Meta: Llama 3.1 70B Instruct

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

Created Jul 23, 2024131,072 context
$0.12/M input tokens$0.3/M output tokens

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.

Providers for Llama 3.1 70B Instruct

OpenRouter routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

Context
131K
Max Output
8K
Input
$0.12
Output
$0.3
US
fp8
Context
131K
Max Output
131K
Input
$0.12
Output
$0.3
Context
128K
Max Output
128K
Input
$0.13
Output
$0.4
Context
16K
Max Output
16K
Input
$0.3
Output
$0.4
US
bf16
Context
33K
Max Output
33K
Input
$0.34
Output
$0.39
Context
131K
Max Output
131K
Input
$0.4
Output
$0.4
Context
131K
Max Output
131K
Input
$0.6
Output
$0.6
US
bf16
Context
131K
Max Output
4K
Input
$0.6
Output
$1.2
Context
131K
Max Output
131K
Input
$0.8
Output
$0.8
Context
131K
Max Output
131K
Input
$0.88
Output
$0.88
Context
131K
Max Output
131K
Input
$0.9
Output
$0.9

More models from Meta Llama

    Meta: Llama 3.1 70B Instruct – Provider Status | OpenRouter