// NVIDIA
Nemotron 3 Ultra
A NVIDIA model. 2 prices across 2 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- —
- Lowest (DeepInfra)
- $0.5 / $2.2
- Context
- 262K
- Prices listed
- 2
Prices checked 2026-10-22Official sources linked on every rowNo estimates
01Specs at a glance
Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.
| Vendor | NVIDIA |
|---|---|
| Context window | 262K (262,144 tokens) |
| Max output | 16K |
| Input | Text |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · openmdw-1.1 (custom) · Hugging Face |
| Parameters | 561B (from weight files) |
| Released | Jun 4, 2026 |
| Model IDs | nvidia/nemotron-3-ultra-550b-a55b |
02Prices on 2 channels
Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.
| Channel | Source | Input | Output | Cache hit | Blended $ | Context | Notes |
|---|---|---|---|---|---|---|---|
| DeepInfra · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.5 | $2.2 | $0.1 | 0.925 | 262K | DeepInfra price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0); not checked against DeepInfra's own page |
| BaseTen · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.6 | $2.4 | $0.12 | 1.05 | 203K | BaseTen price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0); not checked against BaseTen's own page |
“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.
03Where you can use it
Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.
- Via OpenRouter / provider listed there
DeepInfra · BaseTen - Self-host the open weights
GPU / VRAM sizing and build plans→ - Free option
Nemotron 3 Ultra (OpenRouter)→ - Free option
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16→
04Performance
Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| GPQA Diamond | 85.3% | independent | 2026-08-10 |
| AIME (OTIS Mock AIME 2024–2025) | 86.7% | independent | 2026-08-10 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
No price change recorded since we started tracking (2026-10-10).
06More from NVIDIA
FAQ
How much does the Nemotron 3 Ultra API cost?
There is no official pay-as-you-go price in our data. The lowest listed price is $0.5 / $2.2 on DeepInfra.
What is the context window of Nemotron 3 Ultra?
262K tokens of context, up to 16K output tokens. Platforms may cap it lower – see the table.
Is Nemotron 3 Ultra open source?
Yes, the weights are published on Hugging Face (nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16). Licence: openmdw-1.1 (custom).