← Model list
Gemma 4 12B Instruct
google·google/gemma-4-12b-it·GA·Open weights·gemma series·NEW
Google's Gemma 4 12B Instruct is an open-weight multimodal model for text, image, audio, and video understanding, with tool calling and structured output support.
At a glance
Reference price$0.06 / $0.30 per 1M
Cache read $0.03 · NanoGPT
Lowest paid$0.06 / $0.30
NanoGPT Gateway
Context262,144
Output limit32,768
Capabilities
Reasoning✓ Tool use✓ Structured output? Temperature✓ Attachments
Modalities
TextImageVideoAudio
Knowledge cutoff—
Released / updated2026-08-01 / 2026-08-01
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 1 providers1 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| NanoGPT | Gateway | $0.06 | $0.30 | $0.03 | — | 262,144 | 32,768 |
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
1NanoGPT$23.40
The cheapest paid channel is the only channel.
Related models
Gemma 4 26B A4Bsame series$0.13 / $0.40Google Gemma 3 27B Instructsame series$0.12 / $0.20Google Gemma 4 26B A4B Instructsame series$0.13 / $0.40Lyria 3 Clip Previewcheaper alternative$0 / $0Granite 4.1 8Bcheaper alternative$0.05 / $0.10Lyria 3 Pro Previewcheaper alternative$0 / $0
Price historyone sample accumulated per data sync
Input listOutput listMin blended