HASTATAgent stack guide gemma
Google Gemma 3 12B
Open Gemma instruction model for efficient chat and self-hosted deployments
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
Minimum context128K
Output128K
Providers6
CapabilitiesTool calling, Image input
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 Nvidiagoogle/gemma-3-12b-it | $0.00 | $0.00 | Unavailable | 128K | 2025-03-12 |
 NanoGPTunsloth/gemma-3-12b-it | $0.27 | $0.27 | $0.14 | 128K | 2025-03-10 |
 OpenRoutergoogle/gemma-3-12b-it | $0.050 | $0.15 | Unavailable | 128K | 2025-03-13 |
 Heliconegemma-3-12b-it | $0.050 | $0.100 | Unavailable | 128K | 2024-12-01 |
 NovitaAIgoogle/gemma-3-12b-it | $0.050 | $0.10 | Unavailable | 128K | 2025-03-13 |
 Kilo Gatewaygoogle/gemma-3-12b-it | $0.050 | $0.15 | Unavailable | 128K | 2025-03-13 |
Lowest reported provider price in USD per 1M tokens; unavailable is not free. Provider documentation remains authoritative. Catalogue presence is not an uptime, security, or quality endorsement.
Source metadata and limitations
Capabilities are source-reported. Tool calling does not prove quality in a particular harness. Prices and limits can change.
Modalities: text, image → text