Meta

Llama 3.1 8B Instruct

by Metatext->text5 endpoints
Neura Intelligence Index
3.0/ 100
Rank
#359
Confidence
low
Benchmarks
1(3% coverage)

Overview

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...

Capabilities

Text generation
Tool use / Function calling
Structured output
Prompt caching
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
131.1K tokens
Max Output
118.0K tokens
Knowledge Cutoff
2023-12-31
Tokenizer
Llama3
Uptime (24h)
9999.3%
Parameters
8000000000B
License
llama_3_1_community_licenseOpen Weights
Country
🇺🇸US
Release Date
July 23, 20242y

Supported Parameters

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmark Performance

reasoning

BenchmarkScoreSource
GPQA Diamond
30.4
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.05
Output$0.08
Cache read$0.03
Added
July 23, 2024
Last synced 9/18/2026