FP8 quantized variant of Black Forest Labs' FLUX.1 [schnell] model, offering ~2x faster inference with reduced precision while maintaining high-quality image generation in 4 steps
Prices shown are in USD
Full pricing detailsProvider Performance
Fastest generation through fireworks at 1,580ms median latency with 95.7% success rate.
Aggregated from real API requests over the last 30 days.
Generation Time
fireworks
1,580ms
p95: 2,992ms
Success Rate
fireworks
95.7%
331 / 346 requests
Time to First Byte
fireworks
800ms
p95: 1,257ms
Provider Rankings
| # | Provider | p50 Gen Time | p95 Gen Time | Success Rate | TTFB (p50) |
|---|---|---|---|---|---|
| 1 | fireworks | 1,580ms | 2,992ms | 95.7% | 800ms |
Data updated every 15 minutes. Based on all API requests through Lumenfall over the last 30 days.
Providers & Pricing (1)
FLUX.1 [schnell] FP8 is free to use through Fireworks AI.
Fireworks AI
fireworks/flux.1-schnell-fp8
Provider Model ID:
accounts/fireworks/models/flux-1-schnell-fp8/text_to_image
Output
Image
Free
per image
Pricing Notes (4)
- • Free to try
- • Normally priced at $0.00035 per inference step
- • FLUX.1 [schnell] uses 4 steps by default, making the effective per-image cost $0.0014
- • FP8 variant uses reduced precision for ~2x faster inference