[ nvidia ]

llama-nemotron-rerank-vl-1b-v2

Billed at a published markup over the upstream list price. Pay per token in USDF, with no subscription and no minimum. Streaming and the OpenAI-compatible request format are supported.

← All models
llama-nemotron-rerank-vl-1b-v2·Unavailable·rerank·Context window: 10,240 tokens

No route to this model is enabled right now. Requests for it are refused with the error code model_unavailable before any balance is held, so nothing is charged. The listed prices apply once a route is enabled.

Input

$0.02

$ / 1M tokens

Cached input

—

not offered

Context window

10,240

tokens

Model ID
llama-nemotron-rerank-vl-1b-v2
Modality
rerank
Unit
USD per 1M tokens
Status
Unavailable
Last verified
—
Endpoints
/v1/rerank
Context window
10,240 tokens
Pricing basis
Markup
Cache write (5 min)
—
Cache write (1 h)
—
Routes enabled
1 of 1
Price sheet
2026-10-09.1

Routes

ProviderEnabledUpstream input
deepinfraYes$0.01

Make your first request

Responses include a receipt with the exact cost.

No account: send the same request to /x402/v1/rerank without credentials and the gateway answers 402 with the quote. Pay per request.

This model has no enabled route right now, so the request below is refused with model_unavailable until a route is enabled. Nothing is charged for a refused request.

curl https://api.usdf.fi/v1/rerank \
  -H "Authorization: Bearer $FOUNDRY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "llama-nemotron-rerank-vl-1b-v2", "query": "What is USDF?", "documents": ["USDF is a dollar for compute.", "USDG is the reserve asset."]}'