Megatron MarketsWholesale
Sign inContact Us
Models Model details

Meta Llama

Meta: Llama 3.1 70B Instruct

meta-llama/llama-3.1-70b-instruct

Enquire about this model Request a quote

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy.

Input
$0.4

/ 1M tokens

Output
$0.4

/ 1M tokens

Context window
131.07K

tokens

Limits

Context

131,072

tokens

Max output

16,384

13% of the context window

Parameters

70,553,706,496

Model facts

Author

Meta Llama

Tokenizer

Llama3

Modality

Text -> Text

Instruction format

Llama3

License

Llama3.1

Knowledge cutoff

2023-12-31

Created

Jul 23, 2024

Hugging Face

meta-llama/Meta-Llama-3.1-70B-Instruct

Publication status

Hugging Face: verifiedLicense: publishedParameter count: published

Modalities

Input · TextOutput · Text

Generation controls

Frequency penaltyLogit biasMax tokensMin pPresence penaltyRepetition penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop kTop p

Capability scores

6.6
Intelligence index

Better than 6% of models compared