31 video and 17 image models — pick by budget or capability, all on the same endpoint.
The lowest-credit models for testing and iteration. Lock your prompt on one of these, then switch to a premium model for the final render — same call, same payload.
Sorted by the credit cost of the cheapest job. Filter by type or band, then open any model for its full pricing and capabilities.
Showing all 48 models
Z-Image
Alibaba (Tongyi)
image
Budget
Ultra-cheap, fast photorealistic image generation.
from 2 cr
Special video voice elevenlabs_template_baby
video
Budget
from 3 cr
Nano Banana
Google (Gemini)
image
Budget
Fast, low-cost Gemini image generation and editing.
from 4 cr
Qwen Image
Alibaba (Qwen)
image
Budget
Image generation and editing with best-in-class text rendering.
from 4 cr
Wan 2.7 Image
Alibaba (Tongyi)
image
Budget
Director-grade suite: generate, reference and edit video.
from 5 cr
Qwen Image 2
Alibaba (Qwen)
image
Budget
Image generation and editing with best-in-class text rendering.
from 6 cr
Seedream 5.0 Lite
ByteDance
image
Budget
Text-to-image and editing with multimodal reasoning, up to 4K.
from 6 cr
Flux
Black Forest Labs
image
Budget
Photorealistic text-to-image from Black Forest Labs.
from 8 cr
GPT Image 1.5
OpenAI
image
Budget
OpenAI image generation and editing with strong prompt following.
from 8 cr
Grok Imagine
xAI
image
Budget
xAI text-to-image generation and editing.
from 8 cr
Imagen
Google
image
Budget
Google's photorealistic text-to-image model (Imagen 4 Ultra).
from 8 cr
Grok Imagine Video
xAI
video
Budget
xAI text and image to video.
from 10 cr
Wan 2.7 Image Pro
Alibaba (Tongyi)
image
Budget
Director-grade suite: generate, reference and edit video.
from 12 cr
GPT Image 2
OpenAI
image
Budget
OpenAI image generation and editing with strong prompt following.
from 14 cr
Seedream 4.5
ByteDance
image
Budget
Text-to-image and editing with multimodal reasoning, up to 4K.
from 16 cr
Nano Banana 2
Google (Gemini)
image
Budget
Fast Gemini image generation and editing, 1K to 4K.
from 18 cr
Special video image gpt_image_2
image
Budget
from 18 cr
Nano Banana Pro
Google (Gemini)
image
Budget
Reasoning-grade image generation and editing at up to 4K.
from 20 cr
Seedance 1.5 Pro
ByteDance
video
Budget
Multimodal video with native audio and multi-shot cuts.
from 20 cr
Ideogram Character
Ideogram
image
Budget
Keep one character consistent across images from a single reference.
from 24 cr
Hailuo 2.3 Standard
MiniMax
video
Budget
Image-to-video at standard and pro quality tiers.
from 30 cr
Wan 2.7 Image to Video
Alibaba (Tongyi)
video
Budget
Director-grade suite: generate, reference and edit video.
from 32 cr
Wan 2.7 R2V
Alibaba (Tongyi)
video
Budget
Director-grade suite: generate, reference and edit video.
from 32 cr
Wan 2.7 Video
Alibaba (Tongyi)
video
Budget
Director-grade suite: generate, reference and edit video.
from 32 cr
Wan 2.7 Video Edit
Alibaba (Tongyi)
video
Budget
Director-grade suite: generate, reference and edit video.
from 32 cr
Seedance 2.0 Mini
ByteDance
video
Budget
Multimodal video with native audio and multi-shot cuts.
from 38 cr
AI Video Lip Sync
video
Budget
Re-sync an existing video's lips to new target audio.
from 40 cr
Veo 3.1 Lite
Google DeepMind
video
Budget
Cinematic text/image-to-video with synchronized native audio.
from 40 cr
Hailuo 2.3 Pro
MiniMax
video
Standard
Image-to-video at standard and pro quality tiers.
from 45 cr
Gemini Omni Audio
Google
video
Standard
Any-input-to-video with voice and character consistency.
from 50 cr
Gemini Omni Character
Google
video
Standard
Any-input-to-video with voice and character consistency.
from 50 cr
Kling 3.0 Motion Control
Kuaishou
video
Standard
Transfer motion from a reference video onto your character.
from 60 cr
Special video lip_sync volcengine_v2v_lip_sync
video
Standard
from 64 cr
Seedance 2.0 Fast
ByteDance
video
Standard
Multimodal video with native audio and multi-shot cuts.
from 71 cr
Seedance 2.0
ByteDance
video
Standard
Multimodal video with native audio and multi-shot cuts.
from 86 cr
Gemini Omni Video
Google
video
Standard
Any-input-to-video with voice and character consistency.
from 90 cr
Kling 3.0
Kuaishou
video
Standard
Director-grade text/image-to-video, with a fast tier.
from 90 cr
Kling V3 Turbo
Kuaishou
video
Standard
Director-grade text/image-to-video, with a fast tier.
from 90 cr
Kling V3 Turbo Image to Video
Kuaishou
video
Standard
Director-grade text/image-to-video, with a fast tier.
from 90 cr
HappyHorse Video Edit
Alibaba
video
Standard
Joint audio-video generation with best-in-class multilingual lip-sync.
from 93 cr
HappyHorse 1.1 Image to Video
Alibaba
video
Standard
Joint audio-video generation with best-in-class multilingual lip-sync.
from 99 cr
HappyHorse 1.1 Reference to Video
Alibaba
video
Standard
Joint audio-video generation with best-in-class multilingual lip-sync.
from 99 cr
HappyHorse 1.1 Video
Alibaba
video
Standard
Joint audio-video generation with best-in-class multilingual lip-sync.
from 99 cr
Veo 3.1 Fast
Google DeepMind
video
Standard
Cinematic text/image-to-video with synchronized native audio.
from 100 cr
Kling 2.6
Kuaishou
video
Premium
Director-grade text/image-to-video, with a fast tier.
from 110 cr
OmniHuman 1.5
ByteDance
video
Premium
Expressive talking avatar from one image and audio.
from 135 cr
Wan VACE
Alibaba (Tongyi)
video
Premium
All-in-one video creation and editing under one model.
from 160 cr
Veo 3.1 Quality
Google DeepMind
video
Premium
Cinematic text/image-to-video with synchronized native audio.
from 220 cr
One key for deterministic JSON-to-video and every model above. Start on the free plan, query exact credit costs from the API, upgrade when you scale.