--- title: MiniMax H3 Highspeed | Runware Docs url: https://runware.ai/docs/models/minimax-h3-highspeed description: Fast H3 video generation for everyday content, with first-to-last frame control and multimodal references --- # MiniMax H3 Highspeed ![MiniMax H3 Highspeed](https://assets.runware.ai/covers/minimax-h3-highspeed.jpg) MiniMax H3 Highspeed is a member of the MiniMax H3 family that balances generation quality and speed. 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 everyday content creation, social video and production workflows where turnaround matters. - **Status**: live - **ID**: `minimax:h3@highspeed` - 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 $0.04 from, per second · ~41s per request **Rates** - 480p · per second: `$0.04` - 768p · per second: `$0.06` - 480p · uploaded video · per second: `$0.04` - 768p · uploaded video · per second: `$0.06` - each image beyond the first fiveper input image · beyond 5: `$0.03` **4 example generations** - [text-to-video](https://runware.ai/docs/models/minimax-h3-highspeed/examples#example-industrial-flamenco-music-video-segment) · 1344×768 · 5s: `$0.30` (~33s) - [first-last-frame](https://runware.ai/docs/models/minimax-h3-highspeed/examples#example-palimpsest-documentary-title-sequence) · 480p · 8s: `$0.32` (~25s) - [first-frame](https://runware.ai/docs/models/minimax-h3-highspeed/examples#example-automatic-flood-barrier-product-demo) · 768p · 6s: `$0.36` (~1m 15s) - [reference-to-video](https://runware.ai/docs/models/minimax-h3-highspeed/examples#example-botanical-crime-series-teaser) · 1024×768 · 10s: `$0.96` (~49s) 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)` | `1792x768` | ## Request Parameters **API Options** Platform-level options for task execution and delivery. ### [taskType](https://runware.ai/docs/models/minimax-h3-highspeed#request-tasktype) - **Type**: `string` - **Required**: true - **Value**: `videoInference` Identifier for the type of task being performed. ### [taskUUID](https://runware.ai/docs/models/minimax-h3-highspeed#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-highspeed#request-outputtype) - **Type**: `string` - **Default**: `URL` Video output type. **Allowed values**: `URL` ### [outputFormat](https://runware.ai/docs/models/minimax-h3-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#request-safety) - **Path**: `safety.checkContent` - **Type**: `object (2 properties)` Content safety checking configuration for video generation. #### [checkContent](https://runware.ai/docs/models/minimax-h3-highspeed#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-highspeed#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-highspeed#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-highspeed#request-includecost) - **Type**: `boolean` Include task cost in the response. ### [numberResults](https://runware.ai/docs/models/minimax-h3-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#request-model) - **Type**: `string` - **Required**: true - **Value**: `minimax:h3@highspeed` 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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#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-highspeed#response-videouuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID of the output video. ### [videoURL](https://runware.ai/docs/models/minimax-h3-highspeed#response-videourl) - **Type**: `string` - **Format**: `uri` URL of the output video. ### [videoBase64Data](https://runware.ai/docs/models/minimax-h3-highspeed#response-videobase64data) - **Type**: `string` Base64-encoded video data. ### [videoDataURI](https://runware.ai/docs/models/minimax-h3-highspeed#response-videodatauri) - **Type**: `string` - **Format**: `uri` Data URI of the output video. ### [seed](https://runware.ai/docs/models/minimax-h3-highspeed#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-highspeed#response-nsfwcontent) - **Type**: `boolean` Flag indicating if NSFW content was detected. ### [cost](https://runware.ai/docs/models/minimax-h3-highspeed#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-highspeed/4893f77a-e508-4386-a0e9-cbd522468558.mp4) ```json { "taskType": "videoInference", "taskUUID": "9e4b56e6-ae2c-41e5-8d17-d39b05973274", "model": "minimax:h3@highspeed", "positivePrompt": "A cinematic five-second music-video segment for an electro-flamenco single, filmed as one continuous shot inside a vast working ceramic tile factory at night. A charismatic male flamenco dancer in a fitted black work jacket, high-waisted trousers and heavy leather dance boots performs in the center aisle between tall racks of glossy cobalt-blue tiles. He drives forward with two forceful heel stamps, snaps his arms outward, then executes a fast controlled spin as his jacket hem flares. Each stamp kicks pale clay dust across the concrete floor. Nearby suspended tiles sway and flash reflections; conveyor chains move in the background; kiln vents release rolling white steam; loose translucent packing sheets ripple in the hot airflow. The camera begins inches above the floor close to his