NVIDIA

Nemotron 3 Ultra API pricing.

Nemotron 3 Ultra is NVIDIA’s model on the API market, released 4 Jun 2026. Prices are per million tokens in USD, as last read from the price list.

$0.60Input / 1M
$2.40Output / 1M
262KContext
183KMax output
Capability scores
Epoch AI
Maths1 of 4 benchmarks87
Science and knowledge1 of 2 benchmarks80
CodingNot tested by Epoch
Reasoning and puzzles1 of 2 benchmarks12
Agents and long tasksNot tested by Epoch

Each bar is this model's score in that area. The white tick marks the best score any model Epoch has tested reaches there.

Epoch Capabilities Index
146
Range 144 to 148 · #86 of 271 models Epoch has scored
Maths
87average of 1 of 4 Epoch results
OTIS Mock AIME87%
Science and knowledge
80average of 1 of 2 Epoch results
GPQA Diamond85%
Reasoning and puzzles
12average of 1 of 2 Epoch results
Mystery game puzzles20%

The index combines many benchmarks into one general-capability score; the range is how sure Epoch is of the number. Each area score is this site's average of the model's Epoch results in that area, where 0 is what guessing would score and 100 is perfect. Compare every model, and value for money →

Source: Epoch AI, Capabilities & benchmarking (licensed CC BY 4.0). Data refreshed 2 November 2026. These are Epoch's own tests; other benchmark sites can rank models differently.

Cheaper models that come close
Our working on Epoch's index
  1. GLM-5.3-Flash · Z.ai (Zhipu AI)index 153.22 · 96% cheaper
  2. Qwen3.7 Flash · Alibabaindex 144.14 (2 below) · 95% cheaper
  3. Qwen 3.5 Flash (hosted 35B-A3B) · Alibabaindex 143.61 (2 below) · 89% cheaper
  4. DeepSeek V4 Flash 0731 · DeepSeekindex 154.94 · 86% cheaper

Models within 5 points of Nemotron 3 Ultra on Epoch's Capabilities Index that cost less, comparing a typical chat mix (three parts input to one part output). A few points of index is a small difference and says nothing about your task: a place to start testing, not a verdict. Capability against price for every model.

Specification
USD per million tokens
Provider
NVIDIA
Model id
nvidia/nemotron-3-ultra-550b-a55b
Input
$0.60
Output
$2.40
Cached input
$0.12
Context window
262K tokens
Maximum output
183K tokens
Takes
text
Returns
text
Tool use
Yes
Reasoning
Yes
Released
4 Jun 2026
First tracked
17 Sept 2026

At $0.60 per million input tokens, Nemotron 3 Ultra is dearer than 195 of the 340 models on the price list.

Price changes
Tracked since 17 Sept 2026

No price change has been recorded since tracking began on 17 Sept 2026. Prices are checked every six hours, and any change is listed here and on model changes.

Want an email when this model's price changes? Tell us →

Coverage
3 stories
  1. NVIDIA Developer Blog ·
    How Full-Stack NIM Optimizations Deliver 2.5x More Users on Nemotron 3 Ultra
  2. NVIDIA Developer Blog ·
    NVIDIA Nemotron 3 Ultra Leads Open Models on Accuracy and Efficiency in Agentic RTL Coding
  3. NVIDIA Developer Blog ·
    Create a LangChain Deep Agents Harness Profile for NVIDIA Nemotron 3 Ultra to Improve Performance
Other entries for this model
More from NVIDIA
Cheapest input first
  1. Nemotron 3 Nano 30B A3B$0.060 in · $0.24 out
  2. Nemotron 3.5 Lightning$0.070 in · $0.20 out
  3. Nemotron 3.5 Super VL$0.15 in · $0.50 out
  4. Nemotron 3.5 Content Safety$0.20 in · $0.20 out
  5. Nemotron 3 Super$0.30 in · $2.40 out
  6. Switchyard— in · — out

Prices and specifications come from OpenRouter’s catalogue, last read 2 Nov 2026. A provider’s own price may differ; how this is collected.