NVIDIA
Nemotron 3 Ultra
Released 2026-06-04
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
You send / 1M
$0.600
tokens in
It replies / 1M
$2.40
tokens out
Memory
262K
tokens it can read at once
Typical request
Free
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · fp4 | $0.400 | $1.76 | 100% | Read |
| DeepInfra · fp4 | $0.500 | $2.20 | 100% | Read |
| BaseTen · fp4 | $0.600 | $2.40 | 87% | Read |
| BaseTen · fp4 | $0.600 | $2.40 | 90% | Read |
| Venice · fp8 | $0.625 | $3.13 | 65% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 183K tokens
- Repeated text is billed at $0.120 per 1M (prompt caching)
- Intelligence score: 22.9 / 100 (Artificial Analysis)
Similar models
Appears in
Top Free AI ModelsTop Free No-Training AI ModelsTop Free No-Training Zero Data Retention AI ModelsTop Free No-Training Reasoning AI ModelsTop Free No-Training Tool-Calling AI ModelsTop Free Zero Data Retention AI ModelsTop Free Zero Data Retention Reasoning AI ModelsTop Free Zero Data Retention Tool-Calling AI Models