API Marketplace

Browse and integrate AI video generation models into your application.

Google Veo 3.1 video generation via google. Generate high-quality AI videos from text prompts with native audio.

Veo 3.1 Extendfrom 60 credits

Veo 3.1from 40 credits

Seedance 2.0 multi-modal video generation. Supports text, image, video, and audio references with configurable duration (4-15s), resolution (480p/720p/1080p), and aspect ratio.

Seedance 2.0 Fastfrom 7.5 credits/s

Seedance 2.0 Minifrom 2.4 credits/s

Seedance 2.0from 12 credits/s

Seedance 1.5 Pro

Seedance 1.5 Pro video generation via zlhub. Supports text-to-video, first-frame image-to-video, and first-and-last-frame image-to-video.

Seedance 1.5 Profrom 3 credits/s

Kuaishou Kling 3.0 video generation. Native audio with cinematic control, 720P/1080P, 3-15 second outputs.

Kling 3.0from 28 credits/s

Kuaishou Kling 2.6 image-to-video. Convert a still image into a 5s or 10s video, with optional native audio.

Kling 2.6from 22 credits/s

Kling 3.0 Motion Control

Kuaishou Kling 3.0 Motion Control. Transfer the motion from a reference video onto a character in a reference image, preserving identity and appearance. 720P/1080P, up to 30 seconds.

Kling 3.0 Motion Controlfrom 30 credits/s

Alibaba HappyHorse 1.0 video generation and editing via Bailian/DashScope.

HappyHorse 1.0 (Text-to-Video)from 30 credits/s

HappyHorse 1.0 (Image-to-Video)from 30 credits/s

HappyHorse 1.0 (Reference-to-Video)from 30 credits/s

HappyHorse 1.0 (Video Edit)from 30 credits/s

Alibaba HappyHorse 1.1 video generation and editing via Bailian/DashScope.

HappyHorse 1.1 (Image-to-Video)from 30 credits/s

HappyHorse 1.1 (Text-to-Video)from 30 credits/s

HappyHorse 1.1 (Video Edit)from 30 credits/s

HappyHorse 1.1 (Reference-to-Video)from 30 credits/s

xAI Grok Imagine video generation. Text-to-video and image-to-video, 6-30s, 480p / 720p.

Grok Imagine (Text-to-Video)from 2.4 credits/s

Grok Imagine (Image-to-Video)from 2.4 credits/s

Open-weights video generation with native audio: text, first/last frames, and multimodal references. 3-15 seconds at 480p, 540p, 768p or 1080p.

MiniMax H3 SH Text to Videofrom 8 credits/s

MiniMax H3 SH Image to Videofrom 8 credits/s

MiniMax H3 SH Reference to Videofrom 10 credits/s

MiniMax H3 Max Turbo

MiniMax H3 Max Turbo 5-15 second text-to-video and first/last-frame video generation at 480p or 768p. Input images are free.

MiniMax H3 Max Turbofrom 6.54 credits/s

Wan 3.0 All-in-One

Alibaba Wan 3.0 All-in-One video generation via an invited Beijing Bailian Workspace: text, first/last frame, multimodal references, files, and public web pages.

Wan 3.0 Videofrom 12 credits/s

Wan 3.0 Video Primefrom 18 credits/s

Alibaba WAN 2.7 video generation and editing via Bailian/DashScope. Text-to-video, image-to-video, reference-to-video, and video editing with synced audio, 720p / 1080p.

WAN 2.7 (Video Edit)from 24 credits/s

WAN 2.7 (Reference-to-Video)from 24 credits/s

WAN 2.7 (Text-to-Video)from 24 credits/s

WAN 2.7 (Image-to-Video)from 24 credits/s

Ideogram V4 text-to-image generation. Crisp visuals, accurate text rendering — logos, posters, marketing visuals. TURBO / BALANCED / QUALITY rendering speeds.

Ideogram V4 (Text-to-Image)from 28 credits

Google Gemini 3.1 Flash Image - lightning-fast speed with Pro-level quality, 4K output, text rendering, and image editing.

