TrOCR Large
trocr-largeMicrosoft TrOCR large transformer-based OCR. End-to-end visual encoder plus text decoder, trained on synthetic and printed real-world data.
- Status
- Unavailable
- Input β output
- Text + Image β Text
- Developer
- Microsoft
- Updated
- 25 June 2026
TrOCR Large is currently unavailable
Currently unavailable: this model has been deactivated.
You can still read the details on this page. Pick one of the available alternatives below to run a comparable model right away.
Go to alternativesComparable models
All in this category- BLIPSalesforce
Salesforce BLIP. Vision-language model for image captioning and visual question answering. Given an image it writes a short natural-language caption, or answers a question about the image when one is supplied. A widely used baseline for automatic captioning.
β US$0.00030/run
- Claude Opus 4.7Anthropic
Anthropic's April 2026 flagship. 87.6% on SWE-bench Verified, 3x higher image resolution, output self-verification, vision + reasoning.
US$6.00/1M in
- Claude Sonnet 4.6Anthropic
Anthropic's balanced mid-tier model from February 2026. Best price/performance for production workloads: 5x cheaper than Opus, near-flagship quality.
US$3.60/1M in
Playground
Try TrOCR Large
No input form
Currently unavailable: this model has been deactivated.
The playground is disabled. You can find comparable models in the same category: Browse alternatives
About TrOCR Large
TrOCR Large is a model by Microsoft in the Multimodal category. TrOCR Large is currently not available on Railwail.
Pricing
Currently unavailable: this model has been deactivated. There is no price for this model at the moment, so it cannot be run.
API
No verified API example
The public API passes a different input format than this model needs. Use the playground above.
Specifications
- Model ID
trocr-large- Developer
- Microsoft
- Category
- Multimodal
- Input
- Text, Image
- Output
- Text
- Catalog entry updated
- 25 June 2026
Tags
- replicate
- ocr
- vision-understanding
- microsoft
- open-source
Frequently asked questions
What is TrOCR Large?
TrOCR Large is a model by Microsoft in the Multimodal category. It is listed on Railwail but cannot be run at the moment.
How much does TrOCR Large cost on Railwail?
TrOCR Large cannot be run on Railwail at the moment, so there is no current price. Available alternatives with prices are listed further down this page.
How fast is TrOCR Large?
There are not enough measured runs of TrOCR Large on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.
Is TrOCR Large better than BLIP?
That depends on the task. TrOCR Large (Microsoft) and BLIP (Salesforce) are both models in the Multimodal category. The comparison page shows their prices and specifications side by side.
Compare TrOCR Large and BLIPCan TrOCR Large process images?
Yes. TrOCR Large accepts images as input in addition to text.
Can I use TrOCR Large right now?
Currently unavailable: this model has been deactivated. The page stays online; available alternatives from the same category are listed further down.
All models through one API
One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = US$0.01.