US (Other)

Nemotron 3 Super API Pricing

Nemotron 3 Super costs $0.3 per 1M input tokens and $0.75 per 1M output tokens on US (Other)'s API. Cached input is billed at $0.143 per 1M tokens. Prices are provider list prices in USD, refreshed as sources update; see the Nemotron 3 Super model profile for capability scores.

Input / 1M
$0.3
Output / 1M
$0.75
Effective / 1M I/O
$1.53
Cost Rank
#31

Price List

RatePrice (USD)Notes
Input$0.3per 1M tokens
Output$0.75per 1M tokens
Cached input (read)$0.143per 1M tokens
Blended input + output$1.051M in + 1M out at list price
Context window1M tokens

What a Workload Costs

Computed straight from the list prices above — token counts are illustrative workload sizes, not measurements of Nemotron 3 Super.

WorkloadCostTokens
Short chat turn$0.000681K in / 500 out
Summarize a long document$0.032100K in / 2K out
Agentic coding session$0.225500K in / 100K out
1M input + 1M output tokens$1.051M in / 1M out

Effective Cost

In AI IQ's scoring, Nemotron 3 Super's list price is adjusted by a token-usage multiplier of 1.458, giving an effective cost of $1.53 per 1M input + output tokens. That places it #31 of 117 models on the effective-cost ranking (lower is cheaper). Some models spend far more tokens than others on the same task, so effective cost compares what a unit of work really costs. Method details are on the methodology page; see all models on the cost charts and the falling cost of intelligence over time.

Cheaper Alternatives at Similar Capability

Models with a lower effective cost that score within a few IQ points of Nemotron 3 Super (IQ 103), or better.

ModelProviderIQEffective Cost / 1M
deepseek-v4-flashDeepSeek113$1.39
deepseek-v4-flash-vision-expDeepSeek113$1.39
Agnes 2.5 Pro BetaWorld (Other)111$1.22
mimo-v2.5Xiaomi109$0.9553
Inkling-SmallUS (Other)106$1.01
mimo-v2-flashXiaomi105$0.6716

Compare