Capabilities
7-day heat trend
−28.9%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 22% of tracked models
- Faster than 48% of tracked models
- Efficiency rank: #134 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About nvidia/Nemotron-120B-A12B
Baseten Model API route for Nemotron Super, adding a long-context NVIDIA reasoning row with managed Model API pricing fields.
nvidia/Nemotron-120B-A12B is a Text model from Baseten Model APIs (US). HotON.ai tracks it at $0.30 per 1M input tokens and $0.75 per 1M output tokens, with a 202K-token context window, ~147 tokens/sec throughput and 96.6% availability. Its composite efficiency score is 90/100 at an estimated $0.001 per successful task.
Compare nvidia/Nemotron-120B-A12B
Related market news
Frequently asked questions
How much does nvidia/Nemotron-120B-A12B cost per 1M tokens?+
nvidia/Nemotron-120B-A12B is tracked at $0.30 per 1M input tokens and $0.75 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.64 per 1M tokens. Figures are illustrative demo data.
What is nvidia/Nemotron-120B-A12B best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is nvidia/Nemotron-120B-A12B?+
nvidia/Nemotron-120B-A12B delivers about 147 tokens/sec with 96.6% tracked availability, suitable for latency-sensitive, real-time applications.
Is nvidia/Nemotron-120B-A12B cheaper than other AI models?+
Within the HotON.ai tracked set, nvidia/Nemotron-120B-A12B is cheaper than 22% of models on input price and ranks #134 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.