Models / Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
allais/llama-3-1-8b
Small, fast, cheap — ideal for classification and high-volume tasks.
textdensefastcheap
Parameters
8B dense
Context window
131K tokens
Serverless $/1M
$0.3077 in · $0.3077 out
reference $0.2 · $0.2
Dedicated
1× A100-80G
sourced live, undercuts $2.9/hr
Use via API
curl http://localhost:3000/api/v1/chat/completions \
-H "Authorization: Bearer $ALLAIS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "allais/llama-3-1-8b", "messages": [{"role": "user", "content": "Hello"}]}'