Golang client
Provide a client library for integrating the Mindee API using the Go language. Support for: POST using polling and webhook methods loading files from various sources (path, bytes, File object, etc) PDF splitting before sending Must be able to handle dynamic outputs in a simple way.

Ianaré Sévi 4 days ago
Golang client
Provide a client library for integrating the Mindee API using the Go language. Support for: POST using polling and webhook methods loading files from various sources (path, bytes, File object, etc) PDF splitting before sending Must be able to handle dynamic outputs in a simple way.

Ianaré Sévi 4 days ago
Planned
Multiple Receipts in Single Image Support?
Does your receipt OCR API support processing multiple receipts within a single image? If so, will it extract data from each receipt separately or combine them?

FleetYes 5 days ago
Planned
Multiple Receipts in Single Image Support?
Does your receipt OCR API support processing multiple receipts within a single image? If so, will it extract data from each receipt separately or combine them?

FleetYes 5 days ago
In Progress
hello Mindee people :
I'm having trouble having my newly created API KEY recognized, even after having fully followed the technical specifications. i have the following error : Erreur OCR : Erreur technique Mindee : invoices 401 HTTP error: Invalid token provided - Authorization required. Any insights on how to solve this issue ?

Philippe Massoubre expertcomptablenligne 9 days ago
In Progress
hello Mindee people :
I'm having trouble having my newly created API KEY recognized, even after having fully followed the technical specifications. i have the following error : Erreur OCR : Erreur technique Mindee : invoices 401 HTTP error: Invalid token provided - Authorization required. Any insights on how to solve this issue ?

Philippe Massoubre expertcomptablenligne 9 days ago
Completed
Strong-Named Mindee.dll & PublicKeyToken Support (.NET SDK)
Hi Mindee Team, I’m using the Mindee .NET SDK (v3.37.0) in a .NET Framework (net48) application. Our application is strong-name signed, so all referenced assemblies must also be strong-named and contain a valid PublicKeyToken. Currently, the Mindee.dll provided via NuGet is not strong-name signed. Is a strong-named version of Mindee.dll available, or are there any plans to provide one in future releases? Please let us know the recommended approach for environments where strong-name signing is mandatory. Thanks.

Kavya Kavya 23 days ago
Completed
Strong-Named Mindee.dll & PublicKeyToken Support (.NET SDK)
Hi Mindee Team, I’m using the Mindee .NET SDK (v3.37.0) in a .NET Framework (net48) application. Our application is strong-name signed, so all referenced assemblies must also be strong-named and contain a valid PublicKeyToken. Currently, the Mindee.dll provided via NuGet is not strong-name signed. Is a strong-named version of Mindee.dll available, or are there any plans to provide one in future releases? Please let us know the recommended approach for environments where strong-name signing is mandatory. Thanks.

Kavya Kavya 23 days ago
Completed
Base64 Input Support & Model Identification in Mindee V2 (.NET SDK)
Hi Mindee Team, I’m using the Mindee V2 API with the C# (.NET) SDK. Is Base64 image input supported directly in V2? In the .NET SDK, I only see LocalInputSource and UrlInputSource. Currently, I have to convert Base64 → file → LocalInputSource. Is this the recommended approach or will direct Base64 support be added? In V2, is modelId the only way to identify invoice, receipt, and passport models? how to differentiate V2 models such as Invoice, Passport and Expense Receipt using the respective modelIds. Thanks.

Kavya Kavya 26 days ago
Completed
Base64 Input Support & Model Identification in Mindee V2 (.NET SDK)
Hi Mindee Team, I’m using the Mindee V2 API with the C# (.NET) SDK. Is Base64 image input supported directly in V2? In the .NET SDK, I only see LocalInputSource and UrlInputSource. Currently, I have to convert Base64 → file → LocalInputSource. Is this the recommended approach or will direct Base64 support be added? In V2, is modelId the only way to identify invoice, receipt, and passport models? how to differentiate V2 models such as Invoice, Passport and Expense Receipt using the respective modelIds. Thanks.

Kavya Kavya 26 days ago
Completed
Move an already existing field to a nested field
It is really annoying to have to recreate all subfields in a nested field when they already existed as normal fields.

Felix Croizon About 1 month ago
Completed
Move an already existing field to a nested field
It is really annoying to have to recreate all subfields in a nested field when they already existed as normal fields.

Felix Croizon About 1 month ago
Completed
Request for English Name Extraction for Russian Passport
I’m currently using Mindee to process Russian passports, and I’ve noticed that the extracted name fields are returned in Russian. Could you please advise if it’s possible to receive the name response in English instead of Russian, or guide me on how to configure the API/output to achieve this?

Varsha Aurangabadkar Chopra 3 months ago
Completed
Request for English Name Extraction for Russian Passport
I’m currently using Mindee to process Russian passports, and I’ve noticed that the extracted name fields are returned in Russian. Could you please advise if it’s possible to receive the name response in English instead of Russian, or guide me on how to configure the API/output to achieve this?

