37 model families · 358+ endpoints
AI Model APIs
One API key for the leading video, image and 3D models. Pick a model to see its endpoints, live pricing and ready-to-run code.
curl -X POST https://api.wavespeed.ai/api/v3/<model> \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{"prompt": "…"}'Video23
Text, image and reference to video, plus editing and extension.
FLUX 3 API
Black Forest Labs FLUX 3 API is live on WaveSpeedAI with text-to-video, image-to-video, start-end-frame video, video extension, Draft, and video-up…
MiniMax H3 API
MiniMax H3 API for cinematic text-to-video, image-to-video, and reference-to-video generation with native stereo audio, strong motion quality, subj…
Seedance 2.5 API
With text-to-video, image-to-video, video-edit, video-extend, and turbo endpoints.
Seedance 2.0 Mini API
The faster, lower-cost tier of Seedance 2.0.
Seedance 2.0 API
Hollywood-grade cinematic video with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stabil…
Seedance 1.5 Pro API
Cinematic, live-action-leaning clips with strong prompt adherence, expressive motion, and stable aesthetics.
Veo 3.1 API
Text-to-video with synchronized native audio at 1080p.
Wan 3.0 API
Cinematic video in a single generation pass of up to 30 seconds, double the ceiling of Wan 2.7.
Wan 2.7 API
Coherent cinematic video with crisp detail, stable motion, and strong instruction-following.
Happy Horse 1.0 API
Cinematic 720p / 1080p video with smooth camera movement, expressive motion, and strong prompt fidelity.
Kling 3.0 API
Text-to-video and image-to-video with smooth motion, cinematic visuals, accurate prompt adherence, and native audio.
Kling 3.0 Motion Control API
Transfers motion from a reference video to animate a still character image.
Vidu Q4 API
Image-to-video and reference-to-video with 3-16 second clips, 540p to 4K output, and optional generated audio.
Vidu Q3 API
Text-to-video, image-to-video, reference-to-video (1-4 reference images for multi-entity consistency), and start-end-to-video.
InfiniteTalk API
Converts one photo + audio into talking OR singing avatar videos, up to 10 minutes.
Wan 2.2 API
Open-weight video toolkit deployed on WaveSpeedAI with 35+ first-party variants: Animate (120s character animation), Video Edit, Speech-to-Video (1…
Sora 2 API
State-of-the-art text-to-video and image-to-video with realistic visuals, accurate physics, synchronized audio, and strong steerability.
Kling Omni O3 API
Advanced unified multi-modal video model with MVL (Multi-modal Visual Language) technology.
Grok Imagine Video 1.5 API
Fast text-to-video up to 1080p, image-to-video, and reference-to-video from up to seven reference images with identity-consistent output and select…
Grok Imagine Video API
Text-to-video, image-to-video, reference-to-video, video-extend, and edit-video, plus the fast v1.5 generation with 1080p text-to-video and referen…
Hailuo 2.3 API
Physics-aware text-to-video and image-to-video with 2.5× efficiency improvement and 85% complex-instruction accuracy.
Wan 2.6 API
Text-to-video and image-to-video with synced audio at 720p/1080p, plus reference-to-video, video-extend, image-edit, and text-to-image in the same …
Higgsfield API Alternative
Seedance 2.5 and 2.0, Kling 3.0 and O3, Wan 3.0, open-weights MiniMax H3 and Qwen Image 3.0 — plus Seedream 5.0, Nano Banana 2 and Pro, and GPT Ima…
Image11
Text to image and image editing, from fast drafts to 4K.
Nano Banana Pro API
High-res 4K text-to-image and image editing optimized for phones.
Nano Banana 2.1 API
The latest Nano Banana image generation and editing model.
Nano Banana 2 API
Pro-quality image generation at Flash speed.
GPT Image 2 API
High-quality text-to-image and edit endpoints from natural-language prompts.
GPT Image 2.5 API
Text-to-image and edit endpoints in two tiers, Flare (fast, balanced) and Sunburst (precision-focused), with five quality levels from low to max, 1…
Seedream 4.5 API
Next-gen text-to-image model optimized for typography.
Seedream 5 API
Two tiers on one API.
Video Watermark Remover API
Removes Kling and Seedance watermarks, logos, captions, and text from videos while preserving quality.
Qwen Image 3.0 API
Standard and Pro text-to-image and image-edit endpoints with flexible aspect ratios, 1K/2K output, and natural-language instruction understanding.
Qwen Image API
20B MMDiT next-gen text-to-image and editing toolkit with bilingual Chinese/English support, multi-image editing, LoRA customization, layered compo…
Flux 2 Klein API
High-quality 4B and 9B text-to-image and edit models with enhanced realism, crisper text generation, and LoRA support for fast customization.
Tools02
Upscaling and clean-up for images and video.
Image Upscaler Collection API
WaveSpeedAI (Standard, Ultimate, Real-ESRGAN), Clarity AI (Creative, Crystal, Flux, Pro), Recraft (Creative, Crisp), and Pruna AI — all reachable t…
Video Upscaler Collection API
WaveSpeedAI (Standard, Pro, Ultimate, SeedVR2, LTX-2 19B), ByteDance, Bria, and Clarity AI — all reachable through one WaveSpeedAI API key.
3D01
Text and image to 3D assets.
Build with one API key
Every model on WaveSpeedAI shares the same REST API, SDKs and billing.