Baseten
99.78%Context1M
Max output65K
p50 latency2,239 ms
Throughput213.0 t/s
Input price$0.6
Output price$2.4
Zero retentionNo training
Model directory
Baseer model profileLanguage model
nvidia/nemotron-3-ultra-550b-a55b
Nemotron 3 Ultra
A 550B parameter (55B active) open reasoning model from NVIDIA, built for long-running agent workflows. It uses a hybrid Mamba-Transformer MoE architecture and supports a 1M token context window.
Input / 1M tokens$0.5
Output / 1M tokens$2.4
Maximum context1M
Inference providers4
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Deepinfra
99.98%Context262.1K
Max output65K
p50 latency888 ms
Throughput173.0 t/s
Input price$0.5
Output price$2.5
Zero retentionNo trainingCaching
Fireworks
100.00%Context262K
Max output262K
p50 latency269 ms
Throughput171.0 t/s
Input price$0.6
Output price$2.4
Zero retentionNo training
Togetherai
0.00%Context1M
Max output65K
p50 latency—
Throughput—
Input price$0.6
Output price$3.6
Zero retentionNo trainingCaching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Baseten | 1M | 65K | 2,239 ms | 213.0 t/s | 99.783% | $0.6 | $2.4 | |
Deepinfra | 262.1K | 65K | 888 ms | 173.0 t/s | 99.979% | $0.5 | $2.5 | |
Fireworks | 262K | 262K | 269 ms | 171.0 t/s | 99.999% | $0.6 | $2.4 | |
Togetherai | 1M | 65K | — | — | 0.000% | $0.6 | $3.6 |
What can this model do?
Available modalities and capabilities across inference providers.
TextAdvanced reasoningTool useAutomatic cachingTools
Technical profile
- Model type
- Language model
- Release date
- Jun 4, 2026
- Knowledge cutoff
- —
- Regions
- US
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
nvidia/nemotron-3-ultra-550b-a55bModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.