Back to Models
llm-jp/llm-jp-3-1-8x13b-instruct4
LLM-jp 3.1 8x13B Instruct4
A Mixture-of-Experts instruction-tuned Japanese language model developed by the National Institute of Informatics (NII). With 73B total parameters (22B active), it exceeds GPT-4-0613 performance on Japanese instruction-following benchmarks.
4,096 tokens
Input: ¥16/M
Output: ¥79/M
Specifications
Modalities
Input
text
Output
text
Code Examples
curl https://api.fastmetal.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "llm-jp-3.1-8x13b-instruct4",
"messages": [{"role": "user", "content": "Hello!"}]
}'