The endpoint uses MiniMax’s MiniMax-Hailuo-2.3, released through the MiniMax Open Platform API on October 28, 2025. It does not cover Hailuo 2.3 Fast, Hailuo 02, or earlier Hailuo models.
MiniMax Hailuo 2.3 generates videos from text or one starting image, with particular strength in complex physical action, expressive character performance, motion-command adherence, and varied visual styles. APIXO groups standard 768p and pro 1080p workflows under one asynchronous endpoint with distinct duration and billing rules.
Workflows
Text-to-Video / Image-to-Video
Standard Price
$0.056/secAPIXO 768p modes
Pro Price
$0.49/generationAPIXO fixed 1080p generation
APIXO Output
768p / 1080p
Released
Oct 28, 2025
Loading workspace...
Generate more fluid and controlled character actions, including demanding movement sequences. MiniMax specifically improved the model’s understanding of physical action, helping poses and transitions remain more natural during dynamic performance.
Create live-action character performances with subtler facial changes and more natural emotional detail. This makes Hailuo 2.3 useful when expression, reaction, and personality need to carry a short scene.
Direct how characters and objects should move through the scene. Improved response to motion instructions supports clearer actions, product behavior, timing cues, and camera-aware movement within concise generated shots.
Combine moving subjects with dynamic camera direction while retaining more coherent lighting, shadow transitions, and color. Detailed prompts can establish shot movement, atmosphere, visual emphasis, and scene rhythm.
Work across live action, anime, illustration, game CG, ink-wash aesthetics, and other stylized directions. Hailuo 2.3 is designed to preserve a wider variety of visual languages during motion.
Animate products, props, vehicles, effects, and environmental elements with improved response to movement instructions. This supports advertising concepts where the featured object—not only a human character—drives the shot.
Generate from text or one image at 768p. Choose a 6- or 10-second duration, with APIXO billing each output second at $0.056. Standard modes suit story development and shots that need the longer available duration.
Generate from text or one image at 1080p for a fixed APIXO price of $0.49 per generation. On this endpoint, pro modes ignore the submitted duration and return a fixed five-second clip.
Verified identity, inputs, modes, and delivery behavior for this endpoint.
6 / 10 Seconds
Standard Duration
Fixed 5 Seconds
Pro Duration
Standard / Pro
APIXO Modes
1 Image URL
Reference Limit
1 Generated Video
Output Count
Async / Callback
Delivery
Develop dance, sports, dramatic reaction, and performance concepts that depend on coordinated body movement and facial expression. Use descriptive prompts for action order, emotional progression, camera behavior, lighting, and pacing.
Animate product reveals, demonstrations, fashion moments, and ecommerce campaign concepts. Hailuo 2.3’s stronger object-motion response helps when movement, materials, visual effects, and camera direction must work together in one concise shot.
Explore anime, illustration, game CG, ink-wash, and surreal motion directions without switching to a style-specific endpoint. Image-to-video mode can begin from an approved character or environment frame when the initial design matters.
Validate camera movement, blocking, lighting transitions, effects, and scene rhythm before live production or detailed animation. Standard mode provides longer exploration, while APIXO’s pro tier supplies a shorter 1080p output for higher-resolution review.
APIXO exposes separate standard and pro modes for both text-to-video and image-to-video generation.
Standard modes accept 6- or 10-second duration and always produce 768p output.
Pro modes ignore duration and produce a fixed five-second 1080p video on APIXO.
Image-to-video requires exactly one public JPG, JPEG, or PNG image URL.
APIXO does not publicly expose aspect-ratio, frame-rate, seed, audio, or camera-preset fields for this route.
Prompts, source images, and outputs remain subject to provider safety review and may be rejected.
The endpoint uses MiniMax’s MiniMax-Hailuo-2.3, released through the MiniMax Open Platform API on October 28, 2025. It does not cover Hailuo 2.3 Fast, Hailuo 02, or earlier Hailuo models.
Hailuo 2.3 is the quality-focused model and supports both text-to-video and image-to-video. MiniMax positions Hailuo 2.3 Fast as the lower-cost, speed-oriented image-to-video variant; APIXO provides it through a separate endpoint.
No. APIXO publicly documents one starting image for Hailuo 2.3 image-to-video mode. It does not expose a last-frame field, end-frame-only workflow, subject-reference mode, video input, or multiple reference images on this endpoint.
Not through the published APIXO schema. The exposed creative inputs are the mode, prompt, duration, and—when using image-to-video—one image URL. The source image should therefore be prepared with the intended composition before submission.
APIXO does not document an audio input, audio-generation switch, or guaranteed soundtrack for this endpoint. Treat Hailuo 2.3 as a visual video-generation route and plan separate sound design unless output testing confirms otherwise.
Discover more AI models for your next creative workflow
Hailuo 2.3 Fast is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Seedance 2.0 Fast is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Seedance 2.0 is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Veo 3.1 is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Grok Video is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Video
