the model

llama-3.1-8b-instant

Served by Groq. Point a task at it and the audit prices the ceiling before a token is spent.

Vendored from the released binary · supernovae-st/nika@5d61b7e13f1f (v0.107.0) · digest-verified, re-derived at build, gated in CI

Point a task at it

tasks:
  ask:
    infer:
      model: "groq/llama-8b"
      prompt: "…"

The seats · 1

groq/llama-8b128k context · 8k out
Groq · the provider room

The price

groq$0.05 in · $0.08 out · open weights
per million tokens · 131k window

{"id":"llama-3.1-8b-instant","served_by":[{"provider":"groq","provider_name":"Groq","alias":"llama-8b","context_window_tokens":128000,"max_output_tokens":8192}],"pricing":[{"provider":"groq","input_per_million":0.05,"output_per_million":0.08,"cache_read_per_million":null,"cache_write_per_million":null,"context_window_tokens":131072,"max_output_tokens":131072,"open_weights":true}],"slug":"llama-3-1-8b-instant","energy":[]}