MODEL PROVIDER
MiniMax
Explore 27 models and APIs from MiniMax, available through one SandBase integration.
Large Language Models (LLMs)
4 models
minimax/minimax-m3
MiniMax-M3 is MiniMax's flagship multimodal foundation model, which MiniMax describes as open-weight. It is built on MiniMax Sparse Attention, which selects key-value blocks to cut long-context comput...
minimax/minimax-m2.5
MiniMax-M2.5 is a MiniMax M2-series language model released in February 2026 for real-world productivity, trained with reinforcement learning across hundreds of thousands of complex real-world environ...
minimax/minimax-m2.7
MiniMax-M2.7 is a MiniMax M2-series language model that MiniMax describes as its first model to take part in its own development, building agent harnesses, skills and memory for reinforcement learning...
minimax/minimax-m3.1-flash
MiniMax-M3.1-Flash is the fast, cost-efficient tier of MiniMax's M3.1 generation, which MiniMax describes as an ultra-efficient open-weight model for everyday work. It is a multimodal coding model tha...
Video Models
15 models
minimax/h3-max-turbo/text-to-video
MiniMax H3 Max Turbo, the fastest tier of the H3 family post-trained by fal, turns a text prompt into a 5-15 second video with native audio.
minimax/h3-max-turbo/image-to-video
MiniMax H3 Max Turbo, the fastest tier of the H3 family post-trained by fal, animates a first frame (and optional last frame) into a 5-15 second video with native audio.
minimax/h3-max-turbo/video-extend
MiniMax H3 Max Turbo, the fastest tier of the H3 family post-trained by fal, continues an existing video with 1-15 seconds of new footage with native audio.
minimax/h3-max/text-to-video
MiniMax H3 Max by MiniMax turns a text prompt into a 5-15 second video with native audio at 480P or 768P, generating faster than MiniMax H3.
minimax/h3-max/image-to-video
MiniMax H3 Max by MiniMax animates a first frame, optionally toward a last frame, into a 5-15 second video with native audio at 480P or 768P.
minimax/h3-max/reference-to-video
MiniMax H3 Max by MiniMax generates a 5-15 second video with native audio at 480P or 768P that keeps subjects, motion, and voice consistent with reference images, videos, and audio.
minimax/h3/text-to-video
Generate native-stereo 2K video from text with MiniMax H3.
minimax/h3/image-to-video
Generate native-stereo 2K video from a first frame and optional last frame with MiniMax H3.
minimax/h3/reference-to-video
Generate native-stereo 2K video guided by image, video, and audio references with MiniMax H3.
minimax/hailuo/2.3/pro/text-to-video
MiniMax Hailuo 2.3 Pro by MiniMax turns a text prompt into a 6-second 1080P video with realistic motion and strong prompt following.
minimax/hailuo/2.3/standard/text-to-video
MiniMax Hailuo 2.3 Standard by MiniMax turns a text prompt into a 6 or 10 second 768P video with realistic motion.
minimax/hailuo/2.3/pro/image-to-video
MiniMax Hailuo 2.3 Pro by MiniMax animates a still image into a 6-second 1080P video with realistic motion and expressive characters.
minimax/hailuo/2.3/standard/image-to-video
MiniMax Hailuo 2.3 Standard by MiniMax animates a still image into a 6 or 10 second 768P video with realistic motion.
minimax/hailuo/2.3-fast/standard/image-to-video
MiniMax Hailuo 2.3 Fast Standard by MiniMax animates a still image into a 6 or 10 second 768P video at lower cost and latency than Hailuo 2.3 Standard.
minimax/hailuo/2.3-fast/pro/image-to-video
MiniMax Hailuo 2.3 Fast Pro by MiniMax animates a still image into a 6-second 1080P video at lower cost and latency than Hailuo 2.3 Pro.
Audio Models
8 models
minimax/music/2.6
MiniMax Music 2.6 by MiniMax composes a full song with vocals and accompaniment from a style prompt and lyrics, or an instrumental track without lyrics.
minimax/music/3
MiniMax Music 3 by MiniMax composes a complete song up to five minutes long with expressive vocals and evolving arrangements from a style prompt and lyrics.
minimax/speech/2.8/hd
MiniMax Speech 2.8 HD by MiniMax converts text into expressive, high-fidelity speech in 40+ languages with system or cloned voices and emotion control.
minimax/voice-clone
MiniMax Voice Clone by MiniMax creates a reusable custom voice from a reference recording of at least 10 seconds and returns a short preview spoken in that voice.
minimax/speech/2.8/turbo
MiniMax Speech 2.8 Turbo by MiniMax converts text into expressive speech in 40+ languages with low latency, system or cloned voices, and emotion control.
minimax/speech/2.6/hd
MiniMax Speech 2.6 HD by MiniMax converts text into natural, high-fidelity speech in 40+ languages with system or cloned voices and emotion control.
minimax/speech/2.6/turbo
MiniMax Speech 2.6 Turbo by MiniMax converts text into natural speech in 40+ languages with low latency, system or cloned voices, and emotion control.
minimax/voice-design
MiniMax Voice Design by MiniMax creates a new reusable voice from a text description of its timbre, age, and style, and returns a spoken preview.