Back to all models
meta-llama

Meta: Llama 3.3 70B Instruct

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

meta-llama/llama-3.3-70b-instruct

Context Size

131.072K

Input Price

106,500 pts/M6,550 Ks/M

Output Price

106,500 pts/M6,550 Ks/M


Architecture

Text

Supported Parameters

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Details

TokenizerLlama3
Instruct Typellama3
Max Completion115,200 tokens
Provider Context128K tokens
ModeratedNo
CreatedDec 6, 2024