MiniMax
This page is auto-generated from model configurations. Last updated: 2026-10-09.
This reference lists all available MiniMax video generation models and their parameters. Use these parameter names when calling the Generation API.
- Minimax 01 Director
- Minimax H3
- Minimax H3 Max Extend Video
- Minimax H3 Max I2V
- Minimax H3 Max Insert Video
- Minimax H3 Max Lip Sync
- Minimax H3 Max Recast
- MiniMax H3 Max Reference to Video
- Minimax H3 Max T2V
- Minimax H3 Max Turbo Extend Video
- Minimax H3 Max Turbo I2V
- Minimax H3 Max Turbo T2V
- Minimax Hailuo 02
- Minimax Hailuo 2.3
- Minimax Hailuo 2.3 Fast
- Minimax Video 01
Minimax 01 Director
Section titled “Minimax 01 Director”A cinematography model offering advanced camera control for cinematic storytelling and professional framing.
Model ID: model_minimax-video-01-director
Capabilities: txt2video, img2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-video-01-director/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe your video. Try Prompt Spark or check our Help Center for detailed prompt tips for this model. |
firstFrameImage |
file | No | - | - | - | - | Image used as the first frame of the video. |
promptOptimizer |
boolean | No | true |
- | - | - | Use prompt optimizer |
Minimax H3
Section titled “Minimax H3”MiniMax H3 2K / 24 fps video generation with native stereo audio: text, first/last frame, or multimodal references (images, videos, optional audio).
Model ID: model_minimax-h3
Capabilities: txt2video, img2video, video2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-h3/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe the video you want. |
firstFrameImage |
file | No | - | - | - | - | An image to use as the video’s opening frame. The video’s shape follows this image. Can’t be combined with reference images, videos, or audio. |
lastFrameImage |
file | No | - | - | - | - | An image to use as the video’s closing frame. Only works when a first frame is also set. Can’t be combined with reference images, videos, or audio. |
referenceImages |
file_array | No | - | - | - | - | Images to guide the subjects or style (up to 9, max 30 MB each). Can’t be combined with a first or last frame. First 5 are free; additional images are billed. |
referenceVideos |
file_array | No | - | - | - | - | Videos to guide the motion (up to 3, each 2–15s and 2–15s in total, max 50 MB each). Can’t be combined with a first or last frame. Billed per second of uploaded duration. |
referenceAudio |
file_array | No | - | - | - | - | Audio to guide the video (up to 3, each 2–15s and 2–15s in total, max 15 MB each). Requires at least one reference image or video. |
duration |
number | No | 5 |
5 | 15 | - | How long the video lasts, in seconds (5-15). Longer videos cost more. |
resolution |
string | No | 2K |
- | - | 768P, 2K |
The output quality. Higher resolutions cost more. |
aspectRatio |
string | No | adaptive |
- | - | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive |
The shape of the video. Auto picks a fitting shape. Ignored when a first frame is set, since the shape follows that image. |
Minimax H3 Max Extend Video
Section titled “Minimax H3 Max Extend Video”Extend a video with MiniMax H3 Max: describe what happens next and add 1–15s of new footage at 480p up to 2K.
Model ID: model_minimax-h3-max-extend-video
Capabilities: video2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-h3-max-extend-video/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe what happens next. Write about the continuation, not the source video. |
video |
file | Yes | - | - | - | - | The video to extend. Must be 1.625-60 seconds long, up to 50 MB, with an aspect ratio between 0.4 and 2.5. |
referenceAudio |
file_array | No | - | - | - | - | Audio to guide the continuation (up to 3, each 2-15s and 15s in total). Replaces the source soundtrack as the audio reference. |
duration |
number | No | 5 |
1 | 15 | - | Seconds of new footage to add after the source (1-15). Only the new footage is billed. |
resolution |
string | No | 768P |
- | - | 480P, 768P, 1080P, 2K |
The output quality. Higher resolutions cost more. |
aspectRatio |
string | No | auto |
- | - | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 |
Auto follows the source video. Other values crop the video to fit. |
output |
string | No | extended |
- | - | extended, continuation |
Extended returns the source video followed by the new footage. Continuation returns only the new footage. |
enablePromptExpansion |
boolean | No | true |
- | - | - | Rewrite the prompt using the source video to keep the continuation consistent. May take longer. |
seed |
number | No | - | - | - | - | Use a seed for reproducible results. Leave blank for a random seed. |
Minimax H3 Max I2V
Section titled “Minimax H3 Max I2V”Fal’s post-trained MiniMax H3 Max image-to-video: animate a first frame (optional last frame), 5–15s at 480p or 768p.
