Explore models
103 image and video models. Try them in the playground, then build with one API key. Every model priced in credits.
103 models
Bria RMBG 2.0
Create images with Bria RMBG 2.0 using the Made API.
2 credits / image
Bria Video Background Removal 3.0
Create video with Bria Video Background Removal 3.0 using the Made API.
Priced by input
CodeFormer
Create images with CodeFormer using the Made API.
Priced by input
Creatify Aurora
A photo speaks your voice track, in 480p or 720p.
Priced by input
DDColor
Create images with DDColor using the Made API.
Priced by input
FLUX 1.1 Pro
Flux 1.1 Pro is a flexible image-generation model in Made for polished concepts, product visuals, and photorealistic scenes from descriptive prompts.
4 credits / image
FLUX.2 Klein
FLUX.2 Klein is the open-weight 4B tier of Black Forest Labs’ FLUX.2 family, generating images in under a second at 1 credit each — the cheapest way in Made to explore ideas in volume before a flagship pass.
1 credit / image
FLUX 2 Pro
Flux 2 Pro is Black Forest Labs’ current flagship image model, generating high-fidelity images from text and editing existing ones with reference images — the successor to the Flux 1.x line Made has carried from the start.
3 credits / image
FLUX.2 [pro] Outpaint
Create images with FLUX.2 [pro] Outpaint using the Made API.
Priced by input
FLUX 3
FLUX 3 is Black Forest Labs’ first video model, generating 5 to 20 second clips with natively synchronized audio from a text prompt or a start image, in seven aspect ratios up to 2:1.
17 credits / second
FLUX Kontext Pro
Create images with FLUX Kontext Pro using the Made API.
4 credits / image
FLUX Kontext Max
Flux Kontext Max is the higher-quality Kontext option for changing a selected part of a source image while preserving the subject, composition, and surrounding details.
8 credits / image
FLUX Kontext Object Removal
Create images with FLUX Kontext Object Removal using the Made API.
4 credits / image
FLUX Kontext Pro
Flux Kontext Pro is the lower-cost Kontext workflow for targeted product, portrait, and interior edits where quick iteration matters more than choosing the premium Max tier.
4 credits / image
FLUX Kontext Text Removal
Create images with FLUX Kontext Text Removal using the Made API.
4 credits / image
Gemini Omni Flash
Gemini Omni Flash is Google’s multimodal Gemini Omni video model, generating 3 to 10 second clips at 24 FPS from a text prompt or a start image in landscape or portrait.
10 credits / second
Gemini Omni Flash 1.1
Gemini Omni Flash 1.1 is the current version of Google’s fast multimodal video model, generating 3 to 10 second clips from text or a start image with sharper motion and stronger prompt adherence than v1.
from 3 credits / second
GPT Image 2
GPT Image 2 is OpenAI’s flagship image model in Made, strong at photorealism, exact prompt adherence, complex layouts, and readable typography, with instruction-based editing from a reference image.
1–22 credits / image
GPT Image 2.5 Fast
GPT Image 2.5 Fast is Made’s batched version of OpenAI’s GPT Image 2.5: compatible requests share one model call, which makes it the cheapest way to draft with GPT Image 2.5. It is text-to-image only, in square or 3:4 portrait.
1 credit / image
GPT Image 2.5 Flare
GPT Image 2.5 Flare is the original, unbatched OpenAI GPT Image 2.5 in Made: fast, high-quality generation and precise edits that change only what you ask, in nine sizes up to 4K.
1–42 credits / image
GPT Image 2.5 Sunburst
GPT Image 2.5 Sunburst is the original, unbatched OpenAI GPT Image 2.5 tuned for maximum detail and tighter control across demanding edits, in nine sizes up to 4K.
1–42 credits / image
Grok Imagine Image
Grok Imagine Image is xAI’s standard image tier in Made — fast text-to-image generation and reference-based editing at 2 credits per image, across thirteen aspect ratios from ultrawide 2:1 to tall 1:2.
2 credits / image
Grok Imagine Image 2.0
Grok Imagine Image 2.0 is xAI’s newest image model in Made, covering fast text-to-image generation and reference-based editing at 1K or 2K across thirteen aspect ratios.
from 4 credits / image
Grok Imagine Image Quality
Grok Imagine Image Quality is the quality-tuned tier of xAI’s Grok Imagine family in Made — higher-fidelity generation and reference-based editing with a selectable 1K or 2K output resolution across thirteen aspect ratios.
from 5 credits / image
Grok Imagine Video
Grok Imagine Video is xAI’s first-generation video model in Made, generating low-cost 1 to 15 second clips at 720p from a text prompt or a start image, in seven aspect ratios.
