Haiper / Haiper Video

Haiper Video 2.x API

Version-flexible Haiper 2.x video contract for text, image and keyframe-conditioned generation. Exact 2.0/2.5 routing is unresolved.

Video generation

restrictedClosed-source managed componentVideo generation

Official documentation (opens in a new tab)Reviewed 15 Oct 2026
5 of 21 specification fields collected

Output resolution540p, 720pSee specification notes below

Clip durationText/image creation: 4 or 6 seconds, default 6. Keyframe conditioning: 4 or 6 seconds, default 4.See specification notes below

Input billingSee ratesHaiper API

Output billingSee ratesPublished units and conditions below

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
Maximum input tokens: Not collected
Maximum output: Not collected
Maximum prompt characters: Not collected
Reasoning: Not collected
Tool calling: Not collected
Structured output: Not collected
Streaming: Not collected
Batch processing: Not collected
Fine-tuning: Not collected
Context caching: Not collected
Knowledge cutoff: Not collected
Release date: Not collected
Parameters: Not collected
Architecture: Not collected
Languages: Not collected
Input modalities: Text, ImageSource for Input modalities (opens in a new tab)
Output modalities: VideoSource for Output modalities (opens in a new tab)
Video duration: Text/image creation: 4 or 6 seconds, default 6. Keyframe conditioning: 4 or 6 seconds, default 4.Source for Video duration (opens in a new tab)
Output resolutions: 540p, 720pSource for Output resolutions (opens in a new tab)
Frame rate: 24Source for Frame rate (opens in a new tab)

Access & pricing

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

Haiper API

Provider source (opens in a new tab)

API model ID: Not collected
Access: Documented paid API requiring a Haiper API key and top-up. Runtime generation and account eligibility were not tested.
Regions: Deployment regions not established
API endpoint URL: POST https://api.haiper.ai/v1/jobs/gen2/text2videoSource for API endpoint URL (opens in a new tab)
Authentication: Authorization: Bearer APIKEY; Content-Type: application/json. Prepaid balance is required.Source for Authentication (opens in a new tab)
Request quotas: Default 500 HTTP requests per minute and 40 concurrent generations; exceeding either yields HTTP 429. Higher quotas require contacting Haiper.Source for Request quotas (opens in a new tab)
Asynchronous generation: Submission returns generation_id. Poll GET /v1/jobs/{creation_id}/status for pending, processing, succeed, failed or post_processing. Fetch GET /v1/creation/{creation_id} after succeed. Polling is not token streaming.Source for Asynchronous generation (opens in a new tab)
Creation privacy: Schema description: is_public defaults to true; set false for private creation. The official ComfyUI node defaults false, so wrapper and API defaults differ.Source for Creation privacy (opens in a new tab)
Seed controls: Generation settings describe seed default -1 without a verified integer range or reproducibility guarantee.Source for Seed controls (opens in a new tab)
Request format: JSON request and response. Nested source-image requirements are sometimes only descriptive in the schema.Source for Request format (opens in a new tab)
Generation modes: standard (default), smooth or enhanced. These are mode labels, not verified checkpoint-version aliases.Source for Generation modes (opens in a new tab)
Aspect ratios: 21:9, 16:9, 9:16, 3:4, 4:3, 1:1Source for Aspect ratios (opens in a new tab)
Prompt expansion: is_enable_prompt_enhancer defaults true in the schema.Source for Prompt expansion (opens in a new tab)
Content marking controls: POST /v1/creation/{creation_id}/watermark-free-url creates a link expiring after 60 minutes. This is a media-link expiry, not a cache TTL.Source for Content marking controls (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
Category	Usage	Rate	Unit
API media pricing	720p, 24 fps¹	$0.05	video second
API media pricing	540p, 24 fps¹	$0.033	video second

Rate conditions

Native API standard pricing; not a subscription credit conversion. Current runtime availability was not tested.

Pricing source (opens in a new tab)

Data & enterprise terms

The route schema describes is_public defaulting to true. Set false for a private creation. Exact retention, training use and enterprise data-processing terms remain unverified.

