{
  "key": "holo3-35b-a3b",
  "name": "Holo3-35B-A3B",
  "description": "Compact GPT model for low-latency assistance and high-volume workloads",
  "lab": null,
  "family": null,
  "release_date": "2024-01-01",
  "knowledge": null,
  "open_weights": true,
  "has_free_offering": false,
  "published": true,
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "text"
    ]
  },
  "capabilities": {
    "reasoning": true,
    "tool_call": true,
    "structured_output": true,
    "attachment": true,
    "reasoning_options": [
      {
        "type": "toggle"
      }
    ]
  },
  "limit": {
    "context": 65536,
    "output": 8192
  },
  "offerings": [
    {
      "provider": "nano-gpt",
      "provider_model_id": "holo3-35b-a3b",
      "name": "Holo3-35B-A3B",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.25,
        "output": 1.8,
        "cache_read": 0.125,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 65536,
        "output": 8192,
        "input": 65536
      },
      "status": null,
      "last_updated": "2024-01-01"
    },
    {
      "provider": "nano-gpt",
      "provider_model_id": "holo3-35b-a3b:thinking",
      "name": "Holo3-35B-A3B Thinking",
      "variants": [
        "thinking"
      ],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.25,
        "output": 1.8,
        "cache_read": 0.125,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 65536,
        "output": 8192,
        "input": 65536
      },
      "status": null,
      "last_updated": "2024-01-01"
    }
  ]
}