Gemma 3 12B
Google · Open weights · Released Mar 13, 2025 · google/gemma-3-12b-it
Best $0.05 in / $0.15 out via DeepInfra · bf16
131K contextVisionToolsStructured outputPrompt cachingOpen weights
Available from 4 providersUSD / MTOK · PRICES 16 MINUTES AGO · SPEED 14 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.04 | $0.12 | — | 131K | bf16 | — | — | 0.0% | |
| $0.05 | $0.15 | — | 131K | bf16 | 1.6s | 34 tok/s | 99.7% | |
| $0.075 | $0.225 | — | 131K | bf16 | — | — | 99.3% | |
| $0.35 | $0.45 | $0.05 | 131K | int4 | 4.1s | 70 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 14 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Nov 5, 2026endpoint removed · cheaperinference5 → 4
Oct 23, 2026endpoint added · cheaperinference4 → 5
Oct 8, 2026endpoint added · nextbit1 → 2
About
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,...
Specifications
Context window131,072
Max output16,384
Modalities intext, image
Modalities outtext
LicenseOpen weights
ReleasedMar 13, 2025
Knowledge cutoff2024-08-31
TokenizerGemini
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/google/gemma-3-12b-it)Sources
OpenRouter API16 minutes ago
AGGREGATORHugging Face16 minutes ago
COMMUNITYModelIndex benchmarks16 days ago
MEASUREDVerified 16 minutes ago · list prices, not negotiated rates.