Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
No video yet. Submit the form to generate video.
Explore different use cases and parameter configurations
Transparent pricing with no hidden fees. Pay as you go.
| Rule & Modality | Channel | Credits | Price (USD) | Official / Reference Price | Daily Savings |
|---|---|---|---|---|---|
hailuo-768p-6s videoMiniMaxduration: 6, resolution: 768p | Starter | 3per video | $0.014 | - | - |
hailuo-768p-10s videoMiniMaxduration: 10, resolution: 768p | Starter | 5per video | $0.023 | - | - |
hailuo-1080p-6s videoMiniMaxduration: 6, resolution: 1080p | Starter | 5per video | $0.023 | - | - |
hailuo-1080p-10s videoMiniMaxduration: 10, resolution: 1080p | Starter | 5per video | $0.023 | - | - |
Complete guide to using hailuo v2.3
Generate high-quality AI videos from text prompts or images with MiniMax's Hailuo 2.3 model. Support for both 6s and 10s durations, 768p and 1080p resolutions, with intelligent prompt optimization.
MiniMax Hailuo 2.3 is an advanced AI video generation model that creates realistic, high-quality videos from text descriptions or combines text prompts with image inputs for image-to-video generation. The model supports flexible configuration with multiple duration and resolution options, and includes an intelligent prompt optimizer that enhances user input for superior results. The Hailuo 2.3 API makes this powerful capability accessible through a programmatic interface, enabling developers to integrate professional-grade video generation into their applications and workflows with minimal effort.
The 768p resolution mode offers maximum flexibility, supporting both 6-second and 10-second video generation. This mode is ideal for creating longer content sequences, social media videos, and applications where extended duration is more important than maximum resolution. The 768p output delivers excellent quality while maintaining efficient processing and resource usage.
The 1080p resolution mode provides the highest visual quality available in Hailuo 2.3, delivering crisp, detailed video output suitable for professional applications. This mode is limited to 6-second duration but excels in scenarios requiring maximum visual fidelity, such as promotional content, product showcases, and high-end creative projects.
The Hailuo 2.3 API transforms text descriptions into dynamic video content with remarkable realism and coherence. Simply provide a detailed prompt, and the model generates video that matches your description, maintaining visual consistency and natural motion throughout the sequence.
With Hailuo 2.3's first frame image feature, developers can combine a reference image with text prompts to create controlled video generation. The model animates the provided image according to your text description, enabling precise creative control over the starting point of the video sequence.
The built-in prompt optimizer automatically enhances user input to produce better results. When enabled, the system refines and expands your prompt with additional details and technical considerations, improving video quality and coherence without requiring expert prompt engineering skills.
Hailuo 2.3 API offers configurable duration (6s or 10s) and resolution (768p or 1080p) options, allowing developers to balance between video length and visual quality based on specific use case requirements. The intelligent constraint system ensures valid parameter combinations automatically.
Get started with Hailuo 2.3 video generation in just a few simple steps...
Create an account on apipass.dev and obtain your MiniMax Hailuo 2.3 API Key. This key authenticates all your requests and links video generation usage to your account for tracking and billing purposes.
Before integrating the API, use the interactive playground to experiment with Hailuo 2.3's capabilities. Test different prompts, durations, resolutions, and image inputs to understand the model's behavior and find optimal settings for your use case.
Implement the Hailuo 2.3 API in your backend or application logic. Define how prompts, images, duration, and resolution parameters are passed through API requests. Configure callback URLs for asynchronous generation tracking.
Deploy your integration to production, handling asynchronous video generation jobs, monitoring task status, and managing generated video outputs. Implement proper error handling and status tracking for a robust production system.
10-second duration is only available with 768p resolution. 1080p resolution is limited to 6-second duration. The API automatically enforces these constraints and will adjust parameters if invalid combinations are provided.
The prompt optimizer is enabled by default and strongly recommended for best results. It enhances your input prompts with technical details and refinements that improve video quality, coherence, and adherence to your description.
The first_frame_image parameter is optional. When provided, it enables image-to-video generation mode, where the model animates the image according to your text prompt. When omitted, the model performs pure text-to-video generation.
Generate engaging short-form video content for social media platforms. The flexible duration options (6s-10s) are perfectly suited for Instagram stories, TikTok clips, and other social video formats, while the prompt optimizer ensures professional-quality results.
Transform product images into dynamic video presentations using image-to-video mode. Combine product photos with descriptive prompts to create compelling promotional videos, product demos, and marketing materials with minimal manual effort.
Enable creators to rapidly prototype video concepts and bring text-based story ideas to life. The text-to-video capability accelerates creative workflows, allowing writers and designers to visualize scenes and concepts quickly.
Integrate Hailuo 2.3 into automated content generation systems for news visualization, educational content, or mass video production workflows. The API's programmatic interface enables scalable video generation without manual intervention.
apipass.dev offers competitive pricing for MiniMax Hailuo 2.3 API access, with transparent usage-based billing that scales with your needs. No hidden fees or unexpected costs, making professional AI video generation accessible for projects of all sizes.
