NVIDIA-Nemotron-3-Ultra-550B-A55B API Pricing
NVIDIA-Nemotron-3-Ultra-550B-A55B on DeepInfra costs $0.50 per 1M input tokens and $2.20 per 1M output tokens (as of ).
| Input | $0.50 / 1M tokens |
|---|---|
| Output | $2.20 / 1M tokens |
| Cached input (read) | $0.10 |
| Cache write | — |
| Batch input / output | — |
| Above 200K tokens (input / output) | — |
| Context window | 262K tokens |
| Max output | — tokens |
| Supports | vision, tool calling, reasoning, prompt caching |
| Deprecation date | None listed |
| API model id | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B |
| In our records since |
What it costs for common jobs
Estimated from the list price above (no caching or batch discount).
| Job | Estimated cost |
|---|---|
| 1,000 chat replies (2,000 tokens in, 500 out each) | $2.10 |
| Summarising 100 long documents (50,000 in, 1,000 out each) | $2.72 |
| 1 million classification calls (300 in, 5 out each) | $161.00 |
Try your own numbers in the LLM API cost calculator.
Price history
No price change recorded since .
Similarly priced models
| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
| DeepSeek-R1-0528 | DeepInfra | $0.50 | $2.15 | $0.40 | 164K |
| Qwen3-235B-A22B-Thinking-2507 | DeepInfra | $0.30 | $2.90 | — | 262K |
| Kimi-K2.5 | DeepInfra | $0.45 | $2.25 | $0.07 | 262K |
| GLM-5 | DeepInfra | $0.60 | $2.08 | $0.12 | 203K |
| Kimi-K2-Instruct | DeepInfra | $0.50 | $2.00 | — | 131K |
| GLM-4.6 | DeepInfra | $0.50 | $2.00 | $0.10 | 203K |
| Hermes-3-Llama-3.1-405B | DeepInfra | $1.00 | $1.00 | — | 131K |
| L3.1-70B-Euryale-v2.2 | DeepInfra | $0.85 | $0.85 | — | 131K |