Google: Gemma 3 12B
google/gemma-3-12b-it
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,...
Prompt $/1M
$0.050
Completion $/1M
$0.150
Context
131,072 tok
Best provider
135 tok/s · SambaNova
Specs
- Model id
- google/gemma-3-12b-it
- Display name
- Google: Gemma 3 12B
- Modality
- text+image->text
- Tokenizer
- Gemini
- Instruct type
- gemma
- Context length
- 131,072
- Max completion
- 16,384
- Prompt $/1M
- $0.050
- Completion $/1M
- $0.150
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptyes
- Visionyes
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| SambaNovafastest | 135 |
| Cloudflarefastest | 49 |
| DeepInfrafastest | 35 |