the model

meta/llama-3.1-70b-instruct

Served by NVIDIA. 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: "nvidia/llama-70b"
      prompt: "…"

The seats · 1

nvidia/llama-70b128k context · 4k out
NVIDIA · the provider room

The price

nvidia$0 in · $0 out · open weights
per million tokens · 128k window

{"id":"meta/llama-3.1-70b-instruct","served_by":[{"provider":"nvidia","provider_name":"NVIDIA","alias":"llama-70b","context_window_tokens":128000,"max_output_tokens":4096}],"pricing":[{"provider":"nvidia","input_per_million":0,"output_per_million":0,"cache_read_per_million":null,"cache_write_per_million":null,"context_window_tokens":128000,"max_output_tokens":4096,"open_weights":true}],"slug":"meta-llama-3-1-70b-instruct","energy":[]}