{
  "key": "llama-3-1-8b-instruct-fp8",
  "name": "Llama 3.1 8B Instruct fp8",
  "description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
  "lab": "meta",
  "family": "llama",
  "release_date": "2024-07-23",
  "knowledge": "2023-12",
  "open_weights": true,
  "has_free_offering": false,
  "published": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "capabilities": {
    "reasoning": false,
    "tool_call": false,
    "structured_output": false,
    "attachment": false,
    "reasoning_options": null
  },
  "limit": {
    "context": 128000,
    "output": 32000
  },
  "offerings": [
    {
      "provider": "cloudflare-workers-ai",
      "provider_model_id": "@cf/meta/llama-3.1-8b-instruct-fp8",
      "name": "Llama 3.1 8B Instruct fp8",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.152,
        "output": 0.287,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 32000,
        "output": 32000,
        "input": null
      },
      "status": null,
      "last_updated": "2024-07-23"
    },
    {
      "provider": "nano-gpt",
      "provider_model_id": "Meta-Llama-3-1-8B-Instruct-FP8",
      "name": "Llama 3.1 8B (decentralized)",
      "variants": [
        {
          "org": "meta"
        }
      ],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.02,
        "output": 0.03,
        "cache_read": 0.01,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 16384,
        "input": 128000
      },
      "status": null,
      "last_updated": "2024-07-23"
    }
  ]
}