Skip to content
Model infoModelsSnapshot: 15 Oct 2026

HeyGen / HeyGen Video

HeyGen Video 1

MiniMax H3-based model post-trained by HeyGen for complete scenes with generated dialogue, ambience and effects.

availableClosed weightsVideo generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
8 of 21 specification fields collected
Output resolution480p, 768p, 1080p, 2kSee specification notes below
Clip duration5–15 seconds; integer duration, default 5See specification notes below
Input billingNot collectedHeyGen
Output billingNot collectedNo inferred price

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Maximum output
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Context caching
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Reasoning
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Tool calling
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Structured output
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Streaming
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Batch processing
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Fine-tuning
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Parameters
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Architecture
MiniMax H3 base with HeyGen post-trainingSource for Architecture (opens in a new tab)
Knowledge cutoff
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Languages
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Release date
Not collected

No exact model-specific contract established; missing information does not mean unsupported.

Input modalities
Text, Image, Video, AudioSource for Input modalities (opens in a new tab)
Maximum prompt characters
32,000Source for Maximum prompt characters (opens in a new tab)

Prompt requires 1–32,000 characters.

Output duration
5–15 seconds; integer duration, default 5Source for Output duration (opens in a new tab)
Output resolutions
480p, 768p, 1080p, 2kSource for Output resolutions (opens in a new tab)
Output formats
MP4 / H.264 video, AAC / 32 kHz stereo audioSource for Output formats (opens in a new tab)
Frame rate
24Source for Frame rate (opens in a new tab)

Provider labels 24 fps but gives 175 frames for a 7-second example. This arithmetic discrepancy remains unresolved.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

API model ID
heygen-video-1
Access
POST https://api.heygen.com/v3/models/videos; poll GET /v3/models/videos/{video_id}. Paid API key.
Regions
No model-specific processing or storage region guarantee established.
modes
text_to_video, image_to_video, reference_to_videoSource for modes (opens in a new tab)
references
Up to 9 images, 3 videos, 3 audio clips, maximum 12 total. Reference mode needs at least an image or video; audio alone is insufficient. Only first 5 seconds of each reference video are used.Source for references (opens in a new tab)
assetLimits
HTTPS or uploaded assets or base64. Downloads: image 16 MB, video/audio 32 MB. Inline decoded data: image 5 MB, video/audio 16 MB. Redirects are not followed.Source for assetLimits (opens in a new tab)
resolutionBilling
1080p and 2k cost 3× the 768p rate; base dollar rate not established. These resolutions require 16:9 or 9:16 for text/reference modes. Image mode follows its first frame.Source for resolutionBilling (opens in a new tab)
promptEnhancement
turbo, quality, ultraquality, disabledSource for promptEnhancement (opens in a new tab)

Enhancement settings are not separate video model checkpoints.

idempotency
24-hour Idempotency-Key retry window. This prevents duplicate submission; it is not discounted prompt caching.Source for idempotency (opens in a new tab)
delivery
Asynchronous job. Callback is delivered once; polling remains the fallback. Jobs run to completion. Signed output URLs can be refreshed through the job record.Source for delivery (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Privacy policy distinguishes customer-directed processing from HeyGen controller purposes. Applicable plan terms, DPA and Enterprise agreements govern training use. No blanket zero-retention or no-training promise inferred. Deleted information can remain in disaster-recovery backups for 60 days.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

HeyGen

heygen-video-1
Not verified

No model-specific prompt-cache contract established. Idempotency and saved avatar/voice assets are separate.

How it works
Not collected

No model-specific prompt-cache contract established. Idempotency and saved avatar/voice assets are separate.

Minimum reusable input
Not collected

No model-specific prompt-cache contract established. Idempotency and saved avatar/voice assets are separate.

Lifetime & refresh
Not collected

No model-specific prompt-cache contract established. Idempotency and saved avatar/voice assets are separate.

How to enable it
Not collected

No model-specific prompt-cache contract established. Idempotency and saved avatar/voice assets are separate.

Usage fields
Not collected

No model-specific prompt-cache contract established. Idempotency and saved avatar/voice assets are separate.

Billing rules
Not collected

No model-specific prompt-cache contract established. Idempotency and saved avatar/voice assets are separate.

Limits & data boundaries
Not collected

No model-specific prompt-cache contract established. Idempotency and saved avatar/voice assets are separate.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Official model documentation identifies a HeyGen post-trained derivative of MiniMax H3. Hosted proprietary model access under HeyGen terms does not release the weights or establish independent base pretraining.

Classification evidence (opens in a new tab)

Sources reviewed