LLM Reference

DeepSeek OCR

deepseek-ocr

Researched today

Last refreshed 2026-05-22. Next refresh: weekly.

Open SourceMultimodalVision

DeepSeek OCR is worth evaluating for vision when its provider route and context window match the workload.

Decision context: Vision task fit, 1 tracked provider route, and research from 2026-05-22.

Use it for

  • Teams evaluating vision
  • Workloads that can use a 8K context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Strict JSON or tool-calling flows

Cheapest output

$0.030

Novita AI per 1M tokens

Provider routes

1

Tracked API hosts

Quality / dollar

Unknown

No task benchmark coverage yet

Freshness

2026-05-22

Researched today

fresh

Top use-case fit

Vision

Included by capability and metadata signals in the decision map.

Provider price ladder

ProviderInput / 1MOutput / 1MRoute
Novita AI$0.030$0.030
Serverless

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

About

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.

DeepSeek OCR has a 8K-token context window.

DeepSeek OCR input tokens at $0.03/1M, output at $0.03/1M.

Capabilities

VisionMultimodal

Rankings

Specifications

Released2025-10-21
Context8K
ArchitectureDecoder Only
Specializationvision
Trainingpretrained

Created by

Advancing artificial general intelligence (AGI).

Hangzhou, Zhejiang, China
Founded 2023
Website

Providers(1)