--- title: MiniMax H3 Lite | Runware Docs url: https://runware.ai/docs/models/minimax-h3-lite description: Lightweight H3 video generation for previews, drafts and batch variations, with frame and reference control --- # MiniMax H3 Lite ![MiniMax H3 Lite](https://assets.runware.ai/covers/minimax-h3-lite.jpg) MiniMax H3 Lite is the lightweight member of the MiniMax H3 family, built for quick, low-cost iteration. It generates 4 to 15 second videos at 480p or 768p from text, from a first frame or a first and last frame pair, or from reference images, videos and audio. It is well suited to concept previews, creative drafts and batch variations that explore a direction before a final render. - **Status**: live - **ID**: `minimax:h3@lite` - Try in Playground - **Creator**: MiniMax - **Release Date**: October 30, 2026 - **Capabilities**: Text to Video, Image to Video, Video to Video, Audio to Video, Checkpoint, Audio ## Pricing $0.025 from, per second · ~41s per request **Rates** - 480p · per second: `$0.025` - 768p · per second: `$0.04` - 480p · uploaded video · per second: `$0.025` - 768p · uploaded video · per second: `$0.04` - each image beyond the first fiveper input image · beyond 5: `$0.02` **4 example generations** - [text-to-video](https://runware.ai/docs/models/minimax-h3-lite/examples#example-subsea-cable-documentary-title-teaser) · 1344×768 · 5s: `$0.20` (~23s) - [first-frame](https://runware.ai/docs/models/minimax-h3-lite/examples#example-seed-vault-curator-presenter-clip) · 768p · 6s: `$0.24` (~35s) - [first-last-frame](https://runware.ai/docs/models/minimax-h3-lite/examples#example-apiary-thriller-title-sequence) · 768p · 8s: `$0.32` (~46s) - [reference-to-video](https://runware.ai/docs/models/minimax-h3-lite/examples#example-satellite-risk-analyst-briefing-clip) · 480p · 8s: `$0.35` (~1m 9s) times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing) ## Compatibility & Validation Inside `inputs`, `frameImages` cannot be used with `referenceImages`, `referenceVideos`, or `referenceAudios`. --- When `inputs.frameImages` is provided, `width/height` cannot be used. --- When `inputs.referenceAudios` is provided, `inputs.referenceImages` or `inputs.referenceVideos` is required. --- When `resolution` is provided, `inputs.frameImages` is required. --- `width` and `height` must be used together. --- The following dimension combinations are supported: | Configuration | Dimensions | | --- | --- | | `480p (~16:9)` | `864x480` | | `480p (4:3)` | `640x480` | | `480p (1:1)` | `480x480` | | `480p (3:4)` | `480x640` | | `480p (~9:16)` | `480x864` | | `480p (21:9)` | `1120x480` | | `768p (~16:9)` | `1344x768` | | `768p (4:3)` | `1024x768` | | `768p (1:1)` | `768x768` | | `768p (3:4)` | `768x1024` | | `768p (~9:16)` | `768x1344` | | `768p (~21:9)` | `1536x672` | ## Request Parameters **API Options** Platform-level options for task execution and delivery. ### [taskType](https://runware.ai/docs/models/minimax-h3-lite#request-tasktype) - **Type**: `string` - **Required**: true - **Value**: `videoInference` Identifier for the type of task being performed. ### [taskUUID](https://runware.ai/docs/models/minimax-h3-lite#request-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task. ### [outputType](https://runware.ai/docs/models/minimax-h3-lite#request-outputtype) - **Type**: `string` - **Default**: `URL` Video output type. **Allowed values**: `URL` ### [outputFormat](https://runware.ai/docs/models/minimax-h3-lite#request-outputformat) - **Type**: `string` - **Default**: `MP4` Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities. - \`MP4\`: Widely supported video container (H.264), recommended for general use. - \`WEBM\`: Optimized for web delivery. - \`MOV\`: QuickTime format, common in professional workflows (Apple ecosystem). **Allowed values**: `MP4` `WEBM` `MOV` ### [outputQuality](https://runware.ai/docs/models/minimax-h3-lite#request-outputquality) - **Type**: `integer` - **Min**: `20` - **Max**: `99` - **Default**: `95` Compression quality of the output. Higher values preserve quality but increase file size. ### [webhookURL](https://runware.ai/docs/models/minimax-h3-lite#request-webhookurl) - **Type**: `string` - **Format**: `uri` Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available. **Learn more** (1 resource): - [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform) ### [deliveryMethod](https://runware.ai/docs/models/minimax-h3-lite#request-deliverymethod) - **Type**: `string` - **Default**: `async` Determines how the API delivers task results. **Allowed values**: - `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse. - `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. **Learn more** (1 resource): - [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform) ### [uploadEndpoint](https://runware.ai/docs/models/minimax-h3-lite#request-uploadendpoint) - **Type**: `string` - **Format**: `uri` Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials. **Common use cases:** - **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs. - **CDN integration**: Upload to content delivery networks for immediate distribution. ```text // S3 presigned URL for secure upload https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600 // Google Cloud Storage presigned URL https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789 // Custom storage endpoint https://storage.example.com/uploads/generated-image.jpg ``` The content data will be sent as the request body to the specified URL when generation is complete. ### [safety](https://runware.ai/docs/models/minimax-h3-lite#request-safety) - **Path**: `safety.checkContent` - **Type**: `object (2 properties)` Content safety checking configuration for video generation. #### [checkContent](https://runware.ai/docs/models/minimax-h3-lite#request-safety-checkcontent) - **Path**: `safety.checkContent` - **Type**: `boolean` Enable or disable content safety checking. Increases total generation time. #### [mode](https://runware.ai/docs/models/minimax-h3-lite#request-safety-mode) - **Path**: `safety.mode` - **Type**: `string` - **Default**: `fast` Safety checking mode for video generation. **Allowed values**: - `fast` Checks key frames. - `full` Checks all frames. ### [ttl](https://runware.ai/docs/models/minimax-h3-lite#request-ttl) - **Type**: `integer` - **Min**: `60` Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`. ### [includeCost](https://runware.ai/docs/models/minimax-h3-lite#request-includecost) - **Type**: `boolean` Include task cost in the response. ### [numberResults](https://runware.ai/docs/models/minimax-h3-lite#request-numberresults) - **Type**: `integer` - **Min**: `1` - **Max**: `4` - **Default**: `1` Number of results to generate. Each result uses a different seed, producing variations of the same parameters. ### [routing](https://runware.ai/docs/models/minimax-h3-lite#request-routing) - **Path**: `routing.allowedModels` - **Type**: `object (8 properties)` Model router options. Only read when `model` is `auto`, and never sent to the model. #### [allowedModels](https://runware.ai/docs/models/minimax-h3-lite#request-routing-allowedmodels) - **Path**: `routing.allowedModels` - **Type**: `array of strings` - **Min items**: `2` Models the router may choose from. Nothing outside this list is considered, so a request none of them can serve is refused. #### [excludedModels](https://runware.ai/docs/models/minimax-h3-lite#request-routing-excludedmodels) - **Path**: `routing.excludedModels` - **Type**: `array of strings` - **Min items**: `1` Models the router may not choose. Every other model stays a candidate. #### [preferences](https://runware.ai/docs/models/minimax-h3-lite#request-routing-preferences) - **Path**: `routing.preferences` - **Type**: `object (3 properties)` Relative importance of each dimension when models are compared. Weights, not thresholds. ##### [quality](https://runware.ai/docs/models/minimax-h3-lite#request-routing-preferences-quality) - **Path**: `routing.preferences.quality` - **Type**: `integer` - **Min**: `0` - **Max**: `5` Importance of one dimension. `0` leaves it out of the decision. ##### [speed](https://runware.ai/docs/models/minimax-h3-lite#request-routing-preferences-speed) - **Path**: `routing.preferences.speed` - **Type**: `integer` - **Min**: `0` - **Max**: `5` Importance of one dimension. `0` leaves it out of the decision. ##### [cost](https://runware.ai/docs/models/minimax-h3-lite#request-routing-preferences-cost) - **Path**: `routing.preferences.cost` - **Type**: `integer` - **Min**: `0` - **Max**: `5` Importance of one dimension. `0` leaves it out of the decision. #### [maxPrice](https://runware.ai/docs/models/minimax-h3-lite#request-routing-maxprice) - **Path**: `routing.maxPrice` - **Type**: `float` - **Min**: `0` Upper bound on what this request may cost, in USD. A model whose cost cannot be bounded is not