NVIDIA: Nemotron 3 Ultra API pricing on OpenRouter
- id
- nvidia/nemotron-3-ultra-550b-a55b
- nvidia
- First seen 2026-11-07 13:53 UTC
- Open on openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b
RouteNot disclosedvia BaseTen + DeepInfra + Venice + 1 more
Basis: OpenRouter endpoints: BaseTen (baseten): third_party; DeepInfra (deepinfra): third_party; Venice (venice): third_party; KT (kt): undisclosed — provider not mapped to the maker yet Archived copy
Current prices
Per million input tokens1
| Variant | USD | Platform’s own wording | Since |
|---|---|---|---|
| via KT | $0.5/M in | prompt: 0.0000005 / token (endpoint kt) |
Per million output tokens1
| Variant | USD | Platform’s own wording | Since |
|---|---|---|---|
| via KT | $2.2/M out | completion: 0.0000022 / token (endpoint kt) |
Per million cached input tokens (read)1
| Variant | USD | Platform’s own wording | Since |
|---|---|---|---|
| via KT | $0.1/M cache read | input_cache_read: 0.0000001 / token (endpoint kt) |
Change log
No changes yet. A platform’s first run sets the baseline; changes appear from the next one.
Earlier versions
| Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|
| $0.6/M in | prompt: 0.0000006 / token | 2026-11-07 13:53 UTC → 2026-11-11 16:55 UTC | |
| $2.4/M out | completion: 0.0000024 / token | 2026-11-07 13:53 UTC → 2026-11-11 16:55 UTC | |
| Cache read | $0.12/M cache read | input_cache_read: 0.00000012 / token | 2026-11-07 13:53 UTC → 2026-11-11 16:55 UTC |
Where these prices come from
Read from the platform’s public pages and APIs. Every read is archived, so any price here can be checked against what the platform showed at the time.
- openrouter.ai/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b/endpointsLast read 6 h ago1 readsArchived copy
- openrouter.ai/api/v1/modelsLast read 4 days ago1 readsArchived copy