---
title: "Nemotron 3 Ultra 550B A55B API Pricing"
source_api: "openrouter"
model: "nvidia/nemotron-3-ultra-550b-a55b"
provider: "nvidia"
model_type: "llm"
context_window: 262144
max_output_tokens: 182520
input_modalities: ["text"]
output_modalities: ["text"]
weights_access: open_restricted
weights_license: "NVIDIA Nemotron Open Model License"
canonical_url: https://coolhandlabs.com/inference-apis/openrouter-nvidia-nemotron-3-ultra-550b-a55b
index_url: https://coolhandlabs.com/inference-apis
---

# Nemotron 3 Ultra 550B A55B sticker prices

List rates as published by OpenRouter, before any volume or enterprise discounts.

| Field | Value |
|---|---|
| Provider | nvidia (served via OpenRouter) |
| Model type | LLM — Generates text from a prompt, so it can be compared with other LLMs on price and capability. |
| Pricing published by | OpenRouter |
| Input modalities | Text |
| Output modalities | Text |
| Input cost | $0.60 / 1M tokens |
| Output cost | $3.60 / 1M tokens |
| Context window | 262,144 tokens |
| Max output tokens | 182,520 tokens per response (includes reasoning tokens) |
| Model weights | Open weights (restricted license) — NVIDIA Nemotron Open Model License |
| Cached input | $0.20 / 1M tokens |
| Capabilities | Tool calling, Structured output, Reasoning |
| Deprecated | No |
| Verification status | Awaiting human review |


## Get this data free

Want to stay updated on price changes on this model? Pull this data free (no API key required):

```
curl "https://coolhandlabs.com/api/v2/inference_apis?q%5Bmodel_eq%5D=nvidia%2Fnemotron-3-ultra-550b-a55b&q%5Bsource_api_eq%5D=openrouter"
```

Full REST API docs: https://coolhandlabs.com/docs

## Pricing History

- Aug 16, 2026 – present: Input cost: $0.60 / 1M, Output cost: $3.60 / 1M, Cached input cost: $0.20 / 1M, Cache creation cost: $0.00 / 1M, 5-minute cache write cost: $0.00 / 1M, 1-hour cache write cost: $0.00 / 1M, Reasoning output cost: $0.00 / 1M, Cache storage cost: $0.00 / 1M/hr

## History

No automated scan changes recorded yet.

- 2026-08-16 (unknown):
Initial record created

## Source

No source URL recorded yet.

## Comparable models

None identified yet.

## What other models does nvidia offer?

| Model | Input cost | Output cost | Max output tokens | Status |
|---|---|---|---|---|
| [Nemotron 3 Super Free](https://coolhandlabs.com/inference-apis/opencode-nemotron-3-super-free) (via OpenCode) | $0.00/1M | $0.00/1M | 128,000 | Deprecated 2026-08-12 |
| [NVIDIA Nemotron Nano 3 30B](https://coolhandlabs.com/inference-apis/bedrock-nvidia-nemotron-nano-3-30b) (via Bedrock) | $0.06/1M | $0.24/1M | 8,192 | Active |
| [NVIDIA Nemotron Nano 9B v2](https://coolhandlabs.com/inference-apis/bedrock-nvidia-nemotron-nano-9b-v2) (via Bedrock) | $0.06/1M | $0.23/1M | 8,192 | Active |
| [NVIDIA Nemotron 3 Super 120B A12B](https://coolhandlabs.com/inference-apis/bedrock-nvidia-nemotron-super-3-120b) (via Bedrock) | $0.15/1M | $0.65/1M | 131,072 | Active |
| [Nemotron 3.5 Lightning Free](https://coolhandlabs.com/inference-apis/opencode-nemotron-3-5-lightning-free) (via OpenCode) | $0.00/1M | $0.00/1M | 262,144 | Active |
| [Nemotron 3 Ultra Free](https://coolhandlabs.com/inference-apis/opencode-nemotron-3-ultra-free) (via OpenCode) | $0.00/1M | $0.00/1M | 128,000 | Active |

---
[← All Inference APIs](https://coolhandlabs.com/inference-apis)