Last refreshed 2026-05-22. Next refresh: weekly.
Why use DeepSeek OCR on Novita AI?
Novita AI offers DeepSeek OCR with pay-as-you-go pricing at $0.03/1M input tokens. Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: deepseek-ocrdeepseek-ocrRequest example
Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.03 |
| Output tokens | $0.03 |
Capabilities
About DeepSeek OCR
DeepSeek OCR is a specialized vision-language model for optical character recognition and document parsing from DeepSeek. It introduces Contexts Optical Compression, a novel approach to efficiently process documents. Released with arXiv paper 2510.18234 (October 2025). Available on vLLM from October 23, 2025.
FAQ
What does DeepSeek OCR cost on Novita AI?
On Novita AI, DeepSeek OCR costs $0.03 per 1M input tokens and $0.03 per 1M output tokens.
What is the context window for DeepSeek OCR on Novita AI?
DeepSeek OCR supports a 8,192 token context window on Novita AI.
What API model ID do I use for DeepSeek OCR on Novita AI?
Use the model ID deepseek-ocr when calling Novita AI's API.
Who created DeepSeek OCR?
DeepSeek OCR was created by DeepSeek as part of the DeepSeek OCR model family.
Is DeepSeek OCR open source?
DeepSeek OCR is open source according to the seed data.