Google: Gemma 3 4B
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,...
| Specifications | |
|---|---|
| Provider | |
| Input pricing | $0.05/M tokens |
| Output pricing | $0.10/M tokens |
| Context length | 131K tokens |
| Max output | 16K tokens |
| Input modalities | textimage |
| Output modalities | text |
| Tokenizer | Gemini |
| Knowledge cutoff | 2024-08-31 |
| Content moderated | No |
| HuggingFace | google/gemma-3-4b-it |
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p