Today's price · per 1M tokens
Input
$3.00
per 1M tokens
Output
$15.00
per 1M tokens
Blended
$6.00
blended $/1M — 3:1 weighted input:output
Cached input
$0.300
10% of input — prompt caching
Price receipt
We read Fireworks's own pricing page on and found Ember-1 listed with a price on the same card — that read is where the number above comes from. We keep the page text we read; its content hash is 8e9c5063fa.
Overview
Fireworks' own reasoning model, built on Kimi K3, that Fireworks says produces shorter reasoning traces — about 40% fewer tokens at comparable quality in its own evaluations. Served only by Fireworks. 1M-token context, text + image input. $3.00/$15.00 per 1M tokens; cached $0.30.
Capabilities
struck through = not supportedBenchmark performance
accuracy % · higher is betterSources: Fireworks launch blog (SWE-bench Verified, N=500, pass rate; scaffold not stated) (SWE-Bench Verified) · Fireworks launch blog (Terminal Bench 2.1, N=89, pass rate; harness not stated) (Terminal-Bench 2.1)
Every per-benchmark score we hold for this model is reported by its own vendor, so none is counted toward an accuracy average or any ranking.
Source: Fireworks launch blog (SWE-bench Verified, N=500, pass rate; scaffold not stated), Fireworks launch blog (Terminal Bench 2.1, N=89, pass rate; harness not stated) · updated · See full rankings →
Specifications
- Provider
- Fireworks
- Context window
- 1M tokens
- Modality
- text, image
- Parameters
- Proprietary
- Open source
- No — proprietary
- Released
- Status
- Current
- Last updated
- Tags
Availability verified: — listed on Fireworks's own page