Fireworks AI releases Ember-1 based on Kimi K3

On September 23, 2026, Fireworks AI released Ember-1, an efficient inference model based on Kimi K3. The company says the model cuts token consumption by about 40% while maintaining equivalent quality; across seven benchmarks and production traffic from two customers, K3's reasoning process can be shortened by 35–50% without any drop in accuracy. Ember-1 is available on Serverless as a Research Preview, offered alongside the base Kimi K3, with training support on enterprises' own data also opened at the same time. Follow-up reports say the model is offered only through the Fireworks serverless API, with no public weights, training code, or specific training algorithm, and no self-hosting support for now; in A/B tests against two customers' production coding workloads, output tokens per task fell from 49.3K to 29.9K, reasoning tokens dropped 71.3%, total tokens fell 39%, and task scores were essentially flat at 0.753 versus 0.751, with one customer already using it in production. The reports also say Ember-1's per-token price is the same as Kimi K3's, with the savings coming from generating fewer tokens.

AI-generated from public reports

1. Sep 23· 2 reports

   Fireworks AI releases Ember-1

   Source:Fireworks AI