Upload service: 100 MB direct, up to 5 GB with presigned storage upload. These are transport limits, not model context or guaranteed processing capacity.Source for Document file limit (opens in a new tab)
queue_priority does not enable the batch lane on synchronous endpoints.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 15 Oct 2026
Category
Usage
Rate
Unit
Usage pricing
Deep Extract pages1
$40.00
1,000 pages
Rate conditions
Published list rate from September 1, 2026; negotiated contracts may differ. No additional parse cost. More than 100 fields/page may incur a surcharge. Discounted batch requests are rejected.
Growth and Enterprise API artifacts normally expire within 24 hours under the provider policy labelled ZDR. Studio jobs and persist_results are exceptions. Growth+ data is not used for training under that policy. General service terms grant broader data-use rights; do not generalize the paid-tier policy to every account. On-premise and custom contracts differ.
Upload service: 100 MB direct, up to 5 GB with presigned storage upload. These are transport limits, not model context or guaranteed processing capacity.Source for Document file limit (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
Usage pricing
Deep Extract pages1
$40.00
1,000 pages
Rate conditions
Published list rate from September 1, 2026; negotiated contracts may differ. No additional parse cost. More than 100 fields/page may incur a surcharge. Discounted batch requests are rejected.
Growth and Enterprise API artifacts normally expire within 24 hours under the provider policy labelled ZDR. Studio jobs and persist_results are exceptions. Growth+ data is not used for training under that policy. General service terms grant broader data-use rights; do not generalize the paid-tier policy to every account. On-premise and custom contracts differ.
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.
Reducto API
v4
Not verified
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
How it works
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
Minimum reusable input
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
Lifetime & refresh
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
How to enable it
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
Usage fields
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
Billing rules
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
Limits & data boundaries
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 15 Oct 2026
Reducto API
v4
Not verified
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
How it works
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
Minimum reusable input
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
Lifetime & refresh
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
How to enable it
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
Usage fields
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
Billing rules
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
Limits & data boundaries
Not collected
No model-specific prompt-cache contract or discounted cache tariff established. Retained job artifacts, cached weights and downstream LLM caching are different mechanisms.
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
Named processing model revision or agent exposed within the proprietary service. Its exact private versus third-party backbone is not established, so it is explicitly represented as a managed component rather than an independently owned base checkpoint.
