Speed analysis
Latency measured across all benchmark runs. P50 (median) and P95 (95th percentile) give a realistic picture of response speed under normal and peak load.
Tokens per second
Throughput in tokens per second, derived from measured P50 latency. Higher is better; fluctuations track provider-side load.
—
Capabilities
Availability
Availability
No measurements yet
We haven't recorded enough API calls to show availability stats for this model. Data appears once the model starts receiving live traffic.
Tokonomix benchmark verdicts
FLUX.1 Kontext [max] adds image editing to multi-image fusion toolkit
FLUX.1 Kontext [max] has expanded its capabilities with the addition of image editing functionality, complementing its existing multi-image fusion features. This enhancement allows users to both combine multiple images and perform editing operations within the same workflow. The core multi-image fusion performance appears stable, maintaining the model's established approach to blending and compositing visual elements. The new image editing capability broadens the model's utility for creative workflows that require both image manipulation and fusion in a single pipeline. Users working on complex visual projects may find value in this consolidated approach, reducing the need to switch between separate tools for editing and fusion tasks. However, without comparative performance metrics between benchmark windows, it's difficult to assess whether the addition of editing features has impacted fusion quality or processing characteristics. The model continues to serve its primary function of multi-image fusion while now offering extended editing capabilities. Users should evaluate whether the integrated editing features meet their specific requirements compared to specialized single-purpose tools.
Quality
—
Latency p50
—
Test runs
0
FLUX.1 Kontext [max] — Multi-Image Fusion
by fal.ai
- Context window
- — tokens
- Input price
- — / 1M
- Output price
- — / 1M
- Tier
- Tier A — Frontier
- Modality
- Text
- API type
- REST · streaming
- Benchmark runs
- 187
More from fal.ai