boots, rapidly dollies backward with his advance, then rises into a tight semicircular orbit during the spin, maintaining crisp focus on his face and torso. Ember-orange kiln light pulses through the cobalt racks, creating a bold blue-and-orange palette with hard highlights, deep shadows and streaking reflections. Energetic, percussive, tactile, fashion-forward realism; expressive physical performance, believable factory scale, controlled motion blur, subtle handheld vibration, anamorphic cinematic lighting. Landscape composition with the dancer dominant in the central third and strong converging factory lines. No cuts, no slow motion, no lettering, no subtitles, no logos, no audience.", "width": 1344, "height": 768, "duration": 5 } ``` --- ### first-frame (first-frame) [Watch video](https://assets.runware.ai/examples/minimax-h3-highspeed/d8ef0e3b-c2fc-4d34-add3-1a1cfa6f7589.mp4) ```json { "taskType": "videoInference", "taskUUID": "f0b494e4-a4fb-44f5-99ea-4a691826b760", "model": "minimax:h3@highspeed", "positivePrompt": "Continue naturally and continuously from the supplied opening image as a clear physical product demonstration. Keep the apparatus, materials, proportions and workshop unchanged. The reservoir gate on the left lifts smoothly and cyan-tinted water surges through the transparent flume toward the lowered orange flood barrier. As water enters the stainless threshold channel, buoyancy raises the barrier in one convincing mechanical motion along its side rails until it locks upright. Water then piles against the raised barrier with realistic ripples and small splashes while the downstream section remains visibly dry. End on the barrier securely holding back the water. Preserve believable fluid dynamics, gravity, reflections through the acrylic and rigid engineering geometry. Use a subtle slow camera push toward the mechanism while retaining the full water path in frame. Premium photoreal industrial explainer style, crisp daylight, brushed metal, clear acrylic, cyan water and safety orange accents. One uninterrupted shot, no cuts, no exploded view, no added components, no people, no captions, no interface, no logos.", "resolution": "768p", "duration": 6, "inputs": { "frameImages": [ { "image": "https://assets.runware.ai/assets/inputs/d707853c-e340-4367-a1f9-59bbc6bd3e76.jpg", "frame": "first" } ] } } ``` --- ### first-last-frame (first-last-frame) [Watch video](https://assets.runware.ai/examples/minimax-h3-highspeed/b74a21dc-b837-4e5e-a908-6fce095894df.mp4) ```json { "taskType": "videoInference", "taskUUID": "66050ca4-ab6c-495c-b8cf-a7cd7e17d15d", "model": "minimax:h3@highspeed", "positivePrompt": "Create a seamless eight-second museum-documentary title reveal connecting the supplied first and last frames in one continuous overhead macro shot. Keep the vellum folio, table, page edges and camera axis spatially locked. Begin in near darkness with only faint ultraviolet-blue grazing light and barely legible erased marks. The camera makes an extremely slow, controlled push toward the manuscript as a narrow multispectral scanning band travels smoothly from left to right across the page. Behind the moving band, hidden crimson and blue undertext gradually emerges from within the parchment fibers, tiny gold-leaf fragments catch warm light, and subtle dust motes drift above the surface. The transformation must feel like authentic conservation imaging rather than magic: progressive spectral fluorescence, delicate changes in wavelength and realistic material response. As the scan completes, illumination settles into a rich cobalt-and-oxidized-gold final composition and the title PALIMPSEST resolves cleanly in the central negative space, matching the supplied last frame. Solemn, intelligent prestige-documentary mood; elegant restrained motion, photoreal vellum texture, no cuts, no hands, no page movement, no camera shake, no extra objects, no additional words, no flicker or warped lettering.", "resolution": "480p", "duration": 8, "inputs": { "frameImages": [ { "image": "https://assets.runware.ai/assets/inputs/97704e94-471b-4e68-848c-21e2d355b9ef.jpg", "frame": "first" }, { "image": "https://assets.runware.ai/assets/inputs/f9e04ffb-a0d9-444e-93de-e65096249255.jpg", "frame": "last" } ] } } ``` --- ### reference-to-video (reference-to-video) [Watch video](https://assets.runware.ai/examples/minimax-h3-highspeed/39ce4ab9-042c-4b3d-b05b-f712c080091d.mp4) ```json { "taskType": "videoInference", "taskUUID": "1c437c05-66e3-4e48-82a6-b54ab90b87f7", "model": "minimax:h3@highspeed", "positivePrompt": "Create a finished 10-second cinematic title teaser for a prestige investigative limited series about the international trafficking of rare orchids. Landscape 4:3 composition with sophisticated botanical-noir art direction: ultraviolet black, toxic chartreuse, bruised violet, cold white highlights, forensic precision, elegant menace.\n\nUse as the exact visual identity of the central specimen: preserve its distinctive silhouette, petal geometry, translucency, tendril structure, and pale coloration throughout the sequence. Use