Fireworks: Ember-1 Rank
Ember-1 has an overall score of 69 out of 100, tied for rank 106 of 291. The published scores are price 37, context 71, and recency 98. The overall score is their average. parameters and freshness are not published and are left out of the average.
Data sourced from OpenRouter API and manual data collection | Last updated: Nov 3, 2026, 8:01 AM UTC
Component scores are ranked in
tied for rank 106 of 291
Component scores
| Score | Result | Published value | Source |
|---|---|---|---|
| Freshness | — | — | AI Knowledge Cutoff |
| Recency | 98 | AI Release Date | |
| Context | 71 | 1.05M tokens, output 944K | AI Context Window |
| Parameters | — | — | AI Parameter Count |
| Price | 37 | $6 / 1M blended, $3 / 1M input, $15 / 1M output | AI Token Price |
105 listed models have a higher overall score. Among Fireworks models, it ranks 1 of 1.
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%...
Higher overall scores
🤖 Generate website with AI 👆
Join the beta waitlist and get 50% off your first 3 months.
Frequently asked questions
What is the Ember-1 rank?
Ember-1 has an overall score of 69 out of 100, tied for rank 106 of 291. The published scores are price 37, context 71, and recency 98. The overall score is their average. parameters and freshness are not published and are left out of the average.
Where does Ember-1 rank?
Ember-1 is tied for rank 106 of 291. 105 listed models have a higher overall score. Among Fireworks models, it ranks 1 of 1.
What scores make up Ember-1?
Ember-1 scores price 37 (AI Token Price), context 71 (AI Context Window), and recency 98 (AI Release Date). The overall score of 69 is the average of those 3.