Image Lab
Generate and compare your own images across top models like Nano Banana and GPT Image.
Playground Quality, Generation Time & Price Analysis
Playground AIAnalysis of Playground models and comparison to other image models across key metrics including quality, generation time, and price.
For further details, see our methodology page.
Artificial Analysis Image Arena Quality ELO
Relative ELO score of the models as determined by millions of responses from users in Artificial Analysis' Image Arena.
API Generation Time
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 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
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
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
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
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, Over Time
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.
Image models & providers compared
Amazon Titan G1 v2 (Standard), Bagel, Bria 3.2, DALLE 2, DALLE 3 HD, DALLE 3, Dreamina 3.1, Eigen Image, FLUX.1 Kontext [max], FLUX.1 Kontext [pro], FLUX.1 Krea [dev], FLUX.1 [dev], FLUX.1 [pro], FLUX.1 [schnell], FLUX1.1 [pro], FLUX.2 [dev] Flash, FLUX.2 [dev] Turbo, FLUX.2 [dev], FLUX.2 [flex], FLUX.2 [max], FLUX.2 [pro], FLUX1.1 [pro] Ultra, GLM-Image, GPT Image 1 (high), GPT Image 1.5 (high), HiDream-I1-Dev, HiDream-I1-Fast, HunyuanImage 3.0 Instruct (Fal), Ideogram v2a Turbo, Ideogram v2a, Ideogram 3.0, Ideogram v2 Turbo, Ideogram v2, Image-01, Imagen 3 (v002), Imagen 4 Fast, Imagen 4 Standard, Imagen 4 Ultra, Janus Pro, LongCat Image, Lucid Origin Fast, Lucid Origin Ultra, Luma Photon Flash, Luma Photon, Nano Banana Pro (Gemini 3 Pro Image), Phoenix 0.9 Ultra, Playground v2.5, Playground v3 (beta), Qwen Image Plus 2601, Qwen Image, Recraft 20B, Recraft V3, Recraft V4 Pro, Recraft V4, Stable Diffusion XL 1.0, SDXL Lightning, Seedream 3.0, Seedream 4.0, Seedream 4.5, Seedream 5.0 Lite, Stable Diffusion 1.5, Stable Diffusion 1.6, Stable Diffusion 3 Medium, Stable Diffusion 3.5 Large Turbo, Stable Diffusion 3.5 Large, Stable Diffusion 3.5 Medium, Vidu Q2, Z-Image Base, Z-Image Turbo, grok-imagine-image, grok-imagine-image-pro.