chosen. #### [requirements](https://runware.ai/docs/models/minimax-h3-lite#request-routing-requirements) - **Path**: `routing.requirements` - **Type**: `string` - **Max**: `3000` Conditions the result has to meet, in plain words, such as a style or a feature. A model that cannot meet them is not chosen. Output size is set with width and height rather than described here. **Inputs** Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object. ### [referenceImages](https://runware.ai/docs/models/minimax-h3-lite#request-inputs-referenceimages) - **Path**: `inputs.referenceImages` - **Type**: `array of strings` - **Min items**: `1` - **Max items**: `9` - **Size (each)**: `256 px to 5760 px` - **Aspect ratio (each)**: `1:2.5 to 2.5:1` - **File size (each)**: `up to 30 MB` List of reference images (UUID, URL, Data URI, or Base64). ### [frameImages](https://runware.ai/docs/models/minimax-h3-lite#request-inputs-frameimages) - **Path**: `inputs.frameImages` - **Type**: `array of strings or objects` - **Min items**: `1` - **Max items**: `2` - **Size (each)**: `256 px to 5760 px` - **Aspect ratio (each)**: `1:2.5 to 2.5:1` - **File size (each)**: `up to 30 MB` An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target position in the video. The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions. When the `frame` parameter is omitted, automatic distribution rules apply: - **1 image**: Used as the first frame. - **2 images**: First and last frames. **Examples**: **Shorthand format:** When you don't need to specify a frame position, you can pass a plain image input directly. ```json "frameImages": [ "aac49721-1964-481a-ae78-8a4e29b91402" ] ``` **Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent). ```json "frameImages": [ { "image": "aac49721-1964-481a-ae78-8a4e29b91402", "frame": "first" } ] ``` **First and last frames:** With two images, they automatically become the first and last frames of the video sequence. You can mix shorthand and object formats. ```json "frameImages": [ "aac49721-1964-481a-ae78-8a4e29b91402", { "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe", "frame": "last" } ] ``` **Format 1: string[]**: - **Type**: `string` Image input (UUID, URL, Data URI, or Base64). **Format 2: object[]**: #### [image](https://runware.ai/docs/models/minimax-h3-lite#request-inputs-frameimages-format-2-image) - **Path**: `inputs.frameImages.image` - **Type**: `string` - **Required**: true Image input (UUID, URL, Data URI, or Base64). #### [frame](https://runware.ai/docs/models/minimax-h3-lite#request-inputs-frameimages-format-2-frame) - **Path**: `inputs.frameImages.frame` - **Type**: `object` Target frame position for the image. Supports first and last frame. **Allowed values**: - `first` First frame of the video. - `last` Last frame of the video. - `0` Frame index 0 (first frame). - `-1` Frame index -1 (last frame). ### [referenceVideos](https://runware.ai/docs/models/minimax-h3-lite#request-inputs-referencevideos) - **Path**: `inputs.referenceVideos` - **Type**: `array of strings` - **Min items**: `1` - **Max items**: `3` - **Size (each)**: `256 px to 5760 px` - **Aspect ratio (each)**: `1:2.5 to 2.5:1` - **Frame rate (each)**: `23.98 fps to 60 fps` - **Duration (each)**: `2s to 15s` - **Duration (total)**: `up to 15s` - **File size (each)**: `up to 50 MB` List of reference videos (UUID or URL). ### [referenceAudios](https://runware.ai/docs/models/minimax-h3-lite#request-inputs-referenceaudios) - **Path**: `inputs.referenceAudios` - **Type**: `array of strings` - **Min items**: `1` - **Max items**: `3` - **Duration (each)**: `2s to 15s` - **Duration (total)**: `up to 15s` - **File size (each)**: `up to 15 MB` List of reference audios (UUID or URL). **Core Parameters** Primary parameters that define the task output. ### [model](https://runware.ai/docs/models/minimax-h3-lite#request-model) - **Type**: `string` - **Required**: true - **Value**: `minimax:h3@lite` Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router). **Learn more** (3 resources): - [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn) - [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn) - [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn) ### [positivePrompt](https://runware.ai/docs/models/minimax-h3-lite#request-positiveprompt) - **Type**: `string` - **Required**: true - **Min**: `2` - **Max**: `7000` Text prompt describing elements to include in the generated output. **Learn more** (1 