Model ID: model_minimax-h3-max-i2v
Capabilities: img2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-h3-max-i2v/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe the video you want. |
firstFrameImage |
file | Yes | - | - | - | - | An image to use as the video’s opening frame. The video’s shape follows this image. |
lastFrameImage |
file | No | - | - | - | - | An image to use as the video’s closing frame. Only works when a first frame is also set. |
duration |
number | No | 5 |
5 | 15 | - | How long the video lasts, in seconds (5-15). Longer videos cost more. |
resolution |
string | No | 768P |
- | - | 480P, 768P |
The output quality. Higher resolutions cost more. |
promptExpansionMode |
string | No | balanced |
- | - | disabled, balanced, quality |
How much to rewrite the prompt before generation. Disabled skips it. Balanced takes about a second. Quality spends up to ~30s on a richer prompt. |
seed |
number | No | - | - | - | - | Use a seed for reproducible results. Leave blank for a random seed. |
Minimax H3 Max Insert Video
Section titled “Minimax H3 Max Insert Video”Insert a new scene into an existing video with MiniMax H3 Max, guided by a prompt, reference images or videos, then return to the original footage.
Model ID: model_minimax-h3-max-insert-video
Capabilities: video2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-h3-max-insert-video/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
video |
file | Yes | - | - | - | - | The video to insert a new scene into. |
prompt |
string | No | - | - | - | - | Describe the new scene to insert. |
referenceImages |
file_array | No | - | - | - | - | Images to guide subjects or style in the new scene (up to 9). Billed by reference tokens: a square image is 1024 tokens, wider or taller images cost more. |
referenceVideos |
file_array | No | - | - | - | - | Videos to guide motion in the new scene (up to 3). Billed by reference tokens, by duration (up to ~8s per video) at the output resolution. |
startTime |
number | Yes | - | 1.625 | 60 | - | Time in the source video, in seconds, where the new scene starts (1.625-60). |
resumeTime |
number | Yes | - | 1.625 | 60 | - | Time in the source video, in seconds, where the original footage resumes after the new scene (up to 60). |
duration |
number | No | 5 |
5 | 13 | - | Length of the new scene, in seconds (5-13). Only the new scene is billed. |
resolution |
string | No | 768p |
- | - | 480p, 768p |
The output quality. Higher resolutions cost more. |
colorMatch |
boolean | No | true |
- | - | - | Match the colors of the new scene to the source video. |
enablePromptExpansion |
boolean | No | true |
- | - | - | Rewrite the prompt using the source video to keep the new scene consistent. May take longer. |
seed |
number | No | - | - | - | - | Use a seed for reproducible results. Leave blank for a random seed. |
Minimax H3 Max Lip Sync
Section titled “Minimax H3 Max Lip Sync”Animate a still into a talking-head video that lip-syncs to supplied audio. 480p-2K; output length follows the audio (5-15s).
Model ID: model_minimax-h3-max-lip-sync
Capabilities: img2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-h3-max-lip-sync/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
image |
file | Yes | - | - | - | - | A still of the character or person to animate. The aspect ratio must be between 0.4 and 2.5 (roughly tall portrait to wide landscape); the video’s shape follows this image. |
audio |
file | Yes | - | - | - | - | Audio to lip-sync to. Must be 5-15 seconds. Audio above 15 seconds will be trimmed to 15 seconds. |
resolution |
string | No | 768P |
- | - | 480P, 768P, 1080P, 2K |
The output quality. Higher resolutions cost more. Aspect ratio follows the image. |
enableTranscription |
boolean | No | false |
- | - | - | Transcribe the audio to guide lip synchronization. When off, the mouth is synced to the audio without a transcript. |
seed |
number | No | - | - | - | - | Use a seed for reproducible results. Leave blank for a random seed. |
Minimax H3 Max Recast
Section titled “Minimax H3 Max Recast”Recast a video with MiniMax H3 Max: swap up to 4 people for new ones from photos, keeping the original motion and shots, at 768p or 1080p.
Model ID: model_minimax-h3-max-recast
Capabilities: video2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-h3-max-recast/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
video |
file | Yes | - | - | - | - | The video to recast. Must be 5-30 seconds long, with no single shot longer than 15 seconds. Billed per second of this video. |
referenceImages |
file_array | Yes | - | - | - | - | One photo per new person (up to 4). By default they replace the main people in the video from left to right, in every shot they appear in. |
prompt |
string | No | - | - | - | - | Optionally say who becomes whom, or what else to keep or change. |
resolution |
string | No | 1080P |
- | - | 768P, 1080P |
The output quality. Higher resolutions cost more. |
seed |
number | No | - | - | - | - | Use a seed for reproducible results. Leave blank for a random seed. |
MiniMax H3 Max Reference to Video
Section titled “MiniMax H3 Max Reference to Video”MiniMax H3 Max reference-to-video via Fal: stronger prompt adherence and aesthetics from images, videos, and optional audio, with native stereo sound at 480P or 768P.