Haiper API

Provider source (opens in a new tab)

API model ID: Not collected
Access: Documented paid API requiring a Haiper API key and top-up. Runtime generation and account eligibility were not tested.
Regions: Deployment regions not established
API endpoint URL: POST https://api.haiper.ai/v1/jobs/gen2/image2videoSource for API endpoint URL (opens in a new tab)
Authentication: Authorization: Bearer APIKEY; Content-Type: application/json. Prepaid balance is required.Source for Authentication (opens in a new tab)
Request quotas: Default 500 HTTP requests per minute and 40 concurrent generations; exceeding either yields HTTP 429. Higher quotas require contacting Haiper.Source for Request quotas (opens in a new tab)
Asynchronous generation: Submission returns generation_id. Poll GET /v1/jobs/{creation_id}/status for pending, processing, succeed, failed or post_processing. Fetch GET /v1/creation/{creation_id} after succeed. Polling is not token streaming.Source for Asynchronous generation (opens in a new tab)
Creation privacy: Schema description: is_public defaults to true; set false for private creation. The official ComfyUI node defaults false, so wrapper and API defaults differ.Source for Creation privacy (opens in a new tab)
Seed controls: Generation settings describe seed default -1 without a verified integer range or reproducibility guarantee.Source for Seed controls (opens in a new tab)
Request format: JSON request and response. Nested source-image requirements are sometimes only descriptive in the schema.Source for Request format (opens in a new tab)
Generation modes: smooth (default) or enhanced.Source for Generation modes (opens in a new tab)
Input file formats: config.source_image accepts JPG, PNG or WebP URL/Base64. Required top-level fields are prompt and config; the nested source_image requirement is descriptive.Source for Input file formats (opens in a new tab)
Prompt expansion: Schema default true; official ComfyUI image-to-video node defaults false.Source for Prompt expansion (opens in a new tab)
Content marking controls: POST /v1/creation/{creation_id}/watermark-free-url creates a link expiring after 60 minutes. This is a media-link expiry, not a cache TTL.Source for Content marking controls (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
Category	Usage	Rate	Unit
API media pricing	720p, 24 fps¹	$0.05	video second
API media pricing	540p, 24 fps¹	$0.033	video second

Rate conditions

Native API standard pricing; not a subscription credit conversion. Current runtime availability was not tested.

Pricing source (opens in a new tab)

Data & enterprise terms

The route schema describes is_public defaulting to true. Set false for a private creation. Exact retention, training use and enterprise data-processing terms remain unverified.

Haiper API

Provider source (opens in a new tab)

API model ID: Not collected
Access: Documented paid API requiring a Haiper API key and top-up. Runtime generation and account eligibility were not tested.
Regions: Deployment regions not established
API endpoint URL: POST https://api.haiper.ai/v1/jobs/gen2/afcSource for API endpoint URL (opens in a new tab)
Authentication: Authorization: Bearer APIKEY; Content-Type: application/json. Prepaid balance is required.Source for Authentication (opens in a new tab)
Request quotas: Default 500 HTTP requests per minute and 40 concurrent generations; exceeding either yields HTTP 429. Higher quotas require contacting Haiper.Source for Request quotas (opens in a new tab)
Asynchronous generation: Submission returns generation_id. Poll GET /v1/jobs/{creation_id}/status for pending, processing, succeed, failed or post_processing. Fetch GET /v1/creation/{creation_id} after succeed. Polling is not token streaming.Source for Asynchronous generation (opens in a new tab)
Creation privacy: Schema description: is_public defaults to true; set false for private creation. The official ComfyUI node defaults false, so wrapper and API defaults differ.Source for Creation privacy (opens in a new tab)
Seed controls: Generation settings describe seed default -1 without a verified integer range or reproducibility guarantee.Source for Seed controls (opens in a new tab)
Request format: JSON request and response. Nested source-image requirements are sometimes only descriptive in the schema.Source for Request format (opens in a new tab)
Frame controls: source_images and frame_indices must have equal lengths. Indices ascend: 0–31 for a 4-second clip; 0–47 for a 6-second clip. These are the published indices, not indices recalculated from 24 fps.Source for Frame controls (opens in a new tab)
Input file formats: Image URLs or Base64, JPG/PNG/WebP. input_width and input_height have no numeric bounds in the schema. No maximum keyframe count is stated.Source for Input file formats (opens in a new tab)
Required request fields: config is required. Prompt is optional for this operation; do not inherit the text-to-video prompt requirement.Source for Required request fields (opens in a new tab)
Content marking controls: POST /v1/creation/{creation_id}/watermark-free-url creates a link expiring after 60 minutes. This is a media-link expiry, not a cache TTL.Source for Content marking controls (opens in a new tab)

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

Data & enterprise terms

The route schema describes is_public defaulting to true. Set false for a private creation. Exact retention, training use and enterprise data-processing terms remain unverified.

