Gemma 4 12B Instruct: API pricing, providers and specs
Gemma 4 12B Instruct is a text model by Google. One provider serves it: SiliconFlow, at $0.30 /1M.
How Gemma 4 12B Instruct compares
Against the 737 text models on the site priced the same way.
- Cheap for its class: at $0.30 /1M, its lowest price undercuts 76% of comparable models (median $1.10).
- 1 providers serve it; 0% of comparable models have fewer.
- Its weights are open under the Apache 2.0 license: commercial use allowed.
Gemma 4 12B Instruct prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 SiliconFlow | $0.10/1M | $0.30/1M | — | — |
Specs
- Type
- Text
- Maker
- Inputs
- Text
- Outputs
- Text
- Context
- —
- Max output
- —
- Capabilities
- —
- Released
- May 23, 2026
- License
- Apache 2.0commercial use allowed
- Open weights
- Yes, downloadable
- Parameters
- 12B
- Monthly searches
- 2K
4 uncensored versions · See them
Alternatives to Gemma 4 12B Instruct
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Gemma 4 12B Instructthis model | $0.30/1M | — | — | 1 |
 GLM-5.3-Flash | $0.20/1M | 1.05M | 1608 | 45 |
 Qwen3.8 27B | $0.50/1M | 262K | 1591 | 33 |
| GPT-6 Luna | $0.40/1M | 1.05M | 1578 | 28 |
| Claude Haiku 5.5 | $0.30/1M | 1M | 1585 | 27 |
 MiMo-V2.6-Pro | $0.696/1M | 1.05M | 1625 | 21 |
| Qwen3.8 Flash Next | $0.376/1M | 262K | 1628 | 5 |
 DeepSeek V4 Flash | $0.17/1M | 1.05M | — | 26 |
| DeepSeek V4 Flash Vision Exp | $0.294/1M | 1.05M | — | 26 |
More from Google
Gemini 4 ArgonGoogle$8/1MNano Banana 2Google$0.067/imgVeo-3Google$2.50/runNano Banana Pro PreviewGoogle$0.09/runGemini Omni 1.1Google$0.05/secNano Banana 2.1Google$6/1MGemini 3 FlashGoogle$2.40/1MVeo 3.1Google$0.16/secGemma 4 12B Instruct FAQ
The lowest price for Gemma 4 12B Instruct is $0.30 /1M, at SiliconFlow.
Yes. Gemma 4 12B Instruct's weights can be downloaded from its maker's Hugging Face page, under the Apache 2.0 license.
About 12B, as the safetensors metadata of its official Hugging Face repo states.
1 API providers serve Gemma 4 12B Instruct. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us