NVIDIA: Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55b
Nemotron 3 Ultra is an open-weight heavyweight from NVIDIA — 550B parameters with 55B active per token, ranking #90 of 235 on the TryAii Score. It's strongest on head-to-head chat (#32 on Chatbot Arena Elo). API pricing starts at $0.625/$3.12 per million input/output tokens, though similar scores now sell for about $1.2 per million output tokens, with 6 independent hosts serving it. It's among the fastest models we track, at roughly 28-104 tokens/sec.
Prompt $/1M
$0.625
Completion $/1M
$3.125
Context
262,144 tok
Best provider
137 tok/s · Nebius
Specs
- Model id
- nvidia/nemotron-3-ultra-550b-a55b
- Display name
- NVIDIA: Nemotron 3 Ultra
- Modality
- text->text
- Tokenizer
- Other
- Instruct type
- —
- Context length
- 262,144
- Max completion
- 32,768
- Prompt $/1M
- $0.625
- Completion $/1M
- $3.125
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionno
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Nebiusfastest | 137 |
| Crusoe | 111 |
| BaseTen | 83 |
| Together | 70 |
| Venice | 14 |
| DeepInfra | 10 |
| nvidiafastest | — |