Model ID: model_minimax-h3-max-reference-to-video
Capabilities: img2video, video2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-h3-max-reference-to-video/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe the video. Refer to uploads by order: Image 1, Image 2, Video 1, Audio 1, and so on. |
referenceImages |
file_array | No | - | - | - | - | Images to guide subjects or style (up to 9, max 30 MB each). Refer to them as Image 1, Image 2, and so on. Combined images, videos, and audio must not exceed 12 files. First 4 (1024×1024) are included; additional images are billed. |
referenceVideos |
file_array | No | - | - | - | - | Videos to guide motion (up to 3, each 2–15s and 2–15s in total, max 50 MB each). Refer to them as Video 1, Video 2, and so on. Billed per second of uploaded duration at the output resolution. |
referenceAudio |
file_array | No | - | - | - | - | Audio to guide the video (up to 3, each 2–15s and 2–15s in total, max 15 MB each). Requires at least one reference image or video. |
duration |
number | No | 5 |
5 | 15 | - | How long the video lasts, in seconds (5–15). Longer videos cost more. |
resolution |
string | No | 768P |
- | - | 480P, 768P |
The native generation resolution. Reference video billing depends on this value. |
aspectRatio |
string | No | adaptive |
- | - | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive |
The shape of the video. Auto picks a fitting shape. |
promptExpansionMode |
string | No | balanced |
- | - | balanced, quality |
How much to rewrite the prompt before generation. Balanced returns in about a second; quality spends up to ~30s on a richer prompt. |
seed |
number | No | - | 0 | 2147483647 | - | Optional seed for reproducible results. A random seed is used when omitted. |
Minimax H3 Max T2V
Section titled “Minimax H3 Max T2V”Fal’s post-trained MiniMax H3 Max text-to-video: stronger prompt adherence and aesthetics, 5–15s at 480p or 768p.
Model ID: model_minimax-h3-max-t2v
Capabilities: txt2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-h3-max-t2v/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe the video you want. |
duration |
number | No | 5 |
5 | 15 | - | How long the video lasts, in seconds (5-15). Longer videos cost more. |
resolution |
string | No | 768P |
- | - | 480P, 768P |
The output quality. Higher resolutions cost more. |
aspectRatio |
string | No | 16:9 |
- | - | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 |
The shape of the video. |
promptExpansionMode |
string | No | balanced |
- | - | disabled, balanced, quality |
How much to rewrite the prompt before generation. Disabled skips it. Balanced takes about a second. Quality spends up to ~30s on a richer prompt. |
seed |
number | No | - | - | - | - | Use a seed for reproducible results. Leave blank for a random seed. |
Minimax H3 Max Turbo Extend Video
Section titled “Minimax H3 Max Turbo Extend Video”Extend a video with MiniMax H3 Max Turbo: describe what happens next and add 1–15s of new footage at 480p up to 2K.
Model ID: model_minimax-h3-max-turbo-extend-video
Capabilities: video2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-h3-max-turbo-extend-video/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe what happens next. Write about the continuation, not the source video. |
video |
file | Yes | - | - | - | - | The video to extend. Must be 1.625-60 seconds long, up to 50 MB, with an aspect ratio between 0.4 and 2.5. |
referenceAudio |
file_array | No | - | - | - | - | Audio to guide the continuation (up to 3, each 2-15s and 15s in total). Replaces the source soundtrack as the audio reference. |
duration |
number | No | 5 |
1 | 15 | - | Seconds of new footage to add after the source (1-15). Only the new footage is billed. |
resolution |
string | No | 768P |
- | - | 480P, 768P, 1080P, 2K |
The output quality. Higher resolutions cost more. |
aspectRatio |
string | No | auto |
- | - | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 |
Auto follows the source video. Other values crop the video to fit. |
output |
string | No | extended |
- | - | extended, continuation |
Extended returns the source video followed by the new footage. Continuation returns only the new footage. |
enablePromptExpansion |
boolean | No | true |
- | - | - | Rewrite the prompt using the source video to keep the continuation consistent. May take longer. |
seed |
number | No | - | - | - | - | Use a seed for reproducible results. Leave blank for a random seed. |
Minimax H3 Max Turbo I2V
Section titled “Minimax H3 Max Turbo I2V”Fal’s post-trained MiniMax H3 Max Turbo image-to-video: faster inference with stronger prompt adherence, 5–15s at 480p or 768p.
