Gemma 3 12B
Provider: Google AI US
Input price
$0.05
/ 1M tokens
Output price
$0.15
/ 1M tokens
Context
131K tokens
Max output 16K tokens
Overview
Google AI's Gemma 3 12B is a mid-tier multimodal model built for vision tasks, function-calling, and JSON generation within a 131k context window.
Strengths
- Input pricing matches Llama 3.2 3B at $0.05 per million tokens.
- Supports 128k context windows and handles 140 plus languages.
- Includes native vision, function-calling, and JSON mode capabilities.
Best use cases
- Processing multimodal user inputs with structured JSON output requirements.
- Multilingual chat and reasoning tasks inside 131k token limits.
Pricing position
Output costs $0.15 per million tokens, half the price of Gemini 2.5 Flash Lite.
Caveats
No free tier is available, and output length is capped at 16k tokens.
Notes drafted by an LLM from the figures on this page (2026-11-12) and rewritten when the price changes.
Key facts
- Price basis
- Median third-party host price (no first-party API)
- Max output
- 16K tokens
- Knowledge cutoff
- 2024-08-31
- Listed on OpenRouter
- 2025-03-13
- Tracked since
- 2026-05-08
- Last updated
- 2026-11-10
Features
Image inputFunction callingJSON output
Monthly cost estimate
| Scale | Input (M) | Output (M) | Monthly |
|---|---|---|---|
| 0.1M (hobby) | 0.1 | 0.05 | $0.01 |
| 1M (small app) | 1 | 0.5 | $0.13 |
| 10M (mid scale) | 10 | 5 | $1.25 |
| 100M (large) | 100 | 50 | $12.50 |
※ Cache and batch discounts not factored in. Detailed calculator
Official resources
Other models from Google AI
Similar-priced models
Source: OpenRouter API (google/gemma-3-12b-it)