Kling 2.6 Pro (可灵)
KUAISHOU:KLING-2.6-PROVideo DiTBusyLoad:82%SLA:99.92%排队 1.4s
Diffusion Video Transformer + 3D VAE
Base Rate
60 Credits / run
24h +24.15%
Kuaishou state-of-the-art video model with cinematic camera paths, high-motion human dynamics, and physical consistency.
24h Total Calls
1.82Mcalls
+24.15% vs yesterday
Total Generations
1.25Mvids
+22.4% · 1080P Ratio 82%
Avg Latency (P50)
8.7s
5s Video 8.6s · 60 FPS
Availability SLA
99.92%
Failover <110ms
Model Telemetry & Volume Chart
KUAISHOU:KLING-2.6-PROInvocations
79,814次+14.42%
Live Telemetry
Operational Performance
Production-grade Latency & Concurrency
P50 TTFT340 ms
P99 Latency14200 ms
Throughput TPS
Peak Concurrency890 req
Packet Loss Rate0.002%
Cost & Billing Matrix
Credits and Token Breakdown
Base Task Cost60 Credits
Input Cost / 1k Tokens¥0.020
Output Cost / 1k Tokens¥0.060
4K Upscale Multiplier2.0x
VIP Discount至高 30% 优惠
Technical Specifications
Parameters, Context & Resolutions
ArchitectureDiffusion Video Transformer + 3D VAE
Parameters18 Billion
Context Window2,048 tokens
Max Resolution1080P Full HD @ 60 FPS
Max Duration5s / 10s
Global Edge Gateways
Live Region Latency & Load Balancing
East China (Shanghai)
16ms
South China (Guangzhou)
20ms
Hong Kong Gateway
35ms
Asia Pacific (Singapore)
58ms
US West (Silicon Valley)
148ms
EU Central (Frankfurt)
172ms
Comparable Models in Same Domain
Models with similar creative modalities
Hailuo 2.3 (海螺视频)
MINIMAX:HAILUO-2.3
MiniMax cinematic text/image-to-video flagship renowned for subtle facial expressions and complex physical world dynamics.
Rate55 Credits / run
Google Veo 3
GOOGLE:VEO-3-GEN
DeepMind native audio-visual video model mastering cinematic framing, focus pulling, and fluid temporal coherence.
Rate75 Credits / run