{
  "key": "hermes-medium",
  "name": "Hermes Medium",
  "description": "Compact GPT model for low-latency assistance and high-volume workloads",
  "lab": null,
  "family": "hermes",
  "release_date": "2026-05-11",
  "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": [
          "low",
          "high",
          "max"
        ]
      }
    ]
  },
  "limit": {
    "context": 1048576,
    "output": 131072
  },
  "offerings": [
    {
      "provider": "nano-gpt",
      "provider_model_id": "hermes-medium",
      "name": "Hermes Medium",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1,
        "output": 3.2,
        "cache_read": 0.2,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048576,
        "output": 131072,
        "input": 1048576
      },
      "status": null,
      "last_updated": "2026-05-11"
    }
  ]
}