Skip to content
LLMs
Fireworks logo

Fireworks: Ember-1

by Fireworks

Fireworks: Ember-1 is a large language model from Fireworks. It costs $3.00 per million input tokens and $15.00 per million output tokens. Its context window is 1.0M tokens.

ReasoningTool callingStructured outputPrompt cachingimage input
Input / 1M tokens
$3.00
Output / 1M tokens
$15.00
Cached input / 1M
$0.300

On repeated prefixes

Context window
1.0M

tokens

Who serves it cheapest

1 hosts serve Ember-1. Same weights, same API - the price difference is pure margin and routing.

Providers serving Fireworks: Ember-1, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
FireworksCheapest$3.00$15.001.0M-100.0%

About Ember-1

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%...

Specifications

Fireworks: Ember-1 specifications
Model IDfireworks/ember-1
ProviderFireworks
Context window1.0M tokens
Max output944K tokens
Input modalitiestext, image
Output modalitiestext
Knowledge cutoff-
Open weightsNo
ReleasedSeptember 24, 2026

Cheaper alternatives

Models that cost less than Ember-1 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Fireworks: Ember-1 cost?

$3.00 per million input tokens and $15.00 per million output tokens. Cached input reads cost $0.300 per million tokens.

What is the context window of Fireworks: Ember-1?

1.0M tokens, with up to 944K tokens of output per request.