by fireworks

Ember-1.

multimodal open weights 1M ctx

Ember-1 is a specialized model from Fireworks. Built on Kimi K3, it produces shorter reasoning traces, using approximately 40% fewer tokens while maintaining comparable quality across our evaluations

Where to use it

Cheapest hosted endpoints.

Provider	Access	$/M in	$/M out
Fireworks AI	hosted inference	—	—	Launch ↗

FAQ

Frequently asked.

How do I run Ember-1?

Ember-1 is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.

Where can I access Ember-1?

Ember-1 is available via Fireworks AI. Each access option lists its own pricing (per million tokens or hourly hosting).

How much does it cost to run Ember-1?

Self-hosting cost depends on the GPU you rent and the throughput you need. See the Run It Yourself tab for GPU configurations and hourly cost estimates.

Is Ember-1 open-source or proprietary?

Ember-1 is open-weight under the license. You can download and self-host it.