Video generation performance
Measured completion time, reliability, and cost for asynchronous video models served directly through the attested TrustedRouter gateway.
Direct providers
Actual provider paths, not model publishers. A model offered through multiple direct providers receives one row per provider. Configured routes appear before their first completed measurement.
| # | Provider | Models | Completed | p50 total | p95 total | p50 cost / output sec | Jobs |
|---|---|---|---|---|---|---|---|
| 1 | grok | 1 | 100.00% | 17.5 s | 19.8 s | $0.06 | 3 |
| 2 | ltx | 2 | 100.00% | 21.7 s | 21.9 s | $0.072 | 2 |
| 3 | kling | 2 | 100.00% | 22.3 s | 24.9 s | $0.109092 | 2 |
| 4 | alibaba | 1 | 100.00% | 39.1 s | 39.1 s | $0.12 | 1 |
| 5 | atlas-cloud | 1 | 100.00% | 163.7 s | 163.7 s | $0.168 | 1 |
| 6 | venice | 16 | 85.71% | 27.1 s | 180.0 s | $0.04 | 7 |
| 7 | runway | 1 | 33.33% | 44.1 s | 46.9 s | $0.144 | 6 |
| — | google-ai-studio | 2 | Awaiting sample | — | — | — | 0 |
| — | minimax | 1 | Awaiting sample | — | — | — | 0 |
| — | openai | 2 | Awaiting sample | — | — | — | 0 |
Video models
Operational measurements are kept separate from visual quality. A fixed public prompt suite and blind quality results will appear only after each model has enough comparable runs.
| # | Model | Provider | Inputs | Audio | Completed | p50 total | p95 total | p50 time / output sec | p50 job cost | p50 cost / output sec | Jobs |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | pixverse/c1 | venice | text | No | 100.00% | 11.4 s | 38.7 s | 3.8 s | $0.12 | $0.04 | 2 |
| 2 | x-ai/grok-imagine-video | grok | text | No | 100.00% | 17.5 s | 19.8 s | 17.5 s | $0.06 | $0.06 | 3 |
| 3 | lightricks/ltx-2.3-fast | ltx | text | Yes | 100.00% | 21.7 s | 21.9 s | 2.7 s | $0.432 | $0.072 | 2 |
| 4 | kling/v3-pro | kling | text | No | 100.00% | 22.3 s | 24.9 s | 7.4 s | $0.327276 | $0.109092 | 2 |
| 5 | lightricks/ltx-2.3-fast | venice | — | — | 100.00% | 27.1 s | 27.1 s | — | $0.42 | — | 1 |
| 6 | google/gemini-omni-flash | venice | — | — | 100.00% | 27.1 s | 27.1 s | — | $0.5775 | — | 1 |
| 7 | alibaba/wan-2.7 | alibaba | text | No | 100.00% | 39.1 s | 39.1 s | 19.6 s | $0.24 | $0.12 | 1 |
| 8 | bytedance/seedance-2.0-fast | venice | — | — | 100.00% | 104.2 s | 104.2 s | — | $0.798 | — | 1 |
| 9 | minimax/hailuo-3 | atlas-cloud | text | Yes | 100.00% | 163.7 s | 163.7 s | 32.7 s | $0.84 | $0.168 | 1 |
| 10 | minimax/hailuo-3 | venice | — | — | 50.00% | 180.0 s | 180.0 s | — | $0.8505 | — | 2 |
| 11 | runway/gen-4.5 | runway | text | No | 33.33% | 44.1 s | 46.9 s | 22.1 s | $0.288 | $0.144 | 6 |
| — | alibaba/wan-2.7 | venice | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | bytedance/seedance-2.0 | venice | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | google/veo-3.1 | venice | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | google/veo-3.1 | google-ai-studio | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | google/veo-3.1-fast | venice | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | google/veo-3.1-fast | google-ai-studio | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | kling/o3-pro | kling | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | kling/o3-pro | venice | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | kling/v3-pro | venice | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | lightricks/ltx-2.3 | ltx | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | lightricks/ltx-2.3 | venice | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | minimax/hailuo-3 | minimax | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | openai/sora-2 | openai | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | openai/sora-2 | venice | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | openai/sora-2-pro | openai | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | openai/sora-2-pro | venice | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | runway/gen-4.5 | venice | — | — | Awaiting sample | — | — | — | — | — | 0 |
| — | shengshu/vidu-q3 | venice | — | — | Awaiting sample | — | — | — | — | — | 0 |
Quality without hand waving.
The quality suite will hold prompt, duration, aspect ratio, resolution, and audio settings constant. It will report prompt adherence, motion consistency, visual artifacts, identity consistency, text rendering, and audio synchronization separately.
Blind human preference and machine-judge scores will remain separate from reliability and cost. TrustedRouter will publish the prompts and replay metadata needed to reproduce every score.