Back to model shop
Nvidia
Rendered from D1 model snapshot · D1 read 114msCache check: checking

nvidia/nemotron-3-ultra-550b-a55b

Open weights
Nemotron 3 Ultra 550B A55B

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

This model's cache

This model page returns the exact headers below. The page and /api/models/nvidia--nemotron-3-ultra-550b-a55b share the model:nvidia--nemotron-3-ultra-550b-a55b tag, so invalidation stays scoped to this model.

Cache key/models/nvidia--nemotron-3-ultra-550b-a55b
Cache-Controlpublic, max-age=300, stale-while-revalidate=3600
Cache-Tagcatalogmodel:nvidia--nemotron-3-ultra-550b-a55b

Workers Cache derives the key from this path/query, plus the Worker entrypoint and current Worker version.

export const Route = createFileRoute('/models/$modelSlug')({
  headers: () => ({
    'Cache-Control': 'public, max-age=300, stale-while-revalidate=3600',
    'Cache-Tag': 'catalog,model:nvidia--nemotron-3-ultra-550b-a55b',
  }),
})

Invalidate this cache tag

await ctx.cache.purge({ tags: ['model:nvidia--nemotron-3-ultra-550b-a55b'] })

Use this when one model changes and you do not want to evict the whole catalog.

NemotronReasoningTool callingTemperature control
Released
Jun 4, 2026
Last updated
Jun 4, 2026
Context window
1M tokens
Max output
128K tokens
Open weights
Yes
Family
Nemotron

Starts at

$0.5

per 1M input tokens

Output

$2.5

Sellers

4

No cart or checkout in this MVP — pick a provider below and open their docs when you're ready to use it.

Capabilities & modalities
Reasoning
Tool calling
Structured output
Attachments
InputText
OutputText
Provider shelf
Where to get Nemotron 3 Ultra 550B A55B

Sorted by lowest input price

ProviderInput / 1MOutput / 1MContext

Nvidia

nvidia/nemotron-3-ultra-550b-a55b

$0.5$2.51MDocs

OpenRouter

nvidia/nemotron-3-ultra-550b-a55b

$0.5$2.2262.1KDocs

Vercel AI Gateway

nvidia/nemotron-3-ultra-550b-a55b

$0.6$2.41MDocs

Together AI

nvidia/nemotron-3-ultra-550b-a55b

$0.6$3.6512.3KDocs
More from Nvidia