modelbenchmark.io

Fireworks: Ember-1

ember-1

Compare

Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...

Specification

most-agreed values

Context
1M
Max output
944K
Released
2026-09-24
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$3.00
Output
$15.00
Cache read
$0.30

Available from 5 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
fireworks_ai$3.00$15.00$0.30—1M——
fireworks-ai · accounts$3.00$15.00$0.30—1M131K—
kilo$3.00$15.00$0.30—1M944K—
openrouter$3.00$15.00$0.30—1M944K—
vercel$3.00$15.00$0.30—1M1M—