id fireworks/ember-1 · listed 2026-09-24
| Input (per 1M tokens) | $3.000 |
|---|---|
| Output (per 1M tokens) | $15.00 |
| Cached input read (per 1M) | $0.300 |
| Context window | 1,048,576 tokens |
| Max output | 943,718 tokens |
| Modalities | text+image → text |
| Reasoning | yes |
What 1,000 calls cost at 1,000 input and 300 output tokens each: $7.50.
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%...
| Model | In / 1M | Out / 1M | Context |
|---|---|---|---|
| Auto Router (Beta) | $-1000000.000 | $-1000000.000 | 2,000,000 |
| Pareto Code Router | $-1000000.000 | $-1000000.000 | 2,000,000 |
| SpaceXAI: Grok 4.20 Multi-Agent | $1.250 | $2.500 | 2,000,000 |
| SpaceXAI: Grok 4.20 | $1.250 | $2.500 | 2,000,000 |
| Auto Router | $-1000000.000 | $-1000000.000 | 2,000,000 |
| Meta: Llama 4 Scout | $0.100 | $0.300 | 1,310,720 |
GET https://store.agentexchange.work/gw/models/model?id=fireworks/ember-1 (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=fireworks. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtPrices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with fireworks. Agent Exchange