Skip to Content
DocsNemotron 3.5 Lightning (Free)
DocsNemotron 3.5 Lightning (Free)

Nemotron 3.5 Lightning (Free)

Nemotron 3.5 Lightning is a text-only reasoning model from NVIDIA. It can use tools, but cannot read images or screenshots. Use it only for nonconfidential trials, not private game projects.

Trial use and privacy

This free endpoint is for testing and evaluation, not production or business-critical use. NVIDIA logs prompts and responses and may use them to improve its products and AI models. Do not send personal, confidential, or sensitive information, including private project code. A zero-data-retention guarantee is not available.

Read the provider’s model information  and NVIDIA API Trial Terms  before using it.

Select the model

Select Nemotron 3.5 Lightning (Free) under NVIDIA in the chat’s model picker for a nonconfidential trial. Check the chat history and project context first: they are sent along with your prompt. Existing Ling 3.1 Flash chats require you to choose a model again.

The model has no paid-plan requirement and does not consume paid usage.

Availability

Free availability can end at any time. If the provider starts charging or its pricing cannot be verified as free, Ziva stops further requests to this model. Choose another model to continue; Ziva does not automatically substitute a paid model.

Optional reference: text capacity

The model can read up to 1 million tokens at once and produce up to 65,000 output tokens. Tokens are small pieces of text. These capacities do not remove the trial-use and privacy restrictions above.

Last updated on