This website is not yet fully optimised for mobile viewing. Some features may not display or function as intended.

Llama 3.1 70B Instruct

Overview

No description provided. Want to help? Contribute on GitHub or click here!

Quick Links

Suggest Edits

Key Metrics

Max Input

32.768K

Tokens

Max Output

32.768K

Tokens

Input Price

Per 1M Tokens

Output Price

Per 1M Tokens

Throughput

tok/s

Latency

Model Information

Release Details

Released

23 Jul 2024

Knowledge Cutoff

License

Model Architecture

Parameters

Training Data

Context Window

Input Context Length

32,768 tokens

Output Context Length

32,768 tokens

Key Features

Web Access

Unknown

Real-time access to current web information

Multimodal

Ability to process multiple data types (text, images, etc.)

Reasoning

Unknown

Advanced logical and deductive reasoning capabilities

Fine-Tunable

Unknown

Can be customized for specific use cases

Model Release & Updates

23 Jul 2024

Model Released

Model first made available to the public

Benchmarks & Performance Comparison

GPQA

41.70%

LisanBench

AidanBench

Aider-Polyglot

LiveBench

AIME 2024

ARC-AGI-1

ARC-AGI-2

AIME 2025

Humanity's Last Exam