modelgrep
S

Sao10K models

4models tracked · ranked by intelligence, speed & price

Quick answer · Updated June 2026

its fastest is Llama 3 8B Lunaris at 79 tokens/sec, and its cheapest is Llama 3 8B Lunaris at $0.040 per million input tokens. All 4 Sao10K models are compared below by intelligence, speed, latency, context and price.

Smartest
Fastest
79 t/s
sao10k/l3-lunaris-8b
Cheapest
$0.040/M
sao10k/l3-lunaris-8b
ModelIntelIn $/MContext
l3.1-70b-hanami-x1
$3.0016K
l3.3-euryale-70b
JSON
$0.650131K
l3.1-euryale-70b
ToolsJSON
$0.850131K
l3-lunaris-8b
JSON
$0.0408K