4 Multimodalcheaper alternative$0.08 / $0.32Phi-4-minicheaper alternative$0.075 / $0.30
Price historyone sample accumulated per data sync
Input listOutput listMin blended