8 credits / second
Grok Imagine Video 1.5
Grok Imagine Video 1.5 is xAI’s current video model in Made, generating 1 to 15 second clips with audio on by default at 480p to 1080p, from a text prompt or a start image.
from 8 credits / second
Grok Imagine Video Extend
Create video with Grok Imagine Video Extend using the Made API.
8 credits / second
Hailuo 02
Create video with Hailuo 02 using the Made API.
4.5 credits / second
Happy Horse 1.1
Happy Horse 1.1 is Alibaba’s flagship video model — a long-running #1 on the Artificial Analysis Video Arena — generating 3 to 15 second clips at 1080p with native audio and multilingual lip-sync.
from 14 credits / second
Ideogram V4.5 Edit
Create images with Ideogram V4.5 Edit using the Made API.
1–22 credits / image
Image Compress
Create images with Image Compress using the Made API.
Priced by input
Image Convert
Create images with Image Convert using the Made API.
Priced by input
Image Resize
Create images with Image Resize using the Made API.
Priced by input
Kling 2.5 Turbo
Kling 2.5 Turbo is Kling AI’s fast image-to-video model in Made — every generation starts from an image you supply, animated into a 5 or 10 second clip that keeps the still’s composition.
4.2 credits / second
Kling 2.5 Turbo Pro
Create video with Kling 2.5 Turbo Pro using the Made API.
7 credits / second
Kling 2.6 Pro
Kling 2.6 Pro is Kling AI’s cinematic 2.x flagship in Made, generating stable, controlled 5 or 10 second clips from a text prompt or a start image — with an optional end frame for smoother image-to-video transitions.
7 credits / second
Kling 2.6 (Image to Video)
Kling 2.6 from a photo with native audio: it speaks the quoted line in your prompt (English and Chinese).
from 7 credits / second
Kling 3 4K
Kling 3 4K renders Kling AI’s third-generation video model directly at 3840×2160, with no upscaling pass. It makes 3 to 15 second clips from text or from a start image, with an optional end frame and native audio.
42 credits / second
Kling 3 Motion Control Pro
Create video with Kling 3 Motion Control Pro using the Made API.
Priced by input
Kling 3 Pro
Kling 3 Pro is the benchmark tier of Kling AI’s third-generation video model, generating 3 to 15 second clips with optional native audio and the cinematic motion the Kling line is known for.
from 11.2 credits / second
Kling 3 Pro (Image to Video)
Create video with Kling 3 Pro (Image to Video) using the Made API.
from 11.2 credits / second
Kling 3 Standard (Image to Video)
Create video with Kling 3 Standard (Image to Video) using the Made API.
from 8.4 credits / second
Kling 3 Turbo
Kling 3 Turbo is the fast tier of Kling AI’s third-generation video model, generating 3 to 15 second clips at 720p with native audio from a text prompt or a start image — the Kling look at a lower per-second rate.
11.2 credits / second
Kling AI Avatar v2 Pro
The 1080p Kling avatar: a photo speaks your voice track.
Priced by input
Kling AI Avatar v2 Standard
A photo speaks your voice track, for as long as the audio runs.
Priced by input
Kling LipSync
Kling LipSync takes a video of a person and a new audio track and regenerates realistic lip movement to match — swap the script, the language, or the voice without reshooting a frame.
Priced by input
Kling O3 4K
Kling O3 4K renders Kling AI’s realism-focused O3 model directly at 3840×2160, with no upscaling pass. It makes 3 to 15 second clips from text or from a start image, with an optional end frame and optional native audio.
42 credits / second
Kling O3 Video Edit Pro
Create video with Kling O3 Video Edit Pro using the Made API.
Priced by input
Kling O3 Pro
Kling O3 Pro is Kling AI’s realism-focused O3 line, generating 3 to 15 second clips with steady, believable motion and optional start and end frames for controlled transitions.
from 11.2 credits / second
Krea 2
Krea 2 is Krea’s aesthetic-first image model, tuned to avoid the generic “AI look” with opinionated color, light, and composition straight out of the prompt.
6 credits / image
LTX-2.5 Fast
LTX-2.5 Fast is Lightricks’ open audio-video model, generating 6 to 20 second clips with native synchronized audio included at every resolution, from text or a start image.
from 9 credits / second
MADE Image
Create images with MADE Image using the Made API.
4 credits / image
MADE Video
Create video with MADE Video using the Made API.
15 credits / video
MiniMax H3 Max
MiniMax H3 Max is a speed-focused, post-trained variant of the H3 video model, generating 5 to 15 second clips at 480P, 768P, or 1080P with strong prompt adherence — often in a few seconds.
from 5 credits / second
MiniMax H3 Max (Insert Scene)
Create video with MiniMax H3 Max (Insert Scene) using the Made API.
from 5 credits / second
MiniMax H3 Max (Reference to Video)
Create video with MiniMax H3 Max (Reference to Video) using the Made API.
