← Back to Directory

Sao10K: Llama 3 8B Lunaris

SAO10K Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1300Chatbot Arena Verified
Max Context8,192Tokens
API Cost / 1M$0.09Blended Prompt + Completion

Model Capabilities

  • Coding & Logic
  • Roleplay
  • Reasoning
  • Drafting
  • Classification
  • Agentic
  • Fictional
Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge. Created by [Sao10k](https://huggingface.co/Sao10k), this model aims to offer an improved experience over Stheno v3.2, with enhanced creativity and logical reasoning. For best results, use with Llama 3 Instruct context template, temperature 1.4, and min_p 0.1.

Granular Pricing Matrix

Input Tokens (Prompt)$0.04 / 1M
Output Tokens (Completion)$0.05 / 1M

Pricing data via OpenRouter. Sync: 3/16/2026

Evaluate Competitors

VS Engine MatchupSao10K: Llama 3 8B Lunaris vs Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)VS Engine MatchupSao10K: Llama 3 8B Lunaris vs Google: Gemini 3.1 Pro Preview Custom ToolsVS Engine MatchupSao10K: Llama 3 8B Lunaris vs OpenAI: GPT-5.2-CodexVS Engine MatchupSao10K: Llama 3 8B Lunaris vs Google: Gemini 3 Flash PreviewVS Engine MatchupSao10K: Llama 3 8B Lunaris vs OpenAI: GPT-5.2 ProVS Engine MatchupSao10K: Llama 3 8B Lunaris vs OpenAI: GPT-5.2