[
  {
    "id": "llama-3.3-70b",
    "aliases": [
      "llama-3.3"
    ],
    "name": "Llama 3.3 70B",
    "provider": "meta",
    "releaseDate": "2024-12-06",
    "status": "stable",
    "capabilities": [
      "text-generation",
      "chat",
      "code-generation",
      "function-calling",
      "streaming",
      "json-mode"
    ],
    "tags": [
      "flagship",
      "coding",
      "balanced"
    ],
    "limits": {
      "contextWindow": 128000,
      "maxOutputTokens": 8192
    },
    "pricing": {
      "input": 0.6,
      "output": 0.6
    },
    "description": "Latest Llama model with improved performance and longer context",
    "docsUrl": "https://llama.meta.com/docs"
  },
  {
    "id": "llama-3.1-405b",
    "aliases": [
      "llama-3.1-405b-instruct"
    ],
    "name": "Llama 3.1 405B",
    "provider": "meta",
    "releaseDate": "2024-07-23",
    "status": "stable",
    "capabilities": [
      "text-generation",
      "chat",
      "code-generation",
      "function-calling",
      "streaming",
      "reasoning"
    ],
    "tags": [
      "flagship",
      "reasoning",
      "long-context"
    ],
    "limits": {
      "contextWindow": 128000,
      "maxOutputTokens": 8192
    },
    "pricing": {
      "input": 2.7,
      "output": 2.7
    },
    "description": "Largest Llama model with exceptional reasoning capabilities",
    "docsUrl": "https://llama.meta.com/docs"
  },
  {
    "id": "llama-3.1-70b",
    "aliases": [
      "llama-3.1-70b-instruct"
    ],
    "name": "Llama 3.1 70B",
    "provider": "meta",
    "releaseDate": "2024-07-23",
    "status": "stable",
    "capabilities": [
      "text-generation",
      "chat",
      "code-generation",
      "function-calling",
      "streaming"
    ],
    "tags": [
      "balanced",
      "coding"
    ],
    "limits": {
      "contextWindow": 128000,
      "maxOutputTokens": 8192
    },
    "pricing": {
      "input": 0.6,
      "output": 0.6
    },
    "description": "Balanced model with strong coding and reasoning",
    "docsUrl": "https://llama.meta.com/docs"
  },
  {
    "id": "llama-3.1-8b",
    "aliases": [
      "llama-3.1-8b-instruct"
    ],
    "name": "Llama 3.1 8B",
    "provider": "meta",
    "releaseDate": "2024-07-23",
    "status": "stable",
    "capabilities": [
      "text-generation",
      "chat",
      "code-generation",
      "streaming"
    ],
    "tags": [
      "fast",
      "cost-effective"
    ],
    "limits": {
      "contextWindow": 128000,
      "maxOutputTokens": 8192
    },
    "pricing": {
      "input": 0.2,
      "output": 0.2
    },
    "description": "Fast and efficient small model for everyday tasks",
    "docsUrl": "https://llama.meta.com/docs"
  },
  {
    "id": "llama-3.2-90b-vision",
    "aliases": [
      "llama-3.2-vision"
    ],
    "name": "Llama 3.2 90B Vision",
    "provider": "meta",
    "releaseDate": "2024-09-25",
    "status": "stable",
    "capabilities": [
      "text-generation",
      "chat",
      "vision",
      "code-generation",
      "streaming"
    ],
    "tags": [
      "multimodal",
      "balanced"
    ],
    "limits": {
      "contextWindow": 128000,
      "maxOutputTokens": 8192
    },
    "pricing": {
      "input": 0.9,
      "output": 0.9
    },
    "description": "Llama with vision capabilities for image understanding",
    "docsUrl": "https://llama.meta.com/docs"
  },
  {
    "id": "llama-3.2-11b-vision",
    "name": "Llama 3.2 11B Vision",
    "provider": "meta",
    "releaseDate": "2024-09-25",
    "