google
Google: Gemma 3 12B (free)
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Quality Score
57/100
composite of price, context, capability
Input Price
Free
per 1M tokens
Output Price
Free
per 1M tokens
Context Window
32,768
tokens
- Model ID
- google/gemma-3-12b-it:free
- Vendor
- Tokenizer
- Gemini
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 8,192 tokens
- Tool Calling
- not supported
- Structured Output
- not supported
- Reasoning Mode
- not supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
Similar models
google
Google: Gemma 3n 4B
$0.06 in / $0.12 out
32,768 ctx
59
google
Google: Gemma 3n 2B (free)
Free
8,192 ctx
54
google
Google: Gemma 3n 4B (free)
Free
8,192 ctx
54
google
Google: Gemma 2 27B
$0.65 in / $0.65 out
8,192 ctx
60
google
Google: Gemma 3 4B (free)
Free
32,768 ctx
62
google
Google: Nano Banana (Gemini 2.5 Flash Image)
$0.30 in / $2.50 out
32,768 ctx
67