Nvidia

Llama 3.1 70b Instruct

Name: Llama 3.1 70b Instruct
Brand: Nvidia

Canonical ID: nvidia/meta/llama-3.1-70b-instruct

More Nvidia models More llama-3.1-70b-instruct family models

Open Llama instruction model for multilingual chat, reasoning, and coding

Reasoning: No Tool use: Yes Open weights

Overview

text

Provider: Nvidia
Family: llama-3.1-70b-instruct
Release date: 2024-07-16
Last updated: 2024-07-16
Input modalities: text
Output modalities: text

Pricing and Limits

Token pricing

Input: $0/1M
Output: $0/1M
Cached input: N/A

Context and output

Context window: 128,000
Max output tokens: 4,096
Qualified ID: nvidia/meta/llama-3.1-70b-instruct

Model Summary

Llama 3.1 70b Instruct is a model listing in the Nvidia provider catalog. It is categorized under the llama-3.1-70b-instruct family.

The model supports text modalities across input/output paths. Reported context capacity is 128,000. Pricing is listed at $0/1M input and $0/1M output.

Same Family: llama-3.1-70b-instruct

Comparable models in the same family across providers.

Browse family

Model	Provider	Context	Input	Output	Flags
Llama 3.1 70B Instruct amazon_bedrock/meta.llama3-1-70b-instruct-v1:0	Amazon Bedrock	128,000	$0.72/1M	$0.72/1M	Tools
Llama-3.1-70B-Instruct synthetic/hf:meta-llama/Llama-3.1-70B-Instruct	Synthetic	128,000	$0.9/1M	$0.9/1M	Reasoning Tools
Meta: Llama 3.1 70B Instruct openrouter/meta-llama/llama-3.1-70b-instruct	OpenRouter	131,072	$0.4/1M	$0.4/1M	Tools
Meta: Llama 3.1 70B Instruct kilo/meta-llama/llama-3.1-70b-instruct	Kilo Gateway	131,072	$0.4/1M	$0.4/1M	Tools

Llama 3.1 70b Instruct

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From Nvidia

Active Speaker Detection

bevformer

BGE M3

ByteDance-Seed/Seed-OSS-36B-Instruct

Codegemma 1.1 7b

Codegemma 7b

Codellama 70b

Codestral 22b Instruct V0.1

Same Family: llama-3.1-70b-instruct