Model ID: model_minimax-h3-max-turbo-i2v
Capabilities: img2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-h3-max-turbo-i2v/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe the video you want. |
firstFrameImage |
file | Yes | - | - | - | - | An image to use as the video’s opening frame. The video’s shape follows this image. |
lastFrameImage |
file | No | - | - | - | - | An image to use as the video’s closing frame. Only works when a first frame is also set. |
duration |
number | No | 5 |
5 | 15 | - | How long the video lasts, in seconds (5-15). Longer videos cost more. |
resolution |
string | No | 768P |
- | - | 480P, 768P |
The output quality. Higher resolutions cost more. |
promptExpansionMode |
string | No | balanced |
- | - | disabled, balanced, quality |
How much to rewrite the prompt before generation. Disabled skips it. Balanced takes about a second. Quality spends up to ~30s on a richer prompt. |
seed |
number | No | - | - | - | - | Use a seed for reproducible results. Leave blank for a random seed. |
Minimax H3 Max Turbo T2V
Section titled “Minimax H3 Max Turbo T2V”Fal’s post-trained MiniMax H3 Max Turbo text-to-video: faster inference with stronger prompt adherence, 5–15s at 480p or 768p.
Model ID: model_minimax-h3-max-turbo-t2v
Capabilities: txt2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-h3-max-turbo-t2v/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe the video you want. |
duration |
number | No | 5 |
5 | 15 | - | How long the video lasts, in seconds (5-15). Longer videos cost more. |
resolution |
string | No | 768P |
- | - | 480P, 768P |
The output quality. Higher resolutions cost more. |
aspectRatio |
string | No | 16:9 |
- | - | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 |
The shape of the video. |
promptExpansionMode |
string | No | balanced |
- | - | disabled, balanced, quality |
How much to rewrite the prompt before generation. Disabled skips it. Balanced takes about a second. Quality spends up to ~30s on a richer prompt. |
seed |
number | No | - | - | - | - | Use a seed for reproducible results. Leave blank for a random seed. |
Minimax Hailuo 02
Section titled “Minimax Hailuo 02”Model ID: model_minimax-hailuo-02
Capabilities: txt2video, img2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-hailuo-02/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe your video |
firstFrameImage |
file | No | - | - | - | - | Image used as the first frame of the video. The output video will have the same aspect ratio as this image. |
lastFrameImage |
file | No | - | - | - | - | Used to generate a video that transitions from the first frame to this image. Requires a first frame image. |
duration |
number | No | 6 |
- | - | 6, 10 |
Duration of the video in seconds. 10 seconds is only available for 768p resolution. |
resolution |
string | No | 1080p |
- | - | 768p, 1080p |
Pick between standard 768p, or pro 1080p resolution. The pro model is not just high resolution, it is also higher quality. |
promptOptimizer |
boolean | No | true |
- | - | - | Use prompt optimizer |
Minimax Hailuo 2.3
Section titled “Minimax Hailuo 2.3”A high-fidelity video generation model optimized for realistic human motion, cinematic VFX, expressive characters, and strong prompt and style adherence across both text-to-video and image-to-video workflows
Model ID: model_minimax-hailuo-2-3
Capabilities: txt2video, img2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-hailuo-2-3/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Text prompt for generation |
firstFrameImage |
file | No | - | - | - | - | First frame image for video generation. The output video will have the same aspect ratio as this image. |
duration |
number | No | 6 |
- | - | 6, 10 |
Duration of the video in seconds. 10 seconds is only available for 768p resolution. |
resolution |
string | No | 768p |
- | - | 768p, 1080p |
Pick between 768p or 1080p resolution. 1080p supports only 6-second duration. |
promptOptimizer |
boolean | No | true |
- | - | - | Use prompt optimizer |
Minimax Hailuo 2.3 Fast
Section titled “Minimax Hailuo 2.3 Fast”A lower-latency image-to-video version of Hailuo 2.3 that preserves core motion quality, visual consistency, and stylization performance while enabling faster iteration cycles.
Model ID: model_minimax-hailuo-2-3-fast
Capabilities: txt2video, img2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-hailuo-2-3-fast/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Text prompt for generation |
firstFrameImage |
file | No | - | - | - | - | First frame image for video generation. The output video will have the same aspect ratio as this image. |
duration |
number | No | 6 |
- | - | 6, 10 |
Duration of the video in seconds. 10 seconds is only available for 768p resolution. |
resolution |
string | No | 768p |
- | - | 768p, 1080p |
Pick between 768p or 1080p resolution. 1080p supports only 6-second duration. |
promptOptimizer |
boolean | No | true |
- | - | - | Use prompt optimizer |
Minimax Video 01
Section titled “Minimax Video 01”Minimax Video-01 is a versatile model generating high-quality videos with 720p resolution and smooth motion.
Model ID: model_minimax-video-01
Capabilities: txt2video, img2video
LLM Markdown: https://app.scenario.com/api/models/model_minimax-video-01/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe your video |
firstFrameImage |
file | No | - | - | - | - | Image used as the first frame of the video. |
subjectReference |
file | No | - | - | - | - | An optional character reference image to use as the subject in the generated video |
promptOptimizer |
boolean | No | true |
- | - | - | Use prompt optimizer |