Varsha Aurangabadkar Chopra 3 months ago
Completed
QR / Barcode value decode
When the image or document contains barcodes or QR codes in addition to text or photos, it should interpret them and returns their values, not just the object's coordinates. This would be useful for scanning tickets, boarding passes, and all documents that have barcodes to be read.

Juan Antonio 3 months ago
Completed
QR / Barcode value decode
When the image or document contains barcodes or QR codes in addition to text or photos, it should interpret them and returns their values, not just the object's coordinates. This would be useful for scanning tickets, boarding passes, and all documents that have barcodes to be read.

Juan Antonio 3 months ago
Possibility to convert and download extracted data to csv.
Convert a bundle of documents into CSV. To be able to then upload the document in a financial control system

Constance de David Beauregard 4 months ago
Possibility to convert and download extracted data to csv.
Convert a bundle of documents into CSV. To be able to then upload the document in a financial control system

Constance de David Beauregard 4 months ago
In Progress
I am using Mindee v2, and I would like to know how much credit I have used and how much remains. Could you please tell me where I can find the dashboard?

itservice 4 months ago
In Progress
I am using Mindee v2, and I would like to know how much credit I have used and how much remains. Could you please tell me where I can find the dashboard?

itservice 4 months ago
Completed
Make Polygons Available in Free Trial and Starter Plan
Hello Mindee Team, I'm currently evaluating your platform with a free trial and I'm very impressed. However, I've run into a confusing issue. The "Live Test" on your website correctly shows polygon coordinates, but this data is missing when using my trial API key. This is made even more confusing because the API settings have an "Include Polygons" toggle. When I try to enable it, I'm blocked by an upgrade prompt. A trial period should be for testing exactly these kinds of core features, but currently, it's impossible to evaluate this functionality. To add to the confusion, your documentation states polygons are available on Pro and Business plans, while the pricing page only lists them for the Business plan, which at 649€/month is extremely expensive and not a viable option for individual developers. This makes the paid Starter plan functionally identical to the Free plan for any developer who requires this feature, offering no real incentive to upgrade. The entire experience makes it impossible to fully test the visual mapping capabilities of your product, which is the critical feature for my decision to subscribe. For personal developer applications, even the Starter plan is quite expensive, and it's unlikely that a developer who needs polygons but not a high volume of requests would subscribe to a Pro or Business plan. My suggestion: Please consider enabling the polygon feature during the free trial period to allow for proper evaluation. Please make polygons available in the Starter plan. This would create a viable upgrade path for individual developers and small projects that need this core feature without requiring the high volume and cost of the Business plan. Thank you for your consideration. Best regards, Felix

Felix Ka 5 months ago
Completed
Make Polygons Available in Free Trial and Starter Plan
Hello Mindee Team, I'm currently evaluating your platform with a free trial and I'm very impressed. However, I've run into a confusing issue. The "Live Test" on your website correctly shows polygon coordinates, but this data is missing when using my trial API key. This is made even more confusing because the API settings have an "Include Polygons" toggle. When I try to enable it, I'm blocked by an upgrade prompt. A trial period should be for testing exactly these kinds of core features, but currently, it's impossible to evaluate this functionality. To add to the confusion, your documentation states polygons are available on Pro and Business plans, while the pricing page only lists them for the Business plan, which at 649€/month is extremely expensive and not a viable option for individual developers. This makes the paid Starter plan functionally identical to the Free plan for any developer who requires this feature, offering no real incentive to upgrade. The entire experience makes it impossible to fully test the visual mapping capabilities of your product, which is the critical feature for my decision to subscribe. For personal developer applications, even the Starter plan is quite expensive, and it's unlikely that a developer who needs polygons but not a high volume of requests would subscribe to a Pro or Business plan. My suggestion: Please consider enabling the polygon feature during the free trial period to allow for proper evaluation. Please make polygons available in the Starter plan. This would create a viable upgrade path for individual developers and small projects that need this core feature without requiring the high volume and cost of the Business plan. Thank you for your consideration. Best regards, Felix

Felix Ka 5 months ago
In Progress
Invoice extraction: columns not recognized on subsequent pages
Hello, I need to extract elements from a table that may span multiple pages. The table header only appears on the first page. I’ve noticed that the extraction works correctly on the first page, but the model doesn’t seem to recognize the structure consistently on the following pages. I’m not using RAG at the moment because I’m targeting basic, regular invoices. I’d like to know how to solve this issue. I already tried specifying in the schema that the table columns remain consistent across all pages, but this doesn’t seem to improve the results. Could you please help me resolve this issue ? Thank you

