Llama 3.1 70B Hanami x1

Name: Llama 3.1 70B Hanami x1
Brand: sao10k

sao10k

An experiment over Euryale v2.2.

Example Use Cases

Experimental roleplay variant

Euryale-derived creative writing

Llama 3.1 roleplay experiment

Context Window

16,000 tokens

Max Output

16,000 tokens

Cache Miss Cost

$3 per 1M tokens

Non-Reasoning Cost

$3 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

Untested