DeepSeek logo

DeepSeek: DeepSeek OCR 2

High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes

Source-linked Open weights Released 2026-01-27
API record Report
InputT
OutputT
Input price$0.03/M
Output price$0.03/M
Context8.192K
Max output8.192K
Providers2
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering DeepSeek OCR 2
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Regolo AI deepseek-ocr-2 4K 4K Not listed Docs ↗
NovitaAI deepseek/deepseek-ocr-2 8.192K 8.192K $0.03 $0.03 Not listed Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.03/M

Across 1 priced provider

Median input $0.03/M

Midpoint of listed rates

Highest input $0.03/M

Same as the lowest listed rate

Output range $0.03 – $0.03

Per million output tokens

NovitaAI $0.03/MLowest
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 4K to 8.192K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No
× Tool calling No
? Structured output Unknown
Attachments Yes
Vision input Yes
Open weights Yes
Creator
DeepSeek
Model family
Not documented
Knowledge cutoff
Not documented
License
Not documented
Release date
2026-01-27
Model ID
deepseek/deepseek-ocr-2
Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology
Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
No changes recorded

This record has not changed within the retained import history.

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/deepseek/deepseek-ocr-2
curl
curl "https://www.modelbench.lol/api/v1/models/deepseek/deepseek-ocr-2"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is DeepSeek OCR 2?

High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes. It is published by DeepSeek and catalogued here from Models.dev.

How much does DeepSeek OCR 2 cost?

Listed input pricing starts at $0.03 per million tokens from NovitaAI.

What is the context length of DeepSeek OCR 2?

DeepSeek OCR 2 accepts up to 8.192K tokens of context and returns up to 8.192K output tokens.

Does DeepSeek OCR 2 support tool calling and structured output?

Provider catalogs list support for image input.

Which providers serve DeepSeek OCR 2?

2 providers list this model: Regolo AI, NovitaAI.

Are the weights for DeepSeek OCR 2 open?

Yes. The weights are published.

When was DeepSeek OCR 2 released?

The catalog records a release date of 2026-01-27, last verified Aug 08, 2026.

More models from DeepSeek

View all →