NVIDIA-Nemotron-3-Ultra-550B-A55B (NVIDIA)
View on NVIDIAView on DeepInfraView on OpenRouterIdentity and capabilities
- Status
- active
- Local execution
- Available weights · transformers · other
- Context window
- 202,800
- Maximum output
- 182,520
- Image input
- No
- Reasoning
- Yes
- Tool calling
- Yes
- Release date
- First seen
- 2026-08-29 19:40:08Z UTC
- Last verified
Current offers - prices in USD · per 1M tokens
| DeepInfra | OpenRouter | |
|---|---|---|
| Cached input | $0.1 | $0.12 |
| Input | $0.5 | $0.6 |
| Output | $2.2 | $2.4 |
Active promotions
No officially confirmed promotion applies to this model.
Recent price changes
- Effective price increased · cause unverified
- Input: $0.5 → $0.6
- Output: $2.2 → $2.4