NVIDIA: Nemotron 3 Super 120B
Nemotron 3 Super 120B is a reasoning model from NVIDIA released on Mar 1, 2026. It reads text and writes text, with a 1M token context window and up to 32K tokens per reply.
Show moreShow less
It costs $0.05 per million input tokens and $0.25 per million output tokens. Cached input bills at $0.025, 50% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
17 providers serve it, including Amazon Bedrock, Vercel AI Gateway and Baseten. The lowest input price is $0.015 per million tokens at Ollama Cloud.
- Modalities
- In / out price
- $0.05 / $0.25 per 1M
- Context
- 1M
- Max output
- 32K
- Released
- Mar 1, 2026
- Knowledge cutoff
- Feb 2026
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Nemotron 3 Super 120B pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.05 / 1M tokens | |
|---|---|---|
| Output | $0.25 / 1M tokens | |
| Cached input (read) | $0.025 / 1M tokens | 50% off input |
Nemotron 3 Super 120B providers
17 providers serve it, including Amazon Bedrock, Vercel AI Gateway and Baseten. The lowest input price is $0.015 per million tokens at Ollama Cloud. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Amazon Bedrock | $0.15 | $0.65 | – | 262K | 131K |
| Vercel AI Gateway | $0.15 | $0.65 | – | 256K | 32K |
| Baseten | $0.30 | $0.75 | $0.06 | 203K | 203K |
| Nebius Token Factory | $0.30 | $0.90 | – | 262K | 33K |
| Cloudflare Workers AI | $0.50 | $1.50 | – | 256K | 256K |
| Ollama Cloud | $0.015 | $0.60 | $0.015 | 262K | 66K |
| NanoGPT | $0.05 | $0.25 | $0.025 | 262K | 16K |
| Kilo Gateway | $0.08 | $0.45 | – | 262K | 236K |
| Pioneer | $0.09 | $0.45 | $0.09 | 256K | 32K |
| Perplexity Agent | $0.25 | $2.50 | – | 1M | 32K |
| Crusoe | $0.30 | $2.40 | $0.15 | 262K | 262K |
| DigitalOcean | $0.30 | $0.65 | $0.06 | 1M | 33K |
Showing 12 of 17 providers: the lab first, then the major clouds, then the cheapest resellers.
What Nemotron 3 Super 120B costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Nemotron 3 Super 120B through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning - Temperature
temperature
Alternatives to Nemotron 3 Super 120B
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- 33K context
Reads text, images and audio. Tool calling, structured output, reasoning. Served by 2 providers.
by googleApr 2, 2026$0.10/M input tokens$0.10/M output tokens2 providers
- 33K context
Reads text. Tool calling, reasoning.
by qwenMar 31, 2025$0.10/M input tokens$0.10/M output tokens
- 131K context
Reads text. Tool calling, reasoning. Served by 3 providers.
by sarvamSep 1, 2025$0.054/M input tokens$0.2124/M output tokens3 providers
- 262K context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 5 providers.
by inclusionaiSep 8, 2026$0.06/M input tokens$0.18/M output tokens5 providers
- 524K context
Reads text. Tool calling, structured output, reasoning. Served by 2 providers.
by upstageSep 23, 2026$0.05/M input tokens$0.20/M output tokens2 providers
- 262K context
Reads text. Tool calling, structured output, reasoning. Served by 11 providers.
by nvidiaAug 11, 2026$0.05/M input tokens$0.20/M output tokens11 providers
More from NVIDIA
- 1.05M context
Reads text, images and video. Tool calling, reasoning.
by nvidiaOct 15, 2026$0/M input tokens$0/M output tokens
- Index 12.9
Reads text. Reasoning.
by nvidiaAug 11, 20261M context
- 262K context
Reads text. Tool calling, structured output, reasoning. Served by 11 providers.
by nvidiaAug 11, 2026$0.05/M input tokens$0.20/M output tokens11 providers
- Index 22.9
Reads text. Reasoning.
by nvidiaJun 4, 20261M context
- 1M context
Reads text. Tool calling, structured output, reasoning. Served by 20 providers.
by nvidiaJun 4, 2026$0.50/M input tokens$2.50/M output tokens20 providers
- 128K context
Reads text and images. Reasoning. Served by 6 providers.
by nvidiaJun 4, 2026$0.05/M input tokens$0.15/M output tokens6 providers
Nemotron 3 Super 120B questions
How much does the Nemotron 3 Super 120B API cost?
$0.05 per million input tokens and $0.25 per million output tokens, with cached input at $0.025. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Nemotron 3 Super 120B?
1,000,000 tokens of input, and it can write up to 32,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Nemotron 3 Super 120B?
17 providers serve it, including Amazon Bedrock, Vercel AI Gateway and Baseten. The lowest input price is $0.015 per million tokens at Ollama Cloud. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Nemotron 3 Super 120B support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Nemotron 3 Super 120B open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was Nemotron 3 Super 120B released?
Mar 1, 2026, with training data up to Feb 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on Nemotron 3 Super 120B?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting