Llama 3.3 70B Instruct
by Metatext->text12 endpoints
Neura Intelligence Index
20.8/ 100
Rank
#251—
Confidence
lowBenchmarks
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
Modalities
Input
Text
Output
Text
Technical Specifications
Context Window
131.1K tokens
Max Output
128K tokens
Knowledge Cutoff
2023-12-31
Tokenizer
Llama3
Uptime (24h)
9987.4%
Parameters
70000000000B
License
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Performance Over Time
Pricing
Per 1M tokens
Input$0.13
Output$0.40