Haiper web / iOS

Provider source (opens in a new tab)

API model ID: Not collected
Access: Published web/iOS credit schedule. Current signed-in generation availability is not tested.
Regions: Deployment regions not established

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
Category	Usage	Rate	Unit
Web / iOS media credits	Text to video, 720p¹	8 credits	video second
Web / iOS media credits	Text to video, 540p¹	5 credits	video second
Web / iOS media credits	Image to video, 720p¹	8 credits	video second
Web / iOS media credits	Image to video, 540p¹	5 credits	video second
Web / iOS media credits	Keyframe conditioning, 720p¹	8 credits	video second
Web / iOS media credits	Video to video, 720p¹	8 credits	video second

Rate conditions

Web/iOS credit schedule only; no USD conversion inferred. Current runtime availability was not tested.

Pricing source (opens in a new tab)

Data & enterprise terms

Private creation and watermark removal are described as membership benefits in the FAQ. Current plan-specific data retention and training policies remain unverified.

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.

Haiper API

Not verified

No reviewed prompt-cache contract or cache tariff. Job polling, random seeds and expiring media URLs are not prompt caching.

How it works: Not collected
Minimum reusable input: Not collected
Lifetime & refresh: Not collected
How to enable it: Not collected
Usage fields: Not collected
Billing rules: Not collected
Limits & data boundaries: Not collected

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

Caching reviewed 15 Oct 2026

Haiper API

Not verified

No reviewed prompt-cache contract or cache tariff. Job polling, random seeds and expiring media URLs are not prompt caching.

How it works: Not collected
Minimum reusable input: Not collected
Lifetime & refresh: Not collected
How to enable it: Not collected
Usage fields: Not collected
Billing rules: Not collected
Limits & data boundaries: Not collected

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

Caching reviewed 15 Oct 2026

Haiper API

Not verified

No reviewed prompt-cache contract or cache tariff. Job polling, random seeds and expiring media URLs are not prompt caching.

How it works: Not collected
Minimum reusable input: Not collected
Lifetime & refresh: Not collected
How to enable it: Not collected
Usage fields: Not collected
Billing rules: Not collected
Limits & data boundaries: Not collected

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

Caching reviewed 15 Oct 2026

Haiper web / iOS

Not verified

No reviewed prompt-cache contract or cache tariff. Job polling, random seeds and expiring media URLs are not prompt caching.

How it works: Not collected
Minimum reusable input: Not collected
Lifetime & refresh: Not collected
How to enable it: Not collected
Usage fields: Not collected
Billing rules: Not collected
Limits & data boundaries: Not collected

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

Caching reviewed 15 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

Managed Haiper generation or enhancement contract. Exact underlying checkpoint identity and version routing are not established; this record is not an additional private foundation-model count.

Classification evidence (opens in a new tab)

Sources reviewed

Haiper native API rates by operation and resolution (opens in a new tab)Reviewed 15 Oct 2026

Haiper published API schema, including legacy routes (opens in a new tab)Reviewed 15 Oct 2026

Haiper native API rates by operation and resolution (opens in a new tab)Reviewed 15 Oct 2026

Haiper web and iOS credit pricing (opens in a new tab)Reviewed 15 Oct 2026

Haiper official ComfyUI integration (opens in a new tab)Reviewed 15 Oct 2026

Model notes

Eight records: five named model identities and three managed contracts. Native schemas, separate web/API rates and official logo reviewed. Current runtime access, exact 2.x routing, earlier versions and source-policy details remain incomplete.

Official provider logo from the Haiper-owned ComfyUI repository.

Published access requires an API account and prepaid balance. No authenticated request or generation was attempted; current service operability remains unverified.

OpenAPI contains plant-store sample routes and sample MIT metadata; both are excluded from model facts.

Native API video-to-video is labeled coming soon, while the web/iOS price table lists it. Web support is not transferred into the API contract.

The ComfyUI plugin exposes duration 1–6 whereas API schemas describe 4 or 6. API schema limits are retained; the discrepancy is not silently reconciled.

Check against your workload

Try representative inputs, measure task success and total cost, then check the exact endpoint’s data policy.

Read our methodology