fireworksVision
Fireworks: Ember-1
Try in chat →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%...
Context
1M tokens
Input / 1M tokens
$3
Output / 1M tokens
$15
Benchmark
—
Uptime & performance
Loading…
Pricing
Input tokens$3 per 1M tokens
Output tokens$15 per 1M tokens
Cache read$0.30 per 1M tokens
Apps and activity
Loading…
Technical details
Model IDfireworks/ember-1
Context window1M tokens
Input modalitiestext, image
Output modalitiestext
TokenizerOther
Max output tokens943,718
Use with MegaBrain
import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://getmegabrain.com/api/gateway/v1',
apiKey: process.env.MEGABRAIN_API_KEY,
})
const response = await client.chat.completions.create({
model: 'fireworks/ember-1',
messages: [{ role: 'user', content: 'Hello!' }],
})Ready to use Fireworks: Ember-1?
Try it in the browser first, then get an API key and start making requests in minutes.