NVIDIA: Nemotron 3 Super pricing
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. NVIDIA: Nemotron 3 Super from OpenRouter costs $0.080 per 1M input tokens and $0.450 per 1M output tokens. Context window 262,144 tokens.
API id nvidia/nemotron-3-super-120b-a12b · OpenRouter · source · updated 2026-09-25 · general-purpose
NVIDIA: Nemotron 3 Super specifications
- Provider
- OpenRouter
- API id
nvidia/nemotron-3-super-120b-a12b- Model type
- general-purpose
- Context window
- 262K tokens
- Max output
- 236K tokens
- Currency
- USD
- Price source
- Provider API
- Last checked
- 2026-09-25
NVIDIA: Nemotron 3 Super across providers
The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.
| Provider | Input /1M | Cached /1M | Output /1M | 1M in + 1M out | vs vendor |
|---|---|---|---|---|---|
| $0.080 | — | $0.450 | $0.53 | — |
- OpenRouter
nvidia/nemotron-3-super-120b-a12b:free
Free routes are rate-limited, can rotate off the roster without notice, and may differ in context, tools or caching from the paid door. Always confirm on the provider's page before depending on one.
What NVIDIA: Nemotron 3 Super costs in practice
| Workload | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0003 |
| Document summary | 50,000 | 2,000 | $0.0049 |
| 1M tokens in, 200K out | 1,000,000 | 200,000 | $0.17 |
Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.
NVIDIA: Nemotron 3 Super price history
| Recorded | Input /1M | Output /1M |
|---|---|---|
| 2026-09-15 | $0.080 | $0.450 |
| 2026-08-27 | $0.085 | $0.400 |
Common questions
- How much does NVIDIA: Nemotron 3 Super cost per 1M tokens?
- NVIDIA: Nemotron 3 Super costs $0.080 per 1M input tokens and $0.450 per 1M output tokens on the standard tier.
- What is NVIDIA: Nemotron 3 Super's context window?
- NVIDIA: Nemotron 3 Super accepts up to 262,144 tokens in a single request, and can return up to 235,929 output tokens.
- Is there a cheaper OpenRouter model than NVIDIA: Nemotron 3 Super?
- Yes. Mistral: Mistral Nemo is $0.019 per 1M input tokens versus $0.080 for NVIDIA: Nemotron 3 Super, with a 131,072 token context window.
- Where does this NVIDIA: Nemotron 3 Super price come from?
- From the OpenRouter catalogue, because OpenRouter does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from OpenRouter's own — verify before committing spend.
Head-to-head comparisons
Other OpenRouter models
- Fireworks: Ember-1 $3.00
- Z.ai: GLM 5.3 Prime $2.80
- Qwen: Qwen3.8 Max Prime $4.00
- Space Bunny Alpha Free
- AionLabs: Aion 3.5 Mini $0.700
- AionLabs: Aion 3.5 $3.00
- Upstage: Solar Mini 4 $0.050
- Cohere: Command A+ $0.300
- OpenAI: GPT-6 Luna Pro $0.100
- OpenAI: GPT-6 Luna $0.100
- OpenAI: GPT-6 Sol Pro $2.00
- OpenAI: GPT-6 Sol $2.00
- Anthropic: Claude Opus 5.5 $4.00
- Xiaomi: MiMo-V2.6-Pro-UltraSpeed $4.35
- Xiaomi: MiMo-V2.6-Flash $0.140
- Xiaomi: MiMo-V2.6-Pro $0.435