# Gemma 3 12B IT API pricing

No price from the maker itself is on record for Gemma 3 12B IT. The lowest of 13 providers is Helicone: $0.05 per 1M input tokens and $0.1 per 1M output tokens (as of 2026-11-12). Context window: 131K tokens, up to 131K output tokens per request.

- Type: Text
- Context: 131K
- Max output: 131K
- Released: 2025-03-12
- Open weights: Yes

## Price by provider (USD per 1M tokens)

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [Helicone](https://helicone.ai/models) | gemma-3-12b-it | $0.05 | $0.1 | — | Lowest |
| [Novita AI](https://novita.ai/docs/guides/introduction) | google/gemma-3-12b-it | $0.05 | $0.1 | — |  |
| [Kilo Gateway](https://kilo.ai) | google/gemma-3-12b-it | $0.04 | $0.12 | — |  |
| [Deep Infra](https://deepinfra.com/models) | google/gemma-3-12b-it | $0.05 | $0.15 | — |  |
| [Eden AI](https://docs.edenai.co) | deepinfra/google/gemma-3-12b-it | $0.05 | $0.15 | — |  |
| [Hugging Face](https://huggingface.co/docs/inference-providers) | google/gemma-3-12b-it | $0.05 | $0.15 | — |  |
| [OpenRouter](https://openrouter.ai/models) | google/gemma-3-12b-it | $0.05 | $0.15 | — |  |
| [AI/ML API](https://docs.aimlapi.com) | google/gemma-3-12b-it | $0.0529 | $0.1587 | $0.04232 |  |
| [Eden AI](https://docs.edenai.co) | amazon/google.gemma-3-12b-it | $0.09 | $0.29 | — |  |
| [Eden AI](https://docs.edenai.co) | amazon/google.gemma-3-12b-it@us | $0.09 | $0.29 | — |  |
| [Merge Gateway](https://docs.merge.dev/merge-gateway) | google/gemma-3-12b-it | $0.09 | $0.29 | — |  |
| [NanoGPT](https://docs.nano-gpt.com) | unsloth/gemma-3-12b-it | $0.272 | $0.272 | $0.136 |  |
| [Neon](https://neon.com/docs) | gemma-3-12b | $0.15 | $0.5 | — |  |
| [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | google.gemma-3-12b-it | $0.09 | $0.29 | — | Deprecated |
| [Nvidia](https://docs.api.nvidia.com/nim/) | google/gemma-3-12b-it | $0 | $0 | — | Deprecated |

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.

https://apibook.ai/models/google/gemma-3-12b-it/