One API. Every model.
Access leading image, video, LLM, and 3D APIs from one account — create faster and ship without juggling providers.
Provider
Model capabilities
MiniMaxMiniMax H3 Max Turbo Text to Video turns text into coherent 5–15 second videos with synchronized native stereo audio and fast generation. It follows physical motion while rendering subtle changes in light and shadow.
From
MiniMaxMiniMax H3 Max Turbo Image to Video turns still images into 5–15 second videos with start and end frame control and synchronized native stereo audio. It preserves the source subject and textures while adding realistic physical motion.
From
MiniMaxMiniMax H3 Max Text to Video turns text prompts into cinematic video with native stereo audio, faster-than-real-time generation, and precise instruction following. It renders complex camera work and physical motion with fine detail across multiple resolutions and common aspect ratios.
From
MiniMaxMiniMax H3 Max Image to Video turns still images into video with native stereo audio, start and end frame control, and lip-synced dialogue. It preserves the source subject's identity and textures while adding fluid, natural motion and camera work.
From
MiniMaxMiniMax H3 Max Reference to Video creates cinematic video with combined image, video, and audio guidance. It preserves character appearance and motion rhythm while adapting the aspect ratio and delivering multiple HD quality levels.
From
MiniMaxMiniMax H3 on Vidgo API with separate text-to-video, start/end-frame image-to-video, and multimodal reference-to-video workflows at fixed 2K output.
From
MiniMaxMiniMax H3 on Vidgo API with separate text-to-video, start/end-frame image-to-video, and multimodal reference-to-video workflows at fixed 2K output.
From
MiniMaxMiniMax H3 on Vidgo API with separate text-to-video, start/end-frame image-to-video, and multimodal reference-to-video workflows at fixed 2K output.
From
MiniMaxHailuo 2.3 Standard Text to Video: Generate realistic 768p video scenes from text prompts with MiniMax Hailuo 2.3. Supports 6s and 10s durations, up to 5,000 characters of prompt control, prompt optimization, and fluid physical motion simulation via REST API and playground.
From
MiniMaxHailuo 2.3 Standard Image to Video: Animate still photos into natural 768p AI videos from a starting image and text prompt using MiniMax Hailuo 2.3. Supports 6s and 10s duration control, character micro-expressions, and subject consistency via REST API and playground.
From
MiniMaxHailuo 2.3 Pro Text to Video by MiniMax transforms text prompts into cinematic native 1080p video clips in fixed 6-second durations. Featuring realistic physics simulation, sophisticated lighting and camera motion, high-definition character fidelity, an interactive playground, and high-concurrency REST API integration.
From
MiniMaxHailuo 2.3 Pro Image to Video by MiniMax converts first-frame images into cinematic native 1080p video clips across fixed 6-second durations. Featuring pixel-level facial identity preservation, nuanced micro-expressions, fluid 3D camera parallax, an interactive playground, and high-throughput REST API integration.
From
MiniMaxGenerate 512P or 768P videos from text or images, with optional prompt optimization.
From
MiniMaxGenerate 512P or 768P videos from text or images, with optional prompt optimization.
From
MiniMaxGenerate 512P or 768P videos from text or images, with optional prompt optimization.
From
MiniMaxGenerate 512P or 768P videos from text or images, with optional prompt optimization.
From