Meta Llama
Meta: Llama 4 Maverick
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
| Specifications | |
|---|---|
| Provider | Meta Llama |
| Input pricing | $0.20/M tokens |
| Output pricing | $0.80/M tokens |
| Context length | 1.0M tokens |
| Max output | 16K tokens |
| Input modalities | textimage |
| Output modalities | text |
| Tokenizer | Llama4 |
| Knowledge cutoff | 2024-08-31 |
| Content moderated | No |
| HuggingFace | meta-llama/Llama-4-Maverick-17B-128E-Instruct |
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p