CheapestCoding Long-contextBest value Get an API key
🎯 Don't want to pick? Send model: "appmo/auto" and Appmo routes each request to the cheapest model that's good enough — cutting your bill up to 40%. See how →
Models › nvidia › NVIDIA: Nemotron 3 Ultra

NVIDIA: Nemotron 3 Ultra — pricing & benchmarks

By nvidia · Updated 2026-07-24 · step-by-step reasoning

NVIDIA: Nemotron 3 Ultra costs $0.5 per 1M input tokens and $2.2 per 1M output tokens, with a 262K context window. It is best suited for step-by-step reasoning, and is available through one OpenAI-compatible Appmo API key.
$0.5Input / 1M
$2.2Output / 1M
262KContext
—Intelligence
—Coding
—GPQA %
—Speed tok/s

What NVIDIA: Nemotron 3 Ultra is used for

NVIDIA: Nemotron 3 Ultra is best suited for step-by-step reasoning. Access it through one Appmo API key alongside 390 other models — Appmo's optimizer can route to it automatically when it is the best value for a request.

Use it via the Appmo API (OpenAI-compatible)

curl https://appmo.com/v1/chat/completions \
  -H "Authorization: Bearer $APPMO_KEY" \
  -d '{"model":"nvidia/nemotron-3-ultra-550b-a55b","messages":[{"role":"user","content":"Hello"}]}'

FAQ

How much does NVIDIA: Nemotron 3 Ultra cost?
NVIDIA: Nemotron 3 Ultra costs $0.5 per 1M input tokens and $2.2 per 1M output tokens ($0.925 blended), as of 2026-07-24. Prices are expected to fall as competition increases.

What is NVIDIA: Nemotron 3 Ultra best for?
NVIDIA: Nemotron 3 Ultra is best suited for step-by-step reasoning.

How do I use NVIDIA: Nemotron 3 Ultra?
Send requests to Appmo's OpenAI-compatible endpoint with model id "nvidia/nemotron-3-ultra-550b-a55b" and one API key — no separate provider account needed.