8 credits / second
MiniMax H3 Max Turbo
MiniMax H3 Max Turbo is a fal-exclusive fast tier of the H3 Max video model, generating 5 to 15 second clips at 768P — the cheapest capable video generation in the Made library.
4 credits / second
Muse Image
Muse Image is Meta’s first image model, built for precise edits that change only what you ask, coherent multi-turn editing, multi-reference composition, and accurate rendered text — at 1 credit per image.
1 credit / image
Nano Banana
Nano Banana is the original model of Google’s family, running Gemini 2.5 Flash Image. It generates images and edits photos from plain-language instructions at a flat per-image price and a single, roughly 1-megapixel output size.
4 credits / image
Nano Banana 2
Nano Banana 2 runs Google’s Gemini 3.1 Flash Image, generating and editing images from 0.5K to 4K in 15 aspect ratios: fast and affordable for everyday work.
from 6 credits / image
Nano Banana 2.1
Nano Banana 2.1 is Google’s newest Nano Banana model, the successor to Nano Banana 2. It generates and edits images at 1K, 2K, or 4K in 15 aspect ratios, faster than Nano Banana 2 at the same price per image.
from 8 credits / image
Nano Banana 2 Lite
Nano Banana 2 Lite runs Google’s Gemini 3.1 Flash Image Lite, generating and editing images in under two seconds at a fixed 1K resolution — the speed tier of the Nano Banana family, with 14 aspect ratios from 21:9 to 1:8.
5 credits / image
Nano Banana Pro
Nano Banana Pro runs Google’s Gemini 3 Pro Image, the top tier of the Nano Banana family, generating and editing images at 1K, 2K, or 4K with legible in-image text and faithful identity across edits.
from 15 credits / image
OmniHuman 1.5
ByteDance's talking-avatar model: a photo speaks your voice track with gesture and expression.
Priced by input
Qwen Image
Qwen Image is a text-to-image model with a particular strength in structured compositions and prominent typography, plus optional source-image guidance in the current provider contract.
3 credits / image
Qwen Image 3
Qwen Image 3 is Alibaba’s latest open image model — two major versions past the original Qwen Image — combining generation and instruction-based editing with the family’s trademark reliable text rendering.
4 credits / image
Recraft 4.1
Recraft 4.1 is Recraft’s design-first image model, built for branded social assets, editorial compositions, product shots, and typography that sits inside the design rather than on top of it.
4 credits / image
Restore Image
Restore Image is a focused Made workflow for reducing scratches, fading, and visible damage while preserving the recognizable people and composition in a source photo.
4 credits / image
Reve Create
Create images with Reve Create using the Made API.
4 credits / image
Seedance 1.5 Pro
Seedance 1.5 Pro is the previous-generation Seedance model, generating 4 to 12 second clips at 720p with mixed dialogue, foley, and score audio — at roughly a sixth of the flagship Seedance 2.0 per-second rate.
5.2 credits / second
Seedance 1 Pro
Seedance 1.0 Pro is the original pro tier of ByteDance’s Seedance video line, generating 5 or 10 second silent clips at up to 1080p — one of the few Made video models with a selectable resolution control.
12.5 credits / second
Seedance 2.0
Seedance 2.0 is the flagship quality tier of ByteDance’s Seedance 2.0 video family, generating 4 to 15 second clips with native audio at 720p — the take-home fidelity the Fast and Mini tiers draft toward.
from 30.24 credits / second
Seedance 2.0 Fast
Seedance 2.0 Fast is the speed-focused tier of ByteDance’s Seedance 2.0 family, generating 4 to 15 second clips at 720p with native audio at roughly 20% below the flagship per-second rate.
24.19 credits / second
Seedance 2.0 (Image to Video)
Create video with Seedance 2.0 (Image to Video) using the Made API.
from 30.24 credits / second
Seedance 2.0 Mini
Seedance 2.0 Mini is the fast, low-cost tier of ByteDance’s Seedance 2.0 video model, generating 4 to 15 second clips at 720p with audio for quick drafts and high-volume runs.
from 7.21 credits / second
Seedance 2.0 Mini (Video Reference)
Create video with Seedance 2.0 Mini (Video Reference) using the Made API.
from 4.33 credits / second
Seedance 2.5
Seedance 2.5 is ByteDance’s newest video model in Made, generating clips up to 30 seconds in a single pass with native audio at 480p to 1080p — the longest single-shot ceiling in the Made library.
from 22.05 credits / second
Seedance 2.5 (Video Editing)
Create video with Seedance 2.5 (Video Editing) using the Made API.
