You only pay for what you use
no infrastructure to manage
no tuning required.
Flux
Text to Image
Image to Image
Inpanting
Fast Version
Model | Example Resolutions | Steps | Cost per |
|---|---|---|---|
Flux Schnell | 512x512, 512x768, 640x640 | Up to 2 | $0.0010 |
Flux Schnell | 512x512, 512x768, 640x640 | Up to 4 | $0.0015 |
Flux Schnell | 1024x1024, 1024x768 | Up to 2 | $0.0020 |
Flux Schnell | 1024x1024, 1024x768 | Up to 4 | $0.0025 |
Flux Dev | 1024x1024, 1024x768 | Up to 28 | $0.0200 |
Flux Dev | 1024x1024, 1024x768 | Up to 50 | $0.0240 |
Flux Pro 1.1 | 1024x1024, 1024x768 | N/A | $0.0400 |
Flux Pro 1.1 Ultra | 1024x1024, 1024x768 | N/A | $0.0600 |
Flux Kontext
Text to Image
Instruct to Image
Model | Example Resolutions | Cost per Generation |
|---|---|---|
Dev | 1024x1024, 1568x672, 672x1568 | $0.025 |
Pro | 1024x1024, 1568x672, 672x1568 | $0.040 |
Max | 512x512, 512x768, 640x640 | $0.080 |
Google Veo
Text to Video
Image to Video
Model | Example Resolutions | Length | Cost per Generation |
|---|---|---|---|
Veo 3 Fast | 720P | 8 Seconds | $0.80 |
Veo 3 Fast (with audio) | 720P | 8 Seconds | $1.20 |
Veo 3 | 720P | 8 Seconds | $1.60 |
Veo 3 (with audio) | 720P | 8 Seconds | $3.20 |
Google Nano Banana 🍌 (Gemini 2.5 Flash Image)
Text to Image
Instruct to Image
Model | Example Resolutions | Cost per Generation |
|---|---|---|
Gemini 2.5 Flash | 1024x1024, 1568x672, 672x1568 | $0.039 |
Kling
Text to Video
Image to Video
Model | Mode | Example Resolutions | Length | Cost per Generation |
|---|---|---|---|---|
Kling 1.6 | Standard | 720P | 5 Seconds | $0.25 |
Kling 1.6 | Standard | 720P | 10 Seconds | $0.50 |
Kling 1.6 | Pro | 1080P | 5 Seconds | $0.55 |
Kling 1.6 | Pro | 1080P | 10 Seconds | $1.10 |
Kling 2.1 | Standard | 720P | 5 Seconds | $0.28 |
Kling 2.1 | Standard | 720P | 10 Seconds | $0.56 |
Kling 2.1 | Master | 1080P | 5 Seconds | $1.40 |
Kling 2.1 | Master | 1080P | 10 Seconds | $2.80 |
ByteDance SeeDance
Text to Video
Image to Video
Model | Example Resolutions | Length | Cost per Generation |
|---|---|---|---|
SeeDance Lite | 480P | 5 Seconds | $0.09 |
SeeDance Lite | 480P | 10 Seconds | $0.18 |
SeeDance Lite | 720P | 5 Seconds | $0.20 |
SeeDance Lite | 720P | 10 Seconds | $0.40 |
SeeDance Lite | 1080P | 5 Seconds | $0.44 |
SeeDance Lite | 1080P | 10 Seconds | $0.88 |
SeeDance Pro | 480P | 5 Seconds | $0.12 |
SeeDance Pro | 480P | 10 Seconds | $0.24 |
SeeDance Pro | 1080P | 5 Seconds | $0.61 |
SeeDance Pro | 1080P | 10 Seconds | $1.22 |
ByteDance SeedEdit
Text to Image
Instruct to Image
Model | Example Resolutions | Cost per Generation |
|---|---|---|
SeedEdit | 1024x1024, 1568x672, 672x1568 | $0.03 |
Alibaba Qwen Image Edit
Text to Image
Instruct to Image
Model | Example Resolutions | Cost per Generation |
|---|---|---|
Qwen Image Edit | 1024x1024, 1920x1080, 1080x1920 | $0.01 |
Recraft
Text to Image
Model | Example Resolutions | Cost per Generation |
|---|---|---|
V3 | 1024x1024, 2048x1024 | $0.04 |
V3 Vectors | 1024x1024, 2048x1024 | $0.08 |
Stable Diffusion
Text to Image
Image to Image
Inpanting
Model | Example Resolutions | Steps | Cost per |
|---|---|---|---|
SDXL Large | 1024x1024, 768x1024, 1024x768 | Up to 25 | $0.0020 |
SDXL Large | 1024x1024, 768x1024, 1024x768 | Up to 50 | $0.0025 |
SD 1.5 Small | 512x512, 512x768, 768x512 | Up to 25 | $0.0025 |
SD 1.5 Small | 512x512, 512x768, 768x512 | Up to 50 | $0.0030 |
SD 1.5 Medium | 768x768, 1024x512, 512x1024 | Up to 25 | $0.0050 |
SD 1.5 Medium | 768x768, 1024x512, 512x1024 | Up to 50 | $0.0075 |
SD 1.5 Large | 1024x1024, 768x1024, 1024x768 | Up to 25 | $0.0080 |
SD 1.5 Large | 1024x1024, 768x1024, 1024x768 | Up to 50 | $0.0100 |
Utilities
Background Removal
Upscaling
Model | Models | Cost per Generation |
|---|---|---|
Background Removal | BiRefNet 2 | $0.0025 |
NSFW Image Detection | VIT | $0.0002 |
Upscale (2x) | R-ESRGAN | $0.0010 |
Upscale (4x) | R-ESRGAN | $0.0020 |
Upscale (8x) | R-ESRGAN | $0.0030 |
Face Restore | GFPGAN | $0.0008 |