resource): - [Prompts](https://runware.ai/docs/learn/prompts) (learn) ### [width](https://runware.ai/docs/models/minimax-h3-lite#request-width) - **Type**: `integer` - **Default**: `864` - **Paired with**: height Width of the generated media in pixels. **Learn more** (2 resources): - [Dimensions](https://runware.ai/docs/learn/dimensions) (learn) - [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn) ### [height](https://runware.ai/docs/models/minimax-h3-lite#request-height) - **Type**: `integer` - **Default**: `480` - **Paired with**: width Height of the generated media in pixels. **Learn more** (2 resources): - [Dimensions](https://runware.ai/docs/learn/dimensions) (learn) - [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn) ### [resolution](https://runware.ai/docs/models/minimax-h3-lite#request-resolution) - **Type**: `string` Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input. **Allowed values**: `480p` `768p` ### [duration](https://runware.ai/docs/models/minimax-h3-lite#request-duration) - **Type**: `integer` - **Min**: `4` - **Max**: `15` - **Default**: `5` Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps). ### [seed](https://runware.ai/docs/models/minimax-h3-lite#request-seed) - **Type**: `integer` - **Min**: `0` - **Max**: `4294967295` Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range. ## Response Parameters ### [taskType](https://runware.ai/docs/models/minimax-h3-lite#response-tasktype) - **Type**: `string` - **Required**: true - **Value**: `videoInference` Identifier for the type of task this response belongs to. ### [taskUUID](https://runware.ai/docs/models/minimax-h3-lite#response-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier echoed from the original request, used to match async responses to their tasks. ### [videoUUID](https://runware.ai/docs/models/minimax-h3-lite#response-videouuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID of the output video. ### [videoURL](https://runware.ai/docs/models/minimax-h3-lite#response-videourl) - **Type**: `string` - **Format**: `uri` URL of the output video. ### [videoBase64Data](https://runware.ai/docs/models/minimax-h3-lite#response-videobase64data) - **Type**: `string` Base64-encoded video data. ### [videoDataURI](https://runware.ai/docs/models/minimax-h3-lite#response-videodatauri) - **Type**: `string` - **Format**: `uri` Data URI of the output video. ### [seed](https://runware.ai/docs/models/minimax-h3-lite#response-seed) - **Type**: `integer` The seed used for generation. If none was provided, shows the randomly generated seed. ### [NSFWContent](https://runware.ai/docs/models/minimax-h3-lite#response-nsfwcontent) - **Type**: `boolean` Flag indicating if NSFW content was detected. ### [cost](https://runware.ai/docs/models/minimax-h3-lite#response-cost) - **Type**: `float` Task cost in USD. Present when `includeCost` is set to `true` in the request. ## Examples ### text-to-video (text-to-video) [Watch video](https://assets.runware.ai/examples/minimax-h3-lite/a539d67e-95b6-4c95-a600-bb07060e48fc.mp4) ```json { "taskType": "videoInference", "taskUUID": "b3604099-d249-42eb-97da-2cd2e41ad8ec", "model": "minimax:h3@lite", "positivePrompt": "Create a polished five-second cinematic title teaser for a premium investigative documentary about subsea fiber-optic cable repair. One continuous shot in a cold, pitch-dark ocean trench, rendered with grounded photorealism and the visual precision of a high-end natural-history production. Begin in extreme macro on a severed fiber-optic cable resting in black silt; hair-thin glass fibers emit faint pulses of cyan light beneath a torn steel sheath while suspended particles drift through a narrow amber work lamp. The camera slowly pulls backward and rises, revealing the articulated claws and floodlights of a large industrial repair ROV hovering above the cable. Its thrusters disturb the seabed, sending a controlled cloud of sediment curling past the lens. A distant repair ship is visible only as a wavering constellation of work lights far overhead. As the camera reaches a wide composition, the cyan pulses travel along the cable and align into clean, restrained uppercase lettering in the dark water: “THE SILENT NETWORK”. The title should resolve clearly at center frame during the final two seconds and remain stable and legible through the end, elegant condensed sans-serif typography, pale cyan-white, subtle optical glow, no other words, logos, captions, borders, or interface elements. Palette of abyssal