Gemma 3 12B IT
Summary
Gemma 3 12B IT is an open-weight language model from Google DeepMind, released on 12 Mar 2025. It accepts text and images and generates text, with a 131K-token context window and up to 131K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.05 per million input tokens and $0.10 per million output tokens (Novita AI), across 6 providers we track.
Open multimodal Gemma instruction model for multilingual text generation and image understanding
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Google DeepMind |
|---|---|
| Release date | 12 Mar 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | gemma [Hugging Face] |
| Parameters | 12.2B [Hugging Face] |
| Context window | 131K (131,072 tokens) [models.dev] |
| Max output | 131K tokens [models.dev] |
| Knowledge cutoff | Aug 2024 [models.dev] |
| Input | Text and images [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | google/gemma-3-12b-it [Hugging Face] |
Gemma 3 12B IT API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| NVIDIA NIM google/gemma-3-12b-it | Free | Free | – | 131K | models.dev, 4 Oct 2026 |
| Novita AI google/gemma-3-12b-it | $0.05 | $0.10 | – | 131K | models.dev, 4 Oct 2026 |
| Hugging Face Inference Providers google/gemma-3-12b-it | $0.05 | $0.15 | – | 131K | models.dev, 4 Oct 2026 |
| DeepInfra google/gemma-3-12b-it | $0.05 | $0.15 | – | 131K | models.dev, 4 Oct 2026 |
| OpenRouter google/gemma-3-12b-it | $0.05 | $0.15 | – | 131K | OpenRouter, 4 Oct 2026 |
| Amazon Bedrock google.gemma-3-12b-it | $0.09 | $0.29 | – | 131K | models.dev, 4 Oct 2026 |
Frequently asked questions
What is the context window of Gemma 3 12B IT?
Gemma 3 12B IT has a context window of 131,072 tokens (131K) and can generate up to 131,072 tokens in a single response, according to models.dev.
How much does the Gemma 3 12B IT API cost?
Gemma 3 12B IT is listed from $0.05 per million input tokens and $0.10 per million output tokens (Novita AI). Prices last verified 4 Oct 2026.
Is Gemma 3 12B IT open source?
Gemma 3 12B IT is an open-weight model: its weights are published on Hugging Face as google/gemma-3-12b-it under the gemma license. Check the license terms before commercial use.
When was Gemma 3 12B IT released?
Google DeepMind released Gemma 3 12B IT on 12 Mar 2025, according to models.dev.
Which providers offer Gemma 3 12B IT?
We track Gemma 3 12B IT on 6 providers: NVIDIA NIM, Novita AI, Hugging Face Inference Providers, DeepInfra, OpenRouter, Amazon Bedrock.
Change history
No changes detected since we started tracking this model. We re-check every source daily.
Sources
- https://openrouter.ai/google/gemma-3-12b-it
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/google/gemma-3-12b-it.toml
- https://huggingface.co/google/gemma-3-12b-it
- https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/google/gemma-3-12b-it.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/google/gemma-3-12b-it.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/google/gemma-3-12b-it.toml
- https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/google.gemma-3-12b-it.toml