Input billingNot collectedHaiper announced access (historical)
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
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Maximum input tokens
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Maximum output
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Maximum prompt characters
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Reasoning
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Tool calling
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Structured output
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Streaming
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Batch processing
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Fine-tuning
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Context caching
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Knowledge cutoff
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
News-index announcement date; full launch page was not recovered.
Parameters
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Architecture
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Languages
Not collected
Not established for this exact version or operation. Media quotas and polling do not establish language-model context, token prices or a discounted Batch API.
Historical published model identity. Current exact-version runtime access has not been established.
Regions
Not established
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
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 announced access (historical)
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
No reviewed prompt-cache contract or cache tariff. Job polling, random seeds and expiring media URLs are not prompt caching.
Minimum reusable input
Not collected
No reviewed prompt-cache contract or cache tariff. Job polling, random seeds and expiring media URLs are not prompt caching.
Lifetime & refresh
Not collected
No reviewed prompt-cache contract or cache tariff. Job polling, random seeds and expiring media URLs are not prompt caching.
How to enable it
Not collected
No reviewed prompt-cache contract or cache tariff. Job polling, random seeds and expiring media URLs are not prompt caching.
Usage fields
Not collected
No reviewed prompt-cache contract or cache tariff. Job polling, random seeds and expiring media URLs are not prompt caching.
Billing rules
Not collected
No reviewed prompt-cache contract or cache tariff. Job polling, random seeds and expiring media URLs are not prompt caching.
Limits & data boundaries
Not collected
No reviewed prompt-cache contract or cache tariff. Job polling, random seeds and expiring media URLs are not prompt caching.
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
Private hosted-model classification inferred from Haiper naming its own model family and providing hosted access, without a matching public weight release established in reviewed first-party evidence. Exact weight licensing, ancestry and checkpoint architecture remain unresolved. The sample OpenAPI MIT license and public ComfyUI client license are not model weight licenses.