Said El haddati 6 months ago
In Progress
Invoice extraction: columns not recognized on subsequent pages
Hello, I need to extract elements from a table that may span multiple pages. The table header only appears on the first page. I’ve noticed that the extraction works correctly on the first page, but the model doesn’t seem to recognize the structure consistently on the following pages. I’m not using RAG at the moment because I’m targeting basic, regular invoices. I’d like to know how to solve this issue. I already tried specifying in the schema that the table columns remain consistent across all pages, but this doesn’t seem to improve the results. Could you please help me resolve this issue ? Thank you

Said El haddati 6 months ago
In Progress
n8n integration
Hello, I am having a persistent authorization issue while trying to connect to the Invoice OCR API from my n8n.cloud workflow. I have already: Confirmed that the "Invoice OCR" model is active in my Mindee dashboard. Generated a brand new, clean API key from the "API keys" section of my account. Copied this new API key and created a new credential in the official Mindee node in n8n. The node is configured correctly to predict an invoice from a binary file (attachment_0 from a Gmail trigger). Despite these steps, I consistently receive a 401 Unauthorized error with the message "Invalid token provided" every time I execute the node. I have tried generating multiple new keys, and the result is always the same.

Biuro SARCO 6 months ago
In Progress
n8n integration
Hello, I am having a persistent authorization issue while trying to connect to the Invoice OCR API from my n8n.cloud workflow. I have already: Confirmed that the "Invoice OCR" model is active in my Mindee dashboard. Generated a brand new, clean API key from the "API keys" section of my account. Copied this new API key and created a new credential in the official Mindee node in n8n. The node is configured correctly to predict an invoice from a binary file (attachment_0 from a Gmail trigger). Despite these steps, I consistently receive a 401 Unauthorized error with the message "Invalid token provided" every time I execute the node. I have tried generating multiple new keys, and the result is always the same.

Biuro SARCO 6 months ago
Completed
Live test - Max retry async calls reached
I’m trying to configure a model to process tables of data from multi-page PDFs. The table structure isn’t uniform as some of the header titles have a different orientation (set vertically). The error message that returns is "Max retry async calls reached". Even when I reduce the PDF to a single page PDF it still does not return an output. Is there any particular way I should be configuring my model for a successful extraction?

Damien St. John 6 months ago
Completed
Live test - Max retry async calls reached
I’m trying to configure a model to process tables of data from multi-page PDFs. The table structure isn’t uniform as some of the header titles have a different orientation (set vertically). The error message that returns is "Max retry async calls reached". Even when I reduce the PDF to a single page PDF it still does not return an output. Is there any particular way I should be configuring my model for a successful extraction?

Damien St. John 6 months ago
Completed
Page Count Missing in V2 Inference Response
Hi Mindee team, I’ve noticed that in V2, the inference response no longer includes information about the number of pages processed for an invoice document. Is there a new recommended way to retrieve the number of processed pages in the latest version? This information was quite helpful in V1, so I’d like to understand how to access it now. Thanks in advance!

Laura Mitchell 6 months ago
Completed
Page Count Missing in V2 Inference Response
Hi Mindee team, I’ve noticed that in V2, the inference response no longer includes information about the number of pages processed for an invoice document. Is there a new recommended way to retrieve the number of processed pages in the latest version? This information was quite helpful in V1, so I’d like to understand how to access it now. Thanks in advance!

Laura Mitchell 6 months ago
In Progress
PDF Content Splitter - split multipage PDF into individual Invoices/Receipts
We need to handle scenario where a single, multi-page PDF is automatically split into separate files, each representing a distinct transaction. Use case: Client uploads a batch scan of invoices or receipts. Each transaction can also be multi-page. Example: 50 page PDF containing a mix of single page and multi-page invoices. Some can have attachments. The resulting split should ALWAYS start with 1st page of invoice. If there are attachments, these do not need to be split apart and can be part of the resulting transaction. In our experience, each invoice starts with Invoice page 1 and hence that can serve as an indicator where to split the file.

Jan Korecky 6 months ago
In Progress
PDF Content Splitter - split multipage PDF into individual Invoices/Receipts
We need to handle scenario where a single, multi-page PDF is automatically split into separate files, each representing a distinct transaction. Use case: Client uploads a batch scan of invoices or receipts. Each transaction can also be multi-page. Example: 50 page PDF containing a mix of single page and multi-page invoices. Some can have attachments. The resulting split should ALWAYS start with 1st page of invoice. If there are attachments, these do not need to be split apart and can be part of the resulting transaction. In our experience, each invoice starts with Invoice page 1 and hence that can serve as an indicator where to split the file.

Jan Korecky 6 months ago
Completed
Page-Specific Data Extraction
I’m working with a 16-page credit score report, but the information I need to extract is located only on page 8. It would be extremely useful to have the ability to target a specific page for parsing and extraction, rather than processing the entire document.

Romain Colineaux 7 months ago
Completed
Page-Specific Data Extraction
I’m working with a 16-page credit score report, but the information I need to extract is located only on page 8. It would be extremely useful to have the ability to target a specific page for parsing and extraction, rather than processing the entire document.

Romain Colineaux 7 months ago