Remy Reference/Models/Language/Nemotron 3 Nano 30B

Nemotron 3 Nano 30B

Nemotron 3 Nano 30B, a language model from DeepInfra.

modelOverride: { model: "nemotron-3-nano-30b" }

NNvidia·served viaDeepInfra·Released December 2025

Pricing

Input: $0.050 / 1M
Output: $0.20 / 1M

Specifications

Context window: 1,000,000 tokens
Max output: 16,384 tokens
Released: December 2025
Model string: nvidia/Nemotron-3-Nano-30B-A3B

Parameters

Model options, passed in modelOverride.config.

Parameter	Type	Default	Range / options
`reasoning` When enabled, the model generates a reasoning trace before providing a final answer. This improves performance on complex tasks like math, coding, and multi-step reasoning, but results in longer responses and higher token usage.	Select	false	falsetrue

Use this model

await mindstudio.generateText({
  message: "...",
  modelOverride: {
    model: "nemotron-3-nano-30b",
    config: {
      reasoning: "false",
    },
  },
});