Google: Gemma 3 12B
Gemma 3 12B from Google is designed for handling both text and image inputs within an expansive context of up to 131072 tokens. While it supports tools integration, it lacks reasoning capabilities and does not offer structured output formats. Pricing stands at $0.05 per million input tokens and $0.15 per million output tokens. This model should be considered for users who need versatility in handling text and image inputs; however, its lack of reasoning limits its suitability for complex tasks requiring deep analysis or decision-making processes. With a benchmark blended score of 4.6 across three independent benchmarks, it performs well but may not be the best choice if you prioritize reasoning abilities or detailed structured outputs.
Benchmark results
Independent, published benchmarks. Blended score 4.6 across 3 benchmarks, last refreshed 2026-07-23. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 9.1 |
| AI Index Coding | software engineering tasks | 9.5 |
| AI Index Agentic | multi-step tool-using tasks | 0.5 |
- Model ID
- google/gemma-3-12b-it
- Vendor
- Released
- March 2025
- Tokenizer
- Gemini
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 16,384 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.05/M input and $0.15/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.03 |
| A month of a busy support chatbot | 5M in / 2M out | $0.55 |
Similar models
Google: Nano Banana Pro (Gemini 3 Pro Image)
Google: Lyria 3 Pro Preview
Google: Lyria 3 Clip Preview
Google: Nano Banana 2 (Gemini 3.1 Flash Image)
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
Google: Gemma 3 27B
Quick answers
- How much does Google: Gemma 3 12B cost?
- $0.05 per million input tokens and $0.15 per million output tokens.
- What is Google: Gemma 3 12B's context window?
- 131,072 tokens, roughly 196 pages of text in a single request.
- Does Google: Gemma 3 12B support tool calling?
- It supports tool calling, structured output.
- Can Google: Gemma 3 12B process images?
- Yes, it accepts image input.