High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes
- Context
- 8K
- Released
- 8mo ago
- Parameters
- —
Sources:models.dev
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- DeepSeek
- Model family
- DeepSeek
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- January 27, 2026
- Model ID
deepseek/deepseek-ocr-2- Openness
- Open weights
- License
- —
- Parameters
- —
- Input modalities
- text, image
- Output modalities
- text
- Modality
- text+image->text
- Max output tokens
- 8K
- Hugging Face
- —
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- deepseek/deepseek-ocr-2
- Last updated
- 2026-01-27
- Model context
- 8K
- Model output limit
- 8K
- Open weights
- Yes
- File attachments
- Yes
- Reasoning
- No
- Tool calling
- No
Complete source record (JSON)
{
"id": "deepseek/deepseek-ocr-2",
"name": "DeepSeek OCR 2",
"description": "High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes",
"last_updated": "2026-01-27",
"attachment": true,
"reasoning": false,
"tool_call": false,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"release_date": "2026-01-27",
"open_weights": true
}Infrastructure
Provider availability
Provider endpoint data will appear after this model's first OpenRouter endpoint sync.
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.