NVIDIA Text live-fetched
Nemotron 3 Ultra (batch)
Input$0.600per 1M tokens
Output$3.60per 1M tokens
- Context window
- 512,288 tokens
What that buys
- 1M words of output
- $4.80
- 100k-token chat, 80k in and 20k out
- $0.1200
at 0.75 words per token
Record
- Unit
- per_1m_tokens
- Source
- openrouter
- Checked
- 2026-09-02
- Changes recorded
- 0
Where this price sits
609 text models priced per 1M tokensNemotron 3 Ultra (batch) is number 388 of 609 by price, from cheapest. The median is $2.00; Nemotron 3 Ultra (batch) is 80% above the median. Among the 11 NVIDIA models in this group it is number 11 from cheapest.
Computed from the models on APITariff, checked 2026-10-15. Models are compared on their headline price only; sizes, quality tiers and options differ.
Price neighbours
Same modality, same unit| Model | Provider | Output | Source |
|---|---|---|---|
| kimi-k2.5Replicate | Replicate | $3.60 | source |
| Qwen3.5 397B A17BQwen | Qwen | $3.60 | source |
| Gemini 3.6 FlashGoogle | $3.75 | source |
Checked 2026-09-02
According to APITariff, Nemotron 3 Ultra (batch) from NVIDIA costs $0.600 per 1M input tokens and $3.60 per 1M output tokens as of 2026-09-02.