// model_detail
active open-weight
Gemma 3 12B
by Google
Mid-size open-weight Gemma. 12B parameters, 128K context, vision.
Context window 128K 128K tokens
Max output 8K 8K tokens
Pricing /1M tok $0.04 in / $0.04 out per 1M tokens (OpenRouter)
Released Mar 12, 2025
// specifications
Specs & capabilities
API details
- API model ID
google/gemma-3-12b-it- Internal ID
gemma-3-12b- Status
- active
- Type
- open-weight
Capabilities
- Vision
- 👁️ Yes
- Function calling
- No
- Knowledge cutoff
- 📅 2025-01
Pricing
- Input
- $0.04 / 1M tokens
- Output
- $0.04 / 1M tokens
- Source
- OpenRouter pricing
// data_confidence
Data notes
⚠️ Pricing shown via OpenRouter, not first-party
// notes
Additional notes
Open-weight, 12B params
// more_from_google
More Google models
Gemini 3.1 Pro preview frontier
Google's most capable model. 1M context, multimodal. Price doubles for context >200K.
Gemini 3.1 Flash-Lite preview fast
Cost-efficient model in the Gemini 3.1 family. 1M context, lowest pricing tier.
Gemini 3 Flash preview balanced
Third-generation Flash model. 1M context, fast and affordable.
Gemini 2.5 Flash-Lite active fast
Smallest 2.5 model. 1M context, best budget option in the Gemini lineup.
Gemini 2.5 Flash active balanced
Second-generation Flash. 1M context, excellent speed/cost ratio. Supports thinking budgets.
Gemini 2.5 Pro active frontier
Previous-gen flagship with thinking budgets. 1M context. Price doubles for context >200K.
// external_links