Skip to content
nvidia/nemotron-parse-2.0

8K context · Aug 2026 · 2 upstreams

NVIDIA Nemotron Parse 2.0 is a document-understanding VLM: page image in, structured text out (markdown, layout classes, bounding boxes, reading order). Served via NVIDIA NIM OpenAI-compatible /v1/chat/completions. Not image generation.

context
8K
input / 1M
$0
output / 1M
$0
routes
2
speed, 24h
—

Upstreams

2
  1. 1NVIDIAPlatform · freeFreeTPS —TTFT ——
  2. 2NVIDIAYour key · not addedyour planTPS —TTFT ——
  • Up
  • No traffic
  • Down

Try it

Send a prompt

Details

Owner
NVIDIA
Kind
Vision
Released
Aug 2026
Context
8K
Data policy
Provider retention
Endpoint
/api/v1/chat/completions

Quick start

curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nvidia/nemotron-parse-2.0",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'