Back to all models
meta-llama
Meta: Llama 3 8B Instruct
Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...
meta-llama/llama-3-8b-instruct
Context Size
8.192K
Input Price
6,000 pts/M
Output Price
6,000 pts/M
Architecture
Text
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstoptemperaturetop_ktop_p
Details
TokenizerLlama3
Instruct Typellama3
Max Completion8,192 tokens
Provider Context8.192K tokens
ModeratedNo
CreatedApr 18, 2024