Try GPT Image 2.6 Flare by OpenAI from OpenAI →
Models
Agents
Workflows
Studio
PricingBlogDocs
ExploreDiscover models by categoryDiscoverModels and effects built by WiroBrowse All ModelsBrowse the complete catalogSee FavoritesSign in to view saved models
Generative Media AgentCreate and edit media by chattingWorkflow AgentBuild visual workflows with Agent
OverviewThe platform at a glanceLearnSkills, knowledge, guardrailsAnatomyWhat makes agents reasonBuild Your AgentPick connectors and skills, set tier, deploy
Pre-built AgentsBrowse the catalog
Agent Usecases
Ad Campaign ManagerApp Event ManagerApp Review RepliesBarber BookingCustomer Win-BackEcommerce ListingsRestaurant Reviews
Sign InStart Building
Explore models/
Video GenerationActive

MiniMax H3 Highspeed Video Generator

byminimax

MiniMax H3 Highspeed generates 4-15s 768P videos from a prompt, with optional first and last frame images to control the opening and ending.

Text to VideoImage to Video
Model ID
h3 highspeed
Provider
minimax
Updated
Nov 5, 2026, 15:00
0
Comments
Average rating : 0 (0 users)
Providerminimax
Modelh3 highspeed
Text to VideoImage to Video
Support Wiro on G2
wiro playground—minimax/h3 highspeed
1 / 1
Maximum 1 image allowed
Image 1

Optional. Leave empty for text-to-video. Sets the opening frame of the video.

Required. Describes the video to generate. Speech in quotes is spoken on camera.

Required. Length of the video in whole seconds, between 4 and 15.

Required. Default 768P. Choose 480P for a faster, cheaper result.

Sample outputs
Updated Nov 5, 2026, 15:00

Overview

MiniMax H3 Highspeed is a MiniMax video generation model built for fast 768P clips. It takes a scene description and optional keyframe images, then generates a short MP4 video with stereo audio. It’s useful when you need a quick shot with a defined start or end frame.

What you can build

  • Social clips from a single prompt, like product shots or travel B-roll
  • Image-to-video animations that start from a provided first frame
  • First-to-last frame transitions for simple story beats and shot continuity
  • Short ad concepts and motion tests for editing timelines
  • Vertical or square clips for different feed formats

Inputs

  • A required written prompt that describes the scene, subject, motion, camera, and style. If you include speech in quotes, treat it as spoken dialogue on camera.
  • A clip duration you choose as a whole number of seconds from 4 to 15.
  • An output resolution preset. H3 Highspeed is typically delivered as 768P on hosted endpoints.
  • An optional first-frame still image (PNG, JPG, or WEBP) that sets the opening frame. If you provide this, the video follows the image’s aspect ratio.
  • An optional last-frame still image (PNG, JPG, or WEBP) that guides the final frame. This is most useful when you also provide a first frame.
  • An optional aspect ratio setting for text-only generation. Common ratios include 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16.

Outputs

  • One MP4 video clip at the requested duration.
  • A 768P-class frame size, commonly generated at 24 fps.
  • A stereo audio track (32 kHz). It may be silent unless you prompt for sound or dialogue.

Limitations

  • Output length is limited to 4-15 seconds per run.
  • H3 Highspeed targets 768P output and isn’t meant for 2K delivery.
  • When you supply a first frame image, the output aspect ratio follows that image. Aspect ratio controls may be ignored in this mode.
  • Keyframe control is limited to the start frame, end frame, or both. It’s not full shot-by-shot editing.
  • Low-quality inputs can reduce control. Blurry images, heavy compression, text overlays, and watermarks can cause artifacts and shape drift.

Safety & compliance

  • MiniMax applies automated moderation to prompts and uploaded media.
  • Content that appears unlawful, pornographic, or rights-infringing may be blocked.
  • Don’t upload copyrighted material, private images, or likenesses without permission.

Example prompts

Great starting points for h3 highspeed.

The surfer rides through the curling wave, carving along its face as the barrel closes behind him, spray glowing in the golden sunrise light, handheld water-level camera following the motion.Video Generation
The hummingbird hovers at the hibiscus with its wings beating in a fast blur, sips nectar for a moment, then darts away out of frame while the flower sways gently, soft morning light, macro shot.Video Generation
The waterfall pours steadily into the emerald pool, mist drifting and rising through the sunbeams, ripples spreading across the water, ferns swaying gently, slow upward camera tilt toward the top of the falls.Video Generation
The skateboarder pops a clean kickflip at the edge of the bowl, the board spinning beneath him before he lands on it and rolls away, warm sunset light and long shadows, low-angle camera tracking the trick.Video Generation

API quick start

Run h3 highspeed with a single API call.

POST https://api.wiro.ai/v1/Run/minimax/h3-highspeed
{
  "prompt": "The surfer rides through the curling wave…",
  "inputImage": "https://your-cdn.com/input.png",
  "duration": 5,
  "resolution": "768P"
}
curl
curl -X POST "https://api.wiro.ai/v1/Run/minimax/h3-highspeed" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_WIRO_API_KEY" \
  --data-binary @- <<'JSON'
{
  "prompt": "The surfer rides through the curling wave…",
  "inputImage": "https://your-cdn.com/input.png",
  "duration": 5,
  "resolution": "768P"
}
JSON

Other models you might like

Explore similar video generation models.

View all
Text to Video

h3 max

minimax

Text to Video

hailuo-2.3

minimax

Text to Video

h3

minimax

Text to Video

h3 lite

minimax

  • flux-3blackforestlabs
  • kling-v2.5-turboklingai
  • gemini-omni-flashgoogle
  • seedance-v1-pro-fastbytedance
  • happyhorse 1.0alibaba
  • image-to-video-c1pixverse
  • seedance 2.5bytedance
  • seedance-pro-v1bytedance

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational
WiroModelsAgentsPricingAboutBlogCareersContactPartnerChangelogStatusFAQ
CategoriesText to ImageImage to ImageImage EditingImage to TextText to VideoImage to VideoVideo to VideoText to SpeechSpeech to TextSpeech to SpeechVoice CloneRealtime ConversationMusic GenerationLLMUtilities
ModelsNano Banana 2GPT Image 2.5Seedream V5 ProSeedance 2.5Veo 3.1Kling V3FLUX 3FLUX.2 ProWan 3.0 PrimeGrok Imagine 1.5
PartnersGoogleOpenAIByteDanceBlack Forest LabsKling AIQwenAlibabaxAIMiniMaxElevenLabs
Getting StartedWiro ModelsWiro EffectsIntroductionAuthenticationProjectsCode ExamplesWiro MCP ServerSelf-Hosted MCPn8n IntegrationLLMs.txt
API ReferenceModelsRun a ModelModel ParametersTasksLLM & Chat StreamingWebSocketRealtime VoiceFiles
© 2026 Wiro AI. All rights reserved.
PrivacyTermsData Deletion