# Cheapest Nemotron 3 Ultra API providers, compared (prices checked Nov 7, 2026)

URL: https://ernd.ai/inference-prices/nemotron-3-ultra-550b-a55b

> ernd partners with [Wafer](https://ernd.ai/partners/wafer). Prices are from OpenRouter's public listings.

Nemotron 3 Ultra is an open-weight model from NVIDIA. On OpenRouter, 5 listings from 3 providers sell it, and the blended price runs from $0.74 to $1.25 per million tokens.

| Provider | Input /1M | Output /1M | Blended 3:1 | Cache read /1M | Context | Quantization | Latency | Throughput |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| DeepInfra (Flex) | $0.40 | $1.76 | $0.74 | $0.08 | 262K | FP4 | 2.37 s | 50 tok/s |
| DeepInfra | $0.50 | $2.20 | $0.925 | $0.10 | 262K | FP4 | 1.09 s | 55 tok/s |
| Baseten | $0.60 | $2.40 | $1.05 | $0.12 | 203K | FP4 | 0.26 s | 103 tok/s |
| Baseten (US) | $0.60 | $2.40 | $1.05 | $0.12 | 203K | FP4 | 0.27 s | 108 tok/s |
| Venice | $0.625 | $3.13 | $1.25 | $0.188 | 256K | FP8 | 1.40 s | 41 tok/s |

Blended is three parts input price to one part output, per million tokens. Latency is time to first token and throughput is output tokens per second, both averaged from OpenRouter's daily figures for the last 7 days. Cheapest and fastest only count listings that were up when checked.

## Questions

### What is the cheapest Nemotron 3 Ultra API provider?

DeepInfra (Flex), at $0.74 per million tokens blended ($0.40 input, $1.76 output), in OpenRouter's listings on November 7, 2026.

### How much does Nemotron 3 Ultra cost per million tokens?

Input runs from $0.40 to $0.625 per million tokens across 5 listings, and output from $1.76 to $3.13. The middle listing comes to $1.05 blended.

### Which Nemotron 3 Ultra provider is fastest?

Baseten (US) had the most throughput over the last 7 days, about 108 tokens per second. Baseten was quickest to the first token at 0.26 s.

### How do I pay for Nemotron 3 Ultra inference?

Buy OpenRouter credits and it sends each request to one of these providers, or open an account with a provider and pay it directly. The ernd card is a credit card for US companies. It earns 4% back on AI vendor spend and 1.5% back on everything else.

Source: OpenRouter public model and provider listings (https://openrouter.ai/models), checked November 7, 2026.

The ernd card is a credit card for US companies. It earns 4% back on AI vendor spend and 1.5% back on everything else. [Request the card at app.ernd.ai](https://app.ernd.ai/login?next=%2Fapp%2Fcard%2Fapply&utm_source=llms&utm_campaign=inference_prices).