Priced by input
Seedance 2.5 Person Reference
Create a video from an authorized person portrait. PiAPI reviews the reference before generation.
from 16.5 credits / second
Seedance 2.5 (Reference to Video)
Create video with Seedance 2.5 (Reference to Video) using the Made API.
from 22.05 credits / second
Seedance 2.5 (Video Reference)
Create video with Seedance 2.5 (Video Reference) using the Made API.
from 13.23 credits / second
Seedream 4
Seedream 4.0 combines detailed text-to-image generation with optional reference-image guidance, making it useful for polished concepts across square, portrait, landscape, and wide formats.
3 credits / image
Seedream 5 Lite
Seedream 5 Lite is the fast tier of ByteDance’s Seedream 5 image family, generating and editing photoreal images at a flat rate below Nano Banana and Seedream 4.5.
4 credits / image
Seedream 5 Pro
Seedream 5 Pro is ByteDance’s flagship image model, pairing the family’s signature photorealism with strong typography, complex layouts, and reference-guided consistency across up to 10 input images.
7 credits / image
Seedream 5 Pro Edit
Seedream 5 Pro Edit is the editing tier of ByteDance’s flagship Seedream 5 Pro, changing only what you ask — backgrounds, colors, objects, wardrobe — while preserving everything else, with up to 10 reference images per request.
7 credits / image
SeedVR2 Video Upscale
SeedVR2 is ByteDance’s video restoration model, upscaling any clip 2× or 4× with temporal consistency — frames stay coherent instead of flickering — from a single video input, no prompt required.
Priced by input
Sync Lipsync 3
Re-times the mouth in a video to a new voice track, up to 4K.
Priced by input
Topaz Image Upscale
Topaz Image Upscale runs Topaz Labs’ precision upscaling models — the professional standard for enlargement — recovering real detail at 2× or 4× from a single input image, no prompt required.
Priced by input
VEED Fabric 1.0
VEED Fabric 1.0 animates a single photo to speak any audio track — face, mouth, and subtle head motion are generated to match the voice, producing a talking video as long as the audio.
Priced by input
Veo 3
Google's original talking-video model: speech, sound and picture from a photo or a prompt.
40 credits / second
Veo 3.1
Veo 3.1 is Google’s flagship video model, generating 4 or 8 second clips with natively synchronized audio from a text prompt, with optional start and end frames to pin the first and last shot.
40 credits / second
Veo 3.1 Lite
Veo 3.1 Lite is the cost-efficient tier of Google’s Veo 3.1 family, generating 4, 6, or 8 second clips at 720p with natively synchronized audio from a text prompt or a start image.
from 5 credits / second
Veo 3.1 Native Dialogue
Veo 3.1 Native Dialogue animates a start image into an 8-second talking scene where the dialogue, lip movement, vocal performance, and environmental sound are all generated together — script the lines in quotes and the model performs them.
40 credits / second
Veo 3 Fast
The faster, lower-priced Veo 3: speech and sound from a photo or a prompt.
15 credits / second
Video Frame
Create images with Video Frame using the Made API.
Priced by input
WAN 2.2 5B
WAN 2.2 5B is Wan AI’s compact draft model, generating short clips from a text prompt or a start image at 580p or 720p in three aspect ratios — billed at a flat rate per video, not per second.
15 credits / video
WAN 2.2 Turbo
WAN 2.2 Turbo is Made’s fast iteration option for short text-to-video and image-to-video clips, with portrait and landscape output controls.
15 credits / video
WAN 2.5 (Image to Video)
WAN 2.5 from a photo: it speaks a quoted line from your prompt, or lip-syncs to a voice track you add.
from 5 credits / second
WAN 2.7
WAN 2.7 is Wan AI’s current-generation video model, generating 2 to 15 second clips at up to 1080p with synchronized audio from a text prompt or a start image.
from 10 credits / second
WAN 3.0
WAN 3.0 is the standard tier of Alibaba’s WAN 3.0 video line, generating 2 to 30 second clips at 1080p with audio included — half the per-second rate of WAN 3.0 Prime.
from 5 credits / second
WAN 3.0 Prime
WAN 3.0 Prime is the premium tier of Alibaba’s WAN 3.0 video family, generating clips from 2 to 30 seconds with synchronized audio at up to 1080p, including 30 fps image-to-video.
from 6.8 credits / second
WAN 3.0 Prime (Reference to Video)
Create video with WAN 3.0 Prime (Reference to Video) using the Made API.
from 6.8 credits / second
Z Image
Z Image is Made’s fal.ai-backed text-to-image option for quick concept generation across common square, portrait, and landscape sizes.
2 credits / image