{
  "key": "nemotron-lightning-3-5-30b-a3b",
  "name": "nemotron-lightning-3.5-30b-a3b",
  "description": "Nemotron-Lightning-3.5-30B-A3B is a 30B-parameter Mixture-of-Experts language model (3B active) from NVIDIA's Nemotron-H family, built on a hybrid Mamba-Transformer architecture for efficient long-context inference. Like other models in the family, it responds to queries by first generating a reasoning trace and then concluding with a final response, with reasoning behavior configurable through a flag in the chat template. It includes a multi-token prediction (MTP) speculative decoding head for low-latency serving.",
  "lab": "nvidia",
  "family": "nemotron",
  "release_date": "2026-08-15",
  "knowledge": null,
  "open_weights": false,
  "has_free_offering": false,
  "published": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "capabilities": {
    "reasoning": true,
    "tool_call": true,
    "structured_output": true,
    "attachment": false,
    "reasoning_options": [
      {
        "type": "effort",
        "values": [
          "none",
          "low",
          "medium",
          "high",
          "max"
        ]
      },
      {
        "type": "budget_tokens"
      }
    ]
  },
  "limit": {
    "context": 262144,
    "output": 262144
  },
  "offerings": [
    {
      "provider": "requesty",
      "provider_model_id": "nemotron-lightning-3.5-30b-a3b",
      "name": "nemotron-lightning-3.5-30b-a3b",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.05,
        "output": 0.2,
        "cache_read": 0.01,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 262144,
        "output": 262144,
        "input": null
      },
      "status": null,
      "last_updated": "2026-08-15"
    }
  ]
}