Context
256K
Max output
256K
Serving providers
1
Cheapest input
$0.50 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
143 t/s
tokens / second
Time to first token
1.80s
latency
Headline indices
25.7
of 100
Artificial Analysis did not report this score in its latest run on Oct 14, 2026
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AIME 2026 | 90% | default | — | |||||||||||||||||
| APEX AgentsArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 2% | — | — | |||||||||||||||||
| CritPtArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 3% | — | — | |||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 1042.6 | default | — | |||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 698.1 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA DiamondArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 80% | — | — | |||||||||||||||||
| Humanity's Last ExamArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 21% | — | — | |||||||||||||||||
| IFBenchArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 71% | — | — | |||||||||||||||||
| IT-Bench SREArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 1% | — | — | |||||||||||||||||
| Long-Context ReasoningArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 60% | — | — | |||||||||||||||||
| Mlcr OverallFrozen Sep 9, 2026 | 0.0 | default | — | |||||||||||||||||
| OmniscienceArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | -41.5 | — | — | |||||||||||||||||
| Omniscience AccuracyArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 0.2 | — | — | |||||||||||||||||
| Omniscience Non HallucinationArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 0.1 | — | — | |||||||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 36% | — | — | |||||||||||||||||
| SWE-bench Verified | 60% | default | — | |||||||||||||||||
| TerminalBench HardArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 29% | — | — | |||||||||||||||||
| TerminalBench v2.1Artificial Analysis did not report this score in its latest run on Oct 14, 2026 | 39% | — | — | |||||||||||||||||
| τ-bench BankingArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 10% | — | — | |||||||||||||||||
| τ²-benchArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 68% | — | — | |||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CloudflareCheapest | $0.50 | $1.50 | 1 | ||||||||||
Standardcloudflare/@cf/nvidia/nemotron-3-120b-a12b
| |||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Price history is accruing. We record a point each day a listed seller price changes; the full backfill lands shortly.
Cost calculator
estimate your monthly spend on this model$220
estimated / month
Model IDs
copy the exact identifier for your platformcloudflare/@cf/nvidia/nemotron-3-120b-a12b
Frequently asked questions
Nemotron 3 120B A12b pricing, context and availabilityHow much does Nemotron 3 120B A12b cost?
Nemotron 3 120B A12b costs $0.50 per 1M input tokens from Cloudflare, and $1.50 per 1M output tokens from Cloudflare.
What is the context window of Nemotron 3 120B A12b?
Nemotron 3 120B A12b accepts up to 256K tokens of context and can return up to 256K output tokens.
What can Nemotron 3 120B A12b do?
Nemotron 3 120B A12b supports tool use and reasoning.
Other NVIDIA models
compare pricing across the NVIDIA lineupNvidia Nemotron Nano 9B V2$0.04/1M · 4 providersNemotron 3 Nano 30B A3B$0.05/1M · 4 providersNemotron 3 Ultra$0.60/1M · 4 providersNemotron 3.5 Lightning$0.05/1M · 3 providersNemotron 3 Super$0.08/1M · 3 providersNvidia Nemotron 3 Ultra 550B A55b$0.50/1M · 3 providersNvidia Nemotron Nano 12B V2$0.20/1M · 2 providersLlama 3.1 Nemotron 70B Instruct$0.60/1M · 2 providers
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI