Nemotron 3 Super API pricing
Nvidia · Budget price tier · NVIDIA Open Model License · released 2026-03. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
A support ticket workload of 100K requests a month costs $31.25 on Nemotron 3 Super; the next cheaper model in the Budget price tier for this workload, Qwen3 30B A3B Instruct 2507, does it for $30.00. The price we quote for Nemotron 3 Super has changed 5 times since 2026-08-15, most recently on 2026-11-06 when the quoted host changed (-82.9%); it is now the 61st cheapest of 160 models in the Budget price tier. None of its 2 hosts undercuts the price we quote. It is rated a stable release but does not meet all four criteria of the FinOps Friendly badge.
- Input: $0.075 per 1M tokens
- Output: $0.40 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: Not published
- Context window: 262K tokens
- Arena ELO: 1377 as of 2026-11-08
Available on
AWS Bedrock regions: ap-northeast-1, eu-central-1, eu-west-1, us-east-1, us-east-2, us-west-2
Market position
On blended price ($0.3025 per 1M tokens at 30% input, 70% output) it is cheaper than 62% of models in the Budget price tier: 61st cheapest of 160. Across every price tier it is cheaper than 80% of priced text models in the catalogue: 61st cheapest of 303. Its Arena ELO of 1377 ranks 111th of the 160 models that carry one, above 31% of them. With an Arena score of 1377, Nemotron 3 Super sits below OptimNow's lowest working quality threshold, Standard (Arena 1420+), so the quality-bar method would not shortlist it for any of the 8 use cases the table prices. Each threshold is a distance below the best ranked model, which scores 1530 on Arena scores as of 8 Nov 2026.
Licence, size and capabilities
Nemotron 3 Super is open weights, which is not the same as open source: the weights are published, but under NVIDIA Open Model License, a licence that restricts some uses. Read it before self-hosting commercially. Its published size is 120B parameters. Listed capabilities: Text, Reasoning, Agents. Filling its 262K context window once costs $0.0197 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 2 different hosts. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
The price we quote is already the cheapest of the 2 hosts: DeepInfra at $0.075 input / $0.40 output per 1M tokens. The dearest, DekaLLM, charges 1.1x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| DeepInfra (price we quote) | $0.075 | $0.40 | bf16 |
| DekaLLM | $0.08 | $0.45 | fp8 |
List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown. These hosts do not all serve the model at the same numeric precision, so the cheapest is not a like-for-like substitute for the dearest.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where Nvidia publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $31 |
| Knowledge Q&A | 2,000 / 800 | $47 |
| Meeting Summary | 10,000 / 1,200 | $123 |
| Marketing Content | 2,500 / 1,800 | $91 |
| Coding Task | 3,000 / 2,000 | $103 |
| Invoice Processing | 1,500 / 600 | $35 |
| Call Summary | 2,000 / 700 | $43 |
| Agent Workflow | 6,000 / 3,000 | $165 |
Price history
Nemotron 3 Super has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.085 input / $0.40 output per 1M tokens. The price we quote has changed 5 times since then, every time through a change of quoted host rather than a repricing. The latest change, on 2026-11-06, was -82.9% on the blended price (30% input, 70% output), to $0.075 input / $0.40 output (quoted host changed, not a repricing). Net of all changes, the blended price is -1.0% against 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-11-06 | $0.30 / $2.40 | $0.075 / $0.40 | -82.9% (quoted host changed, not a repricing) |
| 2026-10-22 | $0.08 / $0.45 | $0.30 / $2.40 | +422.1% (quoted host changed, not a repricing) |
| 2026-10-09 | $0.085 / $0.40 | $0.08 / $0.45 | +11.0% (quoted host changed, not a repricing) |
| 2026-10-08 | $0.08 / $0.45 | $0.085 / $0.40 | -9.9% (quoted host changed, not a repricing) |
| 2026-09-14 | $0.085 / $0.40 | $0.08 / $0.45 | +11.0% (quoted host changed, not a repricing) |
Alternatives to Nemotron 3 Super
1 of the 4 comparable models below costs less than Nemotron 3 Super: Qwen3 30B A3B Instruct 2507 undercuts it by 21%, and scores 7 Arena points higher.
- Next cheaper model in the Budget price tier: GLM 4.7 Flash (Zhipu) at $0.2981 blended, 1% less.
- Next more expensive: Seed-2.0-Mini (ByteDance) at $0.31 blended, 2% more.
The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against Nemotron 3 Super.
- GLM 4.6V (Zhipu): $0.30 in / $0.90 out per 1M, Arena ELO 1376 (138% more expensive, 1 ELO point lower)
- DeepSeek V3 0324 (DeepSeek): $0.29 in / $1.14 out per 1M, Arena ELO 1375 (193% more expensive, 2 ELO points lower)
- GPT-5.4 Nano (OpenAI): $0.20 in / $1.25 out per 1M, Arena ELO 1372 (209% more expensive, 5 ELO points lower)
- Qwen3 30B A3B Instruct 2507 (Alibaba): $0.10 in / $0.30 out per 1M, Arena ELO 1384 (21% cheaper, 7 ELO points higher)
- Cheapest within 15 Arena points: Qwen3 30B A3B Instruct 2507 (Alibaba), 21% cheaper, 7 ELO points higher, out of 16 models in that band.
- Highest Arena ELO within 20% of this price: DeepSeek V4.1 Flash (DeepSeek), 5% cheaper, 86 ELO points higher, out of 9 models in that price band.
Other models from Nvidia
Nvidia has 5 other models in the catalogue. Prices per 1M tokens, input then output.
- Nemotron 3.5 Lightning: $0.07 / $0.20
- Nemotron 3 Nano 30B A3B: $0.06 / $0.24
- Nemotron 3.5 Content Safety: $0.20 / $0.20
- Nemotron 3.5 Super VL: $0.15 / $0.47
- Nemotron 3 Ultra: $0.60 / $2.40
All 6 Nvidia models and prices
Common questions about Nemotron 3 Super pricing
- How much does Nemotron 3 Super cost?
- Nemotron 3 Super costs $0.075 per 1M input tokens and $0.40 per 1M output tokens at DeepInfra, the host whose rate we quote. Prices as listed on 2026-11-12.
- Which host is cheapest for Nemotron 3 Super?
- The price we quote is already the cheapest of the 2 hosts: DeepInfra at $0.075 input / $0.40 output per 1M tokens. The dearest, DekaLLM, charges 1.1x the cheapest. Host rates as listed on 2026-11-12.
- Does Nemotron 3 Super offer batch or cached pricing?
- No. Neither a batch rate nor a prompt-cache rate is published for Nemotron 3 Super as of 2026-11-12.
- What would Nemotron 3 Super cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $31 on Nemotron 3 Super at the list price quoted on 2026-11-12.
- Can Nemotron 3 Super be self-hosted?
- Yes, within the terms of its licence. Nemotron 3 Super is open weights, which is not the same as open source: the weights are published, but under NVIDIA Open Model License, a licence that restricts some uses. Read it before self-hosting commercially.
- Has the price of Nemotron 3 Super changed?
- Nemotron 3 Super has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.085 input / $0.40 output per 1M tokens. The price we quote has changed 5 times since then, every time through a change of quoted host rather than a repricing. The latest change, on 2026-11-06, was -82.9% on the blended price (30% input, 70% output), to $0.075 input / $0.40 output (quoted host changed, not a repricing). Net of all changes, the blended price is -1.0% against 2026-08-15.
Its weights are published, which changes what you may run yourself: the cost gap between open weights and proprietary APIs.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server