Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Nanonets / Nanonets extraction workflows

Nanonets Nova

Larger extraction family intended for dense tables, handwriting and degraded scans. Distinct from Amazon Nova.

Document extraction / OCR
restrictedClosed-source managed componentDocument extractionOCR
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
7 of 23 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingSee billing notesNanonets workflow API
Output billingSee billing notesAccess and billing notes 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

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Maximum input tokens
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Maximum output
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Maximum input content size
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Reasoning
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Tool calling
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Structured output
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Streaming
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Batch processing
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Fine-tuning
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Context caching
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Parameters
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Architecture
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Languages
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Release date
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Knowledge cutoff
Not collected

Not established for this exact model. Workflow processing, output documents and marketing claims are not LLM capability or token-limit contracts.

Input modalities
Document, ImageSource for Input modalities (opens in a new tab)
Output modalities
JSON, TextSource for Output modalities (opens in a new tab)
Input file formats
PDF, PNG, JPG, CSV, XLS, XLSX, TIFF, TXT, DOCXSource for Input file formats (opens in a new tab)

Platform import support; direct API transport and individual workflow support may differ.

Output formats
Field/table JSON with text, confidence scores and bounding boxes.Source for Output formats (opens in a new tab)
Published price
Family-specific quote requiredSource for Published price (opens in a new tab)

The family page explains per-page pricing but publishes no numeric Spark/Flux/Nova rates.

Usage metering
Extraction is charged per processed page; workflow import, formatting and export can add charges.Source for Usage metering (opens in a new tab)
Learning from corrections
Document corrections must be approved before instant learning uses them. Exact weight-update mechanism is not established.Source for Learning from corrections (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.

Nanonets workflow API

Provider source (opens in a new tab)
API model ID
Not collected

Caller-specific model_id UUID, not the family/tier name. Exact private checkpoint mapping not established.

Access
Family configuration requires an account manager. API calls use the configured account-specific model ID.
Regions
Exact model-specific residency not established
API endpoint URL
POST https://app.nanonets.com/api/v2/OCR/Model/{model_id}/LabelFile/Source for API endpoint URL (opens in a new tab)
Authentication
HTTP Basic authentication: API key as username, empty password. HTTPS required.Source for Authentication (opens in a new tab)

Based on security scheme and request examples, not the ambiguous generic header prose.

Input file formats
multipart/form-data file upload; base64_data alternative described by examples. The schema still requires file, so alternative validation behavior is unresolved.Source for Input file formats (opens in a new tab)
API parameters
Optional l language code and pages_to_process comma-separated page selection; request_metadata echoed in results.Source for API parameters (opens in a new tab)
Output formats
Page-oriented JSON predictions: field/table labels, extracted text, confidence score and xmin/ymin/xmax/ymax boxes. Review validation fields separately from model status.Source for Output formats (opens in a new tab)

The label status correctly_predicted is a protocol value, not a correctness guarantee.

Asynchronous processing
Sync endpoint is optimized for 3 pages or fewer; this is guidance, not a maximum file-page limit.Source for Asynchronous processing (opens in a new tab)
Result URL lifetime
Documented signed URL lifetimes: 4 hours for original URLs and 180 days for long-expiry originals.Source for Result URL lifetime (opens in a new tab)

URL validity is not a complete stored-data retention or deletion policy.

Billing scope
Extraction runs per page. Failed blocks retried to success are charged only for the successful run.Source for Billing scope (opens in a new tab)

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

Data & enterprise terms

No exact-version contractual retention, training-use or residency terms verified.

Nanonets workflow API

Provider source (opens in a new tab)
API model ID
Not collected

Caller-specific model_id UUID, not the family/tier name. Exact private checkpoint mapping not established.

Access
Family configuration requires an account manager. API calls use the configured account-specific model ID.
Regions
Exact model-specific residency not established
API endpoint URL
POST https://app.nanonets.com/api/v2/OCR/Model/{model_id}/LabelFile?async=trueSource for API endpoint URL (opens in a new tab)
Authentication
HTTP Basic authentication: API key as username, empty password. HTTPS required.Source for Authentication (opens in a new tab)

Based on security scheme and request examples, not the ambiguous generic header prose.

Input file formats
multipart/form-data file upload; base64_data alternative described by examples. The schema still requires file, so alternative validation behavior is unresolved.Source for Input file formats (opens in a new tab)
API parameters
async=true query required; request_metadata echoed in results.Source for API parameters (opens in a new tab)
Output formats
Page-oriented JSON predictions: field/table labels, extracted text, confidence score and xmin/ymin/xmax/ymax boxes. Review validation fields separately from model status.Source for Output formats (opens in a new tab)

The label status correctly_predicted is a protocol value, not a correctness guarantee.

Asynchronous processing
Async processing recommended for files above 3 pages; accepted uploads are not completed extraction results.Source for Asynchronous processing (opens in a new tab)
Result URL lifetime
Documented signed URL lifetimes: 4 hours for original URLs and 180 days for long-expiry originals.Source for Result URL lifetime (opens in a new tab)

URL validity is not a complete stored-data retention or deletion policy.

Billing scope
Extraction runs per page. Failed blocks retried to success are charged only for the successful run.Source for Billing scope (opens in a new tab)

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

Data & enterprise terms

No exact-version contractual retention, training-use or residency terms verified.

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.

Nanonets workflow API

Not verified

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

How it works
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

Minimum reusable input
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

Lifetime & refresh
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

How to enable it
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

Usage fields
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

Billing rules
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

Limits & data boundaries
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

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

Caching reviewed 15 Oct 2026

Nanonets workflow API

Not verified

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

How it works
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

Minimum reusable input
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

Lifetime & refresh
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

How to enable it
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

Usage fields
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

Billing rules
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning are not prompt caching.

Limits & data boundaries
Not collected

No documented prompt-cache contract or discounted cache rate. Stored files, signed URLs and instant learning 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

Managed extraction configuration with a named service tier/family. Exact constituent private, public-weight or third-party checkpoint mapping is not disclosed in the reviewed documentation. This is not counted as a separate private foundation model.

Classification evidence (opens in a new tab)

Sources reviewed