navy, graphite black, cold cyan, and sparse industrial amber. Slow deliberate camera motion, realistic underwater physics, volumetric light shafts, immense scale, ominous but intelligent mood, crisp cinematic contrast, anamorphic character, fine film grain.", "width": 1344, "height": 768, "duration": 5 } ``` --- ### first-frame (first-frame) [Watch video](https://assets.runware.ai/examples/minimax-h3-lite/fbb84db9-3fa1-4649-9438-6b42dc783ea5.mp4) ```json { "taskType": "videoInference", "taskUUID": "31617dde-7d9f-429f-bbc1-9c371bc764a7", "model": "minimax:h3@lite", "positivePrompt": "Continue naturally from the supplied opening frame as a polished vertical talking-head museum explainer. The seed-vault curator maintains direct eye contact and delivers one concise sentence to camera: “These seeds are backup copies of crops, protected here for whatever the future brings.” Create believable speech articulation with natural lip, jaw and cheek movement. She gives one small open-palm gesture toward the archive shelves, then returns her hand to a relaxed position. Add subtle blinking, breathing and a slight reassuring nod at the end. Preserve her identity, coral jacket, realistic proportions, archive layout, frost detail and cool cyan lighting throughout. Camera remains steady in the same waist-up composition with only a very gentle documentary-style push-in. The background stays quiet and stable; no other people enter. Calm, intelligent, quietly hopeful mood. Photorealistic motion, restrained professional performance, no cuts, no captions, no graphics, no logos, no camera shake, no exaggerated gestures.", "resolution": "768p", "duration": 6, "inputs": { "frameImages": [ { "image": "https://assets.runware.ai/assets/inputs/5d2d32f4-419f-444c-bb30-98dc12be5049.jpg", "frame": "first" } ] } } ``` --- ### first-last-frame (first-last-frame) [Watch video](https://assets.runware.ai/examples/minimax-h3-lite/b908251c-5274-4259-866b-507d0b6f83d4.mp4) ```json { "taskType": "videoInference", "taskUUID": "18276475-0b1c-4eec-8478-b572b251b243", "model": "minimax:h3@lite", "positivePrompt": "Create an eight-second prestige television title teaser as one plausible, continuous macro shot transitioning exactly between the supplied first and last frames. Hold the perfectly frontal, symmetrical view of the same wooden honeycomb frame inside a dark commercial apiary. Begin in near stillness: amber honey catches the narrow tungsten inspection light while worker bees make small anatomically natural movements across the wax cells and the queen remains near center. A low wave of motion gradually travels through the colony; bees crawl outward in coordinated but realistic paths, antennae and wings moving subtly, never swarming toward the camera. Honey slowly wells into several central cells and produces warm liquid highlights. Add an almost imperceptible camera push-in with stable geometry and no cuts, angle changes or sudden transformations. During the final two seconds, the cleared central area settles and the exact ivory title THE QUEEN'S SHARE gently resolves over the comb, with A LIMITED SERIES above it, matching the final guide precisely. Finish on a composed, fully legible title card while a few bees continue restrained peripheral motion. Photorealistic practical macro cinematography, rich amber, tobacco brown, ivory and deep black palette, controlled highlights, shallow depth of field, subtle 35mm grain, ominous and sophisticated rather than horror. Preserve continuity of the hive frame, bees, lighting and lens throughout. No extra text, credits, logos, cuts, flicker, camera shake, malformed insects or fantasy imagery.", "resolution": "768p", "duration": 8, "inputs": { "frameImages": [ { "image": "https://assets.runware.ai/assets/inputs/717ea533-914f-46cd-881c-8d41cd1be964.jpg", "frame": "first" }, { "image": "https://assets.runware.ai/assets/inputs/6c457862-565d-49fb-95d6-b498bc0b11fb.jpg", "frame": "last" } ] } } ``` --- ### reference-to-video (reference-to-video) [Watch video](https://assets.runware.ai/examples/minimax-h3-lite/d80fc094-5b86-4430-88a7-aa87344d13f7.mp4) ```json { "taskType": "videoInference", "taskUUID": "2cf8b11d-2fb2-4c8f-b7c7-ca4e0a90124c", "model": "minimax:h3@lite", "positivePrompt": "Create a premium widescreen talking-head briefing for the commercial satellite insurance industry. Use as the exact identity, facial appearance, hair, and wardrobe reference for the on-camera analyst. Use