As open-source models quickly evolve, we are focused on providing the most cutting-edge options to our users.
The Nemotron 3 Nano serverless Model API is scheduled to be retired at 5pm PT on August 19, at which time this model will be disabled, and any requests made to it will return HTTP error code 400.
As a replacement, we suggest using Qwen3.8-27B, which delivers strong general purpose reasoning, coding, and long-context performance competitive with large frontier models at a fraction of the cost. Before the cutoff, update your integration to use lightning-ai/Qwen3.8-27B. If you still need access to Nemotron 3 Nano Omni, please reach out to discuss setting up a dedicated deployment.