the model

meta-llama/Llama-3.1-8B-Instruct-Turbo

Served by Together AI. 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: "together/cheap"
      prompt: "…"

The seats · 1

together/cheap128k context · 4k out
Together AI

The price

No exact-match row at this pin · the engine resolves pattern rules at run time and nika audit prints the real ceiling. A local seat is unpriced, never free.

{"id":"meta-llama/Llama-3.1-8B-Instruct-Turbo","served_by":[{"provider":"together","provider_name":"Together AI","alias":"cheap","context_window_tokens":128000,"max_output_tokens":4096}],"slug":"meta-llama-llama-3-1-8b-instruct-turbo","pricing":[],"energy":[]}