Meta

Llama 3.3 70B Instruct

by Metatext->text11 endpoints
Neura Intelligence Index
19.2/ 100
Rank
#293
Confidence
low
Benchmarks
1(3% coverage)

Overview

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Capabilities

Text generation
Tool use / Function calling
Structured output
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
16.4K tokens
Knowledge Cutoff
2023-12-31
Tokenizer
Llama3
Uptime (24h)
9991.9%
Parameters
70000000000B
License
llama_3_3_community_license_agreementOpen Weights
Country
🇺🇸US
Release Date
December 6, 20241y

Supported Parameters

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmark Performance

reasoning

BenchmarkScoreSource
GPQA Diamond
50.5
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.10
Output$0.32
Added
December 6, 2024
Last synced 9/20/2026