# Fireworks AI releases Ember-1, a post-trained Kimi K3 model

Digest AI · Generative AI & Models · published 2026-09-28T07:22:33Z

Canonical: https://digestai.news/story/fireworks-ai-releases-ember-1-a-post-trained-kimi-k3-model

## Summary

Fireworks AI has released Ember-1, a specialized model derived from Moonshot AI’s open-weight Kimi K3. The new model is post-trained to produce shorter reasoning traces while maintaining task accuracy, addressing the high token costs associated with reasoning models in multi-turn agentic workloads. Fireworks reports that Ember-1 delivers Kimi K3’s quality with approximately 40% fewer tokens. Unlike simply lowering the reasoning effort setting, which degrades quality, Ember-1 is trained to cut redundant reasoning loops while preserving useful self-reflection.

The model is currently available only as a Research Preview through the Fireworks serverless API. Fireworks has not released the weights, training code, or exact algorithms, meaning self-hosting is not possible. Pricing remains identical to Kimi K3 at $3.00 per million input tokens and $15.00 per million output tokens, with savings coming solely from reduced token generation.

In production A/B tests with two customers, Ember-1 reduced output tokens per task from 49.3K to 29.9K while keeping the task score nearly unchanged (0.753 vs 0.751). Fireworks states that Ember-1 leads Kimi K3 Max on Terminal Bench 2.1 and DeepSWE 1.1, though it trails slightly on SWE-bench Verified. The company claims these results were achieved using its own data and no customer data, with all training conducted on Fireworks Serverless Training.

## Key points

- Ember-1 is a post-trained Kimi K3 model that uses about 40% fewer tokens while maintaining accuracy.
- The model is available only via Fireworks serverless API as a Research Preview; weights are not released.
- Production A/B tests showed output tokens per task fell from 49.3K to 29.9K with comparable quality scores.

## Why it matters

Ember-1 offers a cost-effective alternative for developers using reasoning models, significantly reducing inference costs for agentic workloads without sacrificing performance, though it remains locked behind a proprietary API.

## Sources

1. [Fireworks AI Releases Ember-1: A Post-Trained Kimi K3 That Uses About 40% Fewer Tokens](https://marktechpost.com/2026/09/28/fireworks-ai-releases-ember-1-a-post-trained-kimi-k3-that-uses-about-40-fewer-tokens) (MarkTechPost, 2026-09-28)

## Cite

Digest AI, "Fireworks AI releases Ember-1, a post-trained Kimi K3 model", 28 September 2026, https://digestai.news/story/fireworks-ai-releases-ember-1-a-post-trained-kimi-k3-model

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/fireworks-ai-releases-ember-1-a-post-trained-kimi-k3-model.json