Claude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MClaude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/M
Nvidia
Nvidia
FrontierAUTO PROFILELIVE INDEX

Nemotron 3 Ultra (batch)

text->text

Nemotron 3 Ultra (batch) sits in the frontier tier — built for high-capability reasoning, tool use, and long-form output where capability outweighs cost. Available via Nvidia. 512,288-token context. Efficient pricing.

Nemotron 3 Ultra (batch) is a frontier AI model from Nvidia. It costs $0.300 per million input tokens and $1.800 per million output tokens (blended $0.750/M), with a 512,288-token context window.

INPUT
$0.300/M
per million input tokens
OUTPUT
$1.800/M
per million output tokens
CONTEXT
512,288
tokens
What it is good at
  • Strong general reasoning
  • Tool use & function calling
  • Long-form writing
  • Production-grade reliability
Typical use cases
  • Production assistants
  • Long-document analysis
  • Multi-step agent workflows
  • Engineering copilots

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from Nvidia

See all 6

Frequently asked questions

How much does Nemotron 3 Ultra (batch) cost?

Nemotron 3 Ultra (batch) costs $0.300 per million input tokens and $1.800 per million output tokens, for a blended reference rate of $0.750 per million tokens.

What is Nemotron 3 Ultra (batch)'s context window?

Nemotron 3 Ultra (batch) supports up to 512,288 tokens of context in a single request.

What is Nemotron 3 Ultra (batch) best for?

Nemotron 3 Ultra (batch) is well suited to Strong general reasoning, Tool use & function calling and Long-form writing.

Who makes Nemotron 3 Ultra (batch)?

Nemotron 3 Ultra (batch) is developed and served by Nvidia.

Terms used on this page