Nemotron 3.5 Super VL

What you can use today

Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.

Exact catalog ID: nvidia/nemotron-3.5-super-vl. The native model supports thinking off, on with a medium budget, or on. Those controls have not been tested here on the same questions. Do not reuse Lightning or older Nemotron scores for this release.

Weights are available under OpenMDW 1.1. The separate free OpenRouter route and paid Gateway route have their own limits and availability; a free offer is not a permanent promise for every host.

The downloadable model supports up to one million tokens, but this OpenRouter offer currently lists 262,144 for its serving provider. The calculator uses that smaller limit. Gateway separately lists 1,048,576; confirm your chosen host before sending a large document.

Rates describe the catalog offer observed on 2026-11-03. Allow for retries and any tool fees. Models that think before answering may also charge for that work.

Provider release and specifications ↗

Inspect the exact catalog model ↗

Test it before switching

Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.