Compare API Providers

Select a model to compare providers across latency, generation time, and price

For further details, see our methodology page.

API Generation Time

Generation time: seconds to generate a 1080p, 5s, 24fps video. When this configuration is not available for the model, the closest settings are used · Lower is better

Median time the provider takes to generate a video over the past 14 days of measurements. This is measured end-to-end, including downloading the completed video from the provider.

API Price

Price: USD per minute of video generation for a 1080p, 5s, 24fps video. When this configuration is not available for the model, the closest settings are used · Lower is better

Price per minute of video generated by the model, based on each provider's published per-minute rate. For further detail, see our methodology page.

Detailed Analysis

Quality vs. API Price

Elo score in Artificial Analysis Video Arena (relative metric of video generation quality) · Price: USD per minute of video generation for a 1080p, 5s, 24fps video. When this configuration is not available for the model, the closest settings are used
Most attractive quadrant
fal.ai

Relative Elo score of the models as determined by responses from users in Artificial Analysis' Video Arena. Some models may not be shown due to not yet having enough votes. For further details, see our methodology page.

Price per minute of video generated by the model, based on each provider's published per-minute rate. For further detail, see our methodology page.

Quality vs. API Generation Time

Elo score in Artificial Analysis Video Arena (relative metric of video generation quality) · Generation time: seconds to generate a 1080p, 5s, 24fps video. When this configuration is not available for the model, the closest settings are used
Most attractive quadrant
fal.ai

Relative Elo score of the models as determined by responses from users in Artificial Analysis' Video Arena. Some models may not be shown due to not yet having enough votes. For further details, see our methodology page.

Median time the provider takes to generate a video over the past 14 days of measurements. This is measured end-to-end, including downloading the completed video from the provider.

API Generation Time vs. API Price

Generation time: seconds to generate a 1080p, 5s, 24fps video. When this configuration is not available for the model, the closest settings are used · Price: USD per minute of video generation for a 1080p, 5s, 24fps video. When this configuration is not available for the model, the closest settings are used
Most attractive quadrant
fal.ai

Median time the provider takes to generate a video over the past 14 days of measurements. This is measured end-to-end, including downloading the completed video from the provider.

Price per minute of video generated by the model, based on each provider's published per-minute rate. For further detail, see our methodology page.

Speed Analysis

API Generation Time, Variance

Generation time: seconds to generate a 1080p, 5s, 24fps video. When this configuration is not available for the model, the closest settings are used · Results by percentile · Lower is better

Median time the provider takes to generate a video over the past 14 days of measurements. This is measured end-to-end, including downloading the completed video from the provider.

Picture of the author

API Generation Time, Over Time

Generation time: seconds to generate a 1080p, 5s, 24fps video. When this configuration is not available for the model, the closest settings are used · Lower is better
Mar 22Jun 14

Median time the provider takes to generate a video over the past 14 days of measurements. This is measured end-to-end, including downloading the completed video from the provider.

Each point is the median of a 14-day window of measurements, based on 1 measurement each day at different times.