{
  "_meta": {
    "source": "https://apipriceindex.com/api/deepinfra/nemotron-3.5-lightning",
    "attribution": "apipriceindex.com",
    "license": "CC BY 4.0",
    "license_url": "https://creativecommons.org/licenses/by/4.0/",
    "note": "Free to reuse with attribution to apipriceindex.com.",
    "generated_at": "2026-09-05T08:15:06.261Z"
  },
  "id": "deepinfra:nemotron-3.5-lightning",
  "name": "Nemotron 3.5 Lightning (DeepInfra)",
  "base_model": "nemotron-3.5-lightning",
  "provider": {
    "id": "deepinfra",
    "name": "DeepInfra",
    "url": "https://deepinfra.com"
  },
  "category": "llm-chat",
  "capabilities": [
    "text",
    "function-calling"
  ],
  "context_window": 262144,
  "max_output": 131072,
  "pricing": {
    "model_id": "deepinfra:nemotron-3.5-lightning",
    "input": 0.08,
    "output": 0.2,
    "cached_input": 0.04,
    "source_url": "https://openrouter.ai/nvidia/nemotron-3.5-lightning",
    "verified_at": "2026-09-05T08:00:57Z",
    "sources": [
      {
        "name": "OpenRouter",
        "input": 0.08,
        "output": 0.2,
        "url": "https://openrouter.ai/nvidia/nemotron-3.5-lightning",
        "verified_at": "2026-09-05T08:00:57Z"
      },
      {
        "name": "LiteLLM",
        "input": 0.05,
        "output": 0.2,
        "url": "https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json",
        "verified_at": "2026-09-03T20:47:46Z"
      },
      {
        "name": "models.dev",
        "input": 0.08,
        "output": 0.2,
        "url": "https://models.dev/",
        "verified_at": "2026-09-04T10:52:49Z"
      }
    ],
    "confidence": "corroborated",
    "delta_pct": 0
  },
  "price_history": [
    [
      "2026-09-03",
      0.08,
      0.2
    ]
  ],
  "latency": [],
  "license": {
    "license": "NVIDIA Open Model License",
    "tier": "conditional",
    "open_weights": true,
    "source_url": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"
  },
  "cutoff": {
    "cutoff": "2024-06",
    "label": "June 2024",
    "source_url": "https://aiknowledgecutoff.com/"
  },
  "intelligence": {
    "score": 23.6,
    "model_name": "Nemotron 3.5 Lightning 30B A3B NVFP4",
    "verified_at": "2026-09-04",
    "benchmark_label": "Artificial Analysis Intelligence Index",
    "source_url": "https://artificialanalysis.ai/"
  },
  "quality": null,
  "api": {
    "base_url": "https://openrouter.ai/api/v1",
    "model": "nvidia/nemotron-3.5-lightning",
    "via": "openrouter",
    "key_env": "OPENROUTER_API_KEY",
    "docs_url": "https://openrouter.ai/nvidia/nemotron-3.5-lightning",
    "or_provider": "DeepInfra"
  },
  "facts": [
    "Nemotron 3.5 Lightning (DeepInfra) costs $0.08 input / $0.20 output per 1M tokens.",
    "Cached input cuts the input price by 50%.",
    "A chatbot workload (1000 in / 500 out tokens) costs $0.18 per 1,000 requests.",
    "Cross-checked against LiteLLM's public price index, which lists nemotron-3.5-lightning at $0.05/$0.20 per 1M (within 11% of this endpoint).",
    "Handles a 262,144-token context window, up to 131,072 output tokens.",
    "Open weights under NVIDIA Open Model License — conditional licence.",
    "Training knowledge cutoff: June 2024.",
    "Scores 23.6 on the Artificial Analysis Intelligence Index for nemotron-3.5-lightning.",
    "Cheapest of 2 providers serving nemotron-3.5-lightning: $0.28 blended per 1M tokens, vs $0.35 for the next cheapest.",
    "Intelligence value: 23.6 index at $0.28 blended = 84.3 index points per dollar — ranking #37 of 373 priced & AA-rated endpoints in the index."
  ]
}