Stay connected with us on X, Discord, and LinkedIn to stay up to date with future analysis
Loading...

Image Lab

Generate and compare your own images across top models like Nano Banana and GPT Image.

Try Image Lab

Compare API Providers

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

API Generation Time

Generation time: Seconds to generate 1 image, Lower is better

Median time the provider takes to generate an image over the past 14 days of measurements. This includes downloading the image from the provider where a URL is provided rather than an image response.

API Price

Price: USD per 1000 image generations, Lower is better

Price per 1k images generated by the model. For detail on how we calculate price per image for providers price based on inference time or steps, see our methodology page.

Detailed Analysis

Quality vs. API Price

ELO score in Artificial Analysis Image Arena (relative metric of image generation quality), Price: USD per 1000 image generations
Most attractive quadrant
fal.ai
Replicate
Runware
Vivago AI
WaveSpeed

Relative ELO score of the models as determined by millions of responses from users in Artificial Analysis' Image Arena.

Price per 1k images generated by the model. For detail on how we calculate price per image for providers price based on inference time or steps, see our methodology page.

Quality vs. API Generation Time

ELO score in Artificial Analysis Image Arena (relative metric of image generation quality), Generation time: Seconds to generate 1 image
Most attractive quadrant
fal.ai
Replicate
Runware
Vivago AI
WaveSpeed

Relative ELO score of the models as determined by millions of responses from users in Artificial Analysis' Image Arena.

Median time the provider takes to generate an image over the past 14 days of measurements. This includes downloading the image from the provider where a URL is provided rather than an image response.

API Generation Time vs. API Price

Generation time: Seconds to generate 1 image, Price: USD per 1000 image generations
Most attractive quadrant
fal.ai
Replicate
Runware
Vivago AI
WaveSpeed

Median time the provider takes to generate an image over the past 14 days of measurements. This includes downloading the image from the provider where a URL is provided rather than an image response.

Price per 1k images generated by the model. For detail on how we calculate price per image for providers price based on inference time or steps, see our methodology page.

Speed Analysis

API Generation Time, Variance

Generation time: Seconds to generate 1 image, Results by percentile, Lower is better
Median; other points represent Min, 25th, 75th percentiles and Max respectively

Median time the provider takes to generate an image over the past 14 days of measurements. This includes downloading the image from the provider where a URL is provided rather than an image response.

Picture of the author

API Generation Time, Over Time

Generation time: Seconds to generate 1 image, Lower is better
HiDream-I1-Dev, fal.ai
HiDream-I1-Dev, Replicate
HiDream-I1-Dev, Runware
HiDream-I1-Dev, Vivago AI
HiDream-I1-Dev, WaveSpeed

Median time the provider takes to generate an image over the past 14 days of measurements. This includes downloading the image from the provider where a URL is provided rather than an image response.

Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.