Fireworks · live price
Ember-1 API pricing
Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...
Frontier (blended $5+ per 1M)Tool callingReasoningimage input
- Input
- $3
- per 1M tokens
- Output
- $15
- per 1M tokens
- Cached input
- $0.3
- per 1M tokens
- Context
- 1.0M
- 944K max output
List price from OpenRouter, which passes Fireworks's price through without markup. Refreshed hourly. Released September 24, 2026. Model id fireworks/ember-1.
What Ember-1 costs in practice
At list price, before any batch or caching discount.
1,000 chat messages
$10.50
1,000 input + 500 output tokens each
1,000 RAG questions
$31.50
8,000 input + 500 output tokens each
100 coding-agent steps
$12.00
30,000 input + 2,000 output tokens each, no caching
Ember-1 price history
No price change since we started tracking on 2026-10-01. We record prices daily; changes will show here.
Ember-1 price by host
One host serves this model through OpenRouter.
- Fireworks$3 in · $15 out · 1.0M ctx · 100.0% uptime 24h
Where to buy Fireworks credits for less
Ember-1 costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:
Ember-1 cost calculator
Enter your monthly tokens to price your own usage.
Usage at list price$300.00/ month
Cheaper alternatives to Ember-1
Other labs' models in the same price range or the one below, cheaper per token.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| OpenAI: GPT-6.2 Sol Pro | $2 | $10 |
| OpenAI: GPT-6.2 Sol | $2 | $10 |
| Qwen: Qwen4 Max | $1.42 | $4.27 |
| Google: Gemini 4 Hydrogen | $1.50 | $7.50 |
| Google: Gemini 4 Carbon | $2 | $10 |
| Google: Gemini Omni 1.2 Flash | $1.50 | $9 |