# Fireworks launches Rune, a 26B decision model for serverless use

> Original title: @runedotgl is live on Fireworks serverless.

- Source: Fireworks
- Published: 2026-10-29T23:05:53.000Z
- Bad Influence: https://badinfluence.news/items/c08z2w1cbwtgek93x7hcuekyv
- Original: https://x.com/FireworksAI_HQ/status/2115943233281044786

## Summary

Fireworks says its Rune model, a 26B-parameter System One decision model with 4B active per token, is live on serverless. It reads a document once and answers up to 256 multiple-choice, true/false, or graded questions, each with a calibrated probability. Median latency is under 150ms server-side, with a 262K text context and input priced at $0.042 per 1M tokens, $0.008 cached, and $0 for output.

## Post

@runedotgl is live on Fireworks serverless.

It's a System One decision model: 26B parameters of pretrained knowledge, only 4B active per token. It doesn't reason or generate text. It reads a document once and answers up to 256 questions (multiple choice, true/false, graded scale) in a single pass, each with a calibrated probability.

→ Median latency under 150ms, measured server-side
→ 262K context, text only
→ $0.042/1M input, $0.008 cached, $0 output
→ Serverless or on-demand deployments

Try it out → http://fireworks.ai/models/fireworks/rune

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHV1VbZ9bwAACfWY.jpg&mode=thumb&exp=1793577600&sig=1f5b74583c13c089)