Together Fireworks

Use when calling open-weight LLMs on Together AI or Fireworks AI's OpenAI-compatible endpoints — `base_url` plus namespaced model id, the cheapest model that clears the bar, per-1M-token cost math, serverless vs batch vs dedicated. NOT renting GPUs to self-host weights (that is `runpod`), NOT running a model locally for free (that is `ollama`).

ericrisco Updated 610 repo stars
rsc-harness: you build the product, rsc-harness builds your agent's harness, following strict best practices instead of improvising one.

File contents

ericrisco/rsc-harness commit a550b67cb5

Frequently asked questions

npx get-skill add ericrisco/together-fireworks