Nemotron Parse
Vision-language model excelling at retrieving text and metadata from images.
Specs
- Context
- —
- Max output
- —
- Input price
- —
- Output price
- —
- Released
- 2025-10-28
Context
- Not published
Pricing
- Not published
Modalities
- Input
- ImageText
- Output
- Text
API
- API types
Reasoning
- Not published
Info
- Status
- Active
- Released
- 2025-10-28
- Knowledge cutoff
- —
Features
- Not published
How to call
1 provider
nvidiamodel = nvidia/nemotron-parse
ocr
POSThttps://integrate.api.nvidia.com/v1/chat/completions
JSON
Standard format
{
"id": "nemotron-parse",
"object": "model",
"created": 1761609600,
"owned_by": "nvidia",
"name": "Nemotron Parse",
"api": {
"types": [
"ocr"
]
},
"limits": {
"context": null,
"input": null,
"output": null
},
"modalities": {
"input": [
"image",
"text"
],
"output": [
"text"
]
},
"reasoning": {
"supported": null,
"efforts": []
},
"pricing": null,
"features": [],
"info": {
"status": "active",
"release_date": "2025-10-28",
"knowledge_cutoff": null,
"description": "Vision-language model excelling at retrieving text and metadata from images.",
"docs": "https://build.nvidia.com/nvidia/nemotron-parse/modelcard",
"verified_at": "2026-10-11"
}
}Official sources
2