Skip to content
Runs in:USMade in:Germany
fal.ai

FLUX.1 Kontext [pro] — Multi-Image Fusion

Tokonomix Editorial Team·Reviewed by Mes Kalkan··
Section 01

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.

P50 latency (median)P95 latency64 runs
0011107-0607-22ms
Section 02

Tokens per second

Throughput in tokens per second, derived from measured P50 latency. Higher is better; fluctuations track provider-side load.

Section 03

Capabilities

source: falimage editing
Section 04

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.

Section 05

Tokonomix benchmark verdicts

2026-07-19

Image editing capability added with consistent core performance metrics

FLUX.1 Kontext [pro] has integrated image editing functionality into its multi-image fusion capabilities, marking a significant expansion of its feature set. The model maintains its established performance profile across core metrics during this transition period. With no benchmark data available from the previous window and limited current data points, comprehensive performance trends cannot be established at this time. The addition of image editing represents a strategic enhancement to the model's toolset, potentially enabling users to perform more complex visual manipulation tasks beyond basic multi-image fusion. Users adopting this model should be aware that the image editing integration is newly deployed, and the model's behavior under various editing scenarios will become clearer as more usage data accumulates. The stable foundation of the FLUX.1 architecture suggests reliability, though the practical performance of the new editing features in production environments requires further observation. Organizations considering this model for workflows involving both image fusion and editing tasks may find value in the consolidated capability set, though thorough testing is recommended given the nascent stage of the image editing integration.

Quality

Latency p50

Test runs

0

Image editing capability introduced Core performance remains stable
Last automated test
Jul 22, 2026 · 02:00 UTC · Speed benchmark
P50 latency
0 ms
P95 latency
0 ms
Errors
3 / 6 runs
Last reviewed by Tokonomix Team·July 22, 2026