Clear, detailed API documentation with code examples, parameter explanations, and integration guides helps developers implement Hailuo 2.3 quickly and correctly. Complete coverage of all features including constraint handling and optimization options.
Round-the-clock technical support ensures your video generation workflows stay operational. Expert assistance is available whenever you need help with integration, troubleshooting, or optimization of your Hailuo 2.3 implementation.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Create a new Hailuo 2.3 video generation task
The API accepts a JSON payload with the following structure:
1{
2 "model": "minimax/hailuo-2-3",
3 "callBackUrl": "string (optional)",
4 "channel": "auto",
5 "input": {
6 "prompt": "string (required)",
7 "duration": 6 or 10 (optional, default: 6),
8 "resolution": "768p" or "1080p" (optional, default: "768p"),
9 "prompt_optimizer": boolean (optional, default: true),
10 "first_frame_image": "string URL (optional)"
11 }
12}modelRequiredstringThe model name to use for video generation
"minimax/hailuo-2-3"
callBackUrlOptionalstringOptional callback URL for task completion notifications
"https://your-domain.com/api/callback"
channelOptionalstringYou may specify the corresponding provider within APIPASS via the channel parameter; these providers handle the actual image and video generation tasks. APIPASS currently offers three provider options:
The default value for the channel parameter is auto. When enabled, APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics to balance minimal cost and reliable performance. Retain the default auto value unless you have custom routing requirements.
Available options:
auto
The input object contains the following parameters based on the model configuration:
input.promptRequiredstringText prompt describing the video you want to generate. Maximum length is 2500 characters.
Required field, max length: 2500 characters
"A serene lake surrounded by mountains at sunset, with reflections on the water"
input.durationOptionalintegerVideo duration in seconds. Must be 6 or 10. Note: 10 seconds is only available for 768p resolution. Default is 6.
Optional, valid values: 6 or 10 (10s only for 768p)
Available options:
6
input.resolutionOptionalstringVideo resolution. Must be '768p' or '1080p'. Note: 1080p is only available for 6 second duration. Default is '768p'.
Optional, valid values: '768p' or '1080p' (1080p only for 6s)
Available options:
"768p"
input.prompt_optimizerOptionalbooleanEnable prompt optimizer to enhance and refine your prompt for better results. Default is true.
Optional, recommended to keep enabled
true
input.first_frame_imageOptionalstring (URL)Optional URL of a first frame image for image-to-video generation. When provided, the model will animate this image according to the prompt.
Optional, provide image URL for image-to-video mode
"https://example.com/image.jpg"
1curl -X POST "https://api.apipass.dev/api/v1/jobs/createTask" \
2 -H "Content-Type: application/json" \
3 -H "Authorization: Bearer YOUR_API_KEY" \
4 -d '{
5 "model": "minimax/hailuo-2-3",
6 "callBackUrl": "https://your-domain.com/api/callback",
7 "input": {
8 "prompt": "A serene lake surrounded by mountains at sunset, with reflections on the water",
9 "duration": 6,
10 "resolution": "1080p",
11 "prompt_optimizer": true
12 }
13 }'1{
2 "code": 200,
3 "message": "success",
4 "data": {
5 "taskId": "task_12345678"
6 }
7}codeStatus code, 200 for success, others for failure
messageResponse message, error description when failed
data.taskIdTask ID for querying task status and retrieving results
ByteDance
ByteDance
Starting from
0 credits
ByteDance
ByteDance
Starting from
0 credits
ByteDance
ByteDance
Turn text, images, video clips, and audio into cinematic, audio-synced videos with a single API call.
Starting from
0 credits
MiniMax
MiniMax
Starting from
0 credits
ByteDance
ByteDance
Generate cinematic 4K AI videos up to 30 seconds with Seedance 2.5's multimodal power.
Starting from
0 credits
Google Veo 3.1 is the latest state-of-the-art generative video model designed to transform text and image prompts into high-fidelity cinematic visuals. Building upon its predecessors, Veo 3.1 features significant upgrades in prompt adherence, visual realism, and native audio generation, creating 8-second clips with synchronized sound effects and dialogue.
Starting from
0 credits
wan
wan
Starting from
0 credits
Runway
Runway
Starting from
0 credits
Kling
Kling
Transform text prompts and images into high-quality videos with advanced AI. Generate cinematic content with customizable duration, aspect ratio, and audio capabilities.
Starting from
0 credits
grok
grok
Grok Imagine is xAI’s AI video generation model for creating high-quality videos with realistic motion, native audio, and synchronized speech. Grok Imagine 1.5 introduces faster generation speeds, improved motion physics, and stronger visual consistency for modern AI video applications.
Starting from
0 credits
Luma
Luma
Starting from
0 credits
Kling
Kling
Kling v3 video generation model, supports text-to-video and image-to-video, up to 15 seconds, 1080p pro mode
Starting from
0 credits
wan
wan
Generate videos with cinematic consistency by reimagining existing footage through high-fidelity visual transformation and structural control.
Starting from
0 credits
Starting from
0 credits
grok
grok
Starting from
0 credits
kling
kling
Starting from
0 credits