# Nemotron Super (latest)

> Always resolves to the newest live Nemotron Super model — currently Nemotron-3 Super 120B (nvidia/nemotron-3-super-120b-a12b). A 120 billion parameter model from NVIDIA's Nemotron-3 family, optimized for efficient text generation and understanding tasks.

**ID**: `nvidia/nemotron-super-latest`  
**Creator**: nvidia  
**Category**: text  
**Context**: 262K tokens  
**Family alias**: always resolves to the newest live family member — currently [`nvidia/nemotron-3-super-120b-a12b`](https://anyrouter.dev/model/nvidia/nemotron-3-super-120b-a12b). Specs below are nvidia/nemotron-3-super-120b-a12b's.  
**Fallback order**: `nvidia/nemotron-3-super-120b-a12b`  
**Pricing**: $0.09 / $0.40 per 1M · billed by your provider (BYOK)  
**Released**: 2024-01-01  
**Web page**: https://anyrouter.dev/model/nvidia/nemotron-super-latest

**Input modalities**: text  
**Output modalities**: text  

**Capabilities**: chat, reasoning, function-calling, streaming, coding

**Aliases**: `nvidia/nemotron-3-120b-a12b`

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nvidia/nemotron-super-latest",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| aihubmix-byok | $0.50/M (list) | $1.50/M (list) |
| openrouter-byok | $0.50/M (list) | $1.50/M (list) |
| vercel-byok | $0.15/M (list) | $0.65/M (list) |
| deepinfra-byok | $0.09/M (list) | $0.40/M (list) |
| nousresearch-byok | $0.08/M (list) | $0.45/M (list) |
| inference-net-byok | $0.10/M (list) | $0.48/M (list) |
| infron-byok | $0.10/M (list) | $0.50/M (list) |
| getvibe-byok | $0.14/M (list) | $0.67/M (list) |
| aimlapi-byok | $0.10/M (list) | $0.48/M (list) |
| ollama-byok | $0.50/M (list) | $1.50/M (list) |
| requesty-byok | $0.50/M (list) | $1.50/M (list) |
| nano-gpt-byok | $0.50/M (list) | $1.50/M (list) |
| fluence-byok | $0.15/M (list) | $0.75/M (list) |
| kenari-byok | $0.50/M (list) | $1.50/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Benchmarks

- **GPQA Diamond**: 0.8
- **HLE**: 0.2

## Source

- Upstream docs: https://build.nvidia.com/nvidia/nemotron-3-super-120b-a12b