# Cheapest Nemotron 3.5 Super VL API providers, compared (prices checked Nov 7, 2026)

URL: https://ernd.ai/inference-prices/nemotron-3-5-super-vl

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

Nemotron 3.5 Super VL is an open-weight model from NVIDIA. On OpenRouter, 10 listings from 10 providers sell it, and the blended price runs from $0.133 to $0.45 per million tokens.

| Provider | Input /1M | Output /1M | Blended 3:1 | Cache read /1M | Context | Quantization | Latency | Throughput |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Darkbloom | $0.06 | $0.35 | $0.133 | $0.01 | 262K | NVFP4 | 2.71 s | 24 tok/s |
| Crusoe | $0.10 | $0.40 | $0.175 | $0.08 | 1.05M | BF16 | 0.83 s | 81 tok/s |
| CoreWeave | $0.15 | $0.50 | $0.237 | $0.02 | 1.05M | NVFP4 | 1.18 s | 155 tok/s |
| DeepInfra | $0.15 | $0.50 | $0.237 | $0.02 | 262K | FP4 | 0.64 s | 220 tok/s |
| io.net | $0.15 | $0.50 | $0.237 | $0.02 | 262K | NVFP4 | 1.42 s | 70 tok/s |
| Prime Intellect | $0.15 | $0.50 | $0.237 | $0.02 | 1.05M | NVFP4 | 1.63 s | 125 tok/s |
| Together | $0.15 | $0.50 | $0.237 | $0.02 | 262K | Not listed | 0.46 s | 164 tok/s |
| Baseten | $0.20 | $0.50 | $0.275 | $0.04 | 1.05M | FP4 | 0.90 s | 173 tok/s |
| Venice | $0.20 | $0.50 | $0.275 | $0.04 | 262K | FP4 | 0.77 s | 222 tok/s |
| Nebius Token Factory | $0.30 | $0.90 | $0.45 | $0.06 | 1.05M | BF16 | 2.62 s | 56 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 3.5 Super VL API provider?

Darkbloom, at $0.133 per million tokens blended ($0.06 input, $0.35 output), in OpenRouter's listings on November 7, 2026.

### How much does Nemotron 3.5 Super VL cost per million tokens?

Input runs from $0.06 to $0.30 per million tokens across 10 listings, and output from $0.35 to $0.90. The middle listing comes to $0.237 blended.

### Which Nemotron 3.5 Super VL provider is fastest?

Venice had the most throughput over the last 7 days, about 222 tokens per second. Together was quickest to the first token at 0.46 s.

### How do I pay for Nemotron 3.5 Super VL 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).