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.
Context window
How much it can remember.
1M tokens
≈ 786,432 English words
4K
32K
128K
1M
Capabilities
What it can do.
·
Vision input
·
Audio input
·
Video input
·
Function calling
·
Tool use
·
JSON mode
✓
Streaming
·
Fine-tuning