Text model
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B pricing
DeepInfra charges $0.50 per million input tokens and $2.20 per million output tokens for nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B, and $0.10 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.50/ 1M
- Output
- $2.20/ 1M
- Cached input
- $0.10/ 1M
- Context
- 262.1Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.50 | $2.20 | $0.10 | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.00163 | 100,000 | $163.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.0025 | 100,000 | $250.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00456 | 250,000 | $1,140.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| deepinfra/NousResearch/Hermes-3-Llama-3.1-70B | $0.00133 | 18% |
| deepinfra/zai-org/GLM-4.7 | $0.0013 | 20% |
| sambanova/Meta-Llama-3.3-70B-Instruct | $0.00138 | 15% |
| databricks/databricks-llama-4-maverick | $0.00135 | 17% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: DeepInfra pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.