Nano Banana 2from 16 credits

MiniMax H3 Fast

MiniMax H3 Fast 480p video generation from text, first/last frames, or image, video and audio references. Only generated output is billed.

MiniMax H3 Fastfrom 11.68 credits/s

Alibaba WAN 2.6 video generation via Bailian/DashScope. Text-to-video, image-to-video, and reference-to-video with audio, 720p / 1080p.

WAN 2.6 (Image-to-Video)from 24 credits/s

WAN 2.6 (Text-to-Video)from 24 credits/s

WAN 2.6 (Reference-to-Video)from 24 credits/s

Fast MiniMax H3 Max video generation for text-to-video and first/last-frame image-to-video at 480p or 768p.

MiniMax H3 Maxfrom 12.7 credits/s

MiniMax H3 native multimodal video generation. Create text-to-video, first/last-frame animation, or reference-guided video with images, videos, and audio at 2K. 768p is coming soon.

MiniMax H3from 19.23 credits/s

Nano Banana 2 Lite

Nano Banana 2 Lite image generation via kie.ai. Supports prompt-based generation and reference-image editing at 1K output.

Nano Banana 2 Litefrom 10 credits

Doubao Seedream

Doubao Seedream image generation via zlhub. Supports Seedream 5.0 Pro, Seedream 5.0 Lite, and Seedream 4.5 for text-to-image and image-reference workflows.

Doubao Seedream 5.0 Litefrom 0 credits/s

Seedream 5.0 Flashfrom 4.68 credits/output

Doubao Seedream 4.5from 0 credits/s

Doubao Seedream 5.0 Profrom 0 credits/s

WaveSpeed AI image upscaling to 2K, 4K, or 8K with JPEG, PNG, and WebP output.

Image Upscalerfrom 4 credits

Seedance 2.5 multimodal video generation at 480p, 720p, or 1080p with text, image, video, audio, and first/last-frame inputs.

Seedance 2.5from 17.24 credits/s

Music Video Generator

AI music video generator. Turn any song plus up to 3 reference photos into a lip-synced music video with cinematic camera angles and smooth transitions. 480p / 720p, up to 10 minutes.

Music Video Generatorfrom 9 credits/s

AI music generation powered by Suno. Generate high-quality songs with lyrics, instrumentals, and custom styles.

Suno V5.5from 24 credits

Suno V5from 24 credits

Music to Video Pro

Revid music-to-video workflow. Generate AI music videos from an audio URL with optional reference images, prompt, subtitles, ratio, resolution, and lyrics lip sync.

Music to Video Profrom 117 credits/s

videoAI Video API

Generate consistent long-form videos up to 180 seconds with HappyHorse or Seedance.

Long Videofrom 21.6 credits/s

ElevenLabs Text-to-Dialogue v3

ElevenLabs Eleven v3 text-to-dialogue: generate natural, expressive multi-speaker dialogue audio across 70+ languages. Powered by kie.ai.

ElevenLabs Text-to-Dialogue v3from 0 credits/s

MiniMax Speech 2.8

MiniMax Speech 2.8 asynchronous long-text speech generation with HD and Turbo models.

MiniMax Speech 2.8 Turbofrom 0 credits/s

MiniMax Speech 2.8 HDfrom 0 credits/s

otherElevenLabs

ElevenLabs Text to Speech

Natural multilingual text-to-speech with expressive voices, adjustable similarity and stability, and fast asynchronous delivery.

ElevenLabs Turbo V2.5from 0 credits/s

ElevenLabs Multilingual V2from 0 credits/s

Google Gemini family — 2.5 / 3 / 3.1 series in Flash & Pro variants, native and OpenAI-compat endpoints.

Gemini 2.5 Profrom 0 credits

Gemini 3 Flashfrom 0 credits

Gemini 3 Profrom 0 credits

Gemini 3.1 Profrom 0 credits

otherMoonshot AI

Kimi chat models exposed through the OpenAI-compatible Chat Completions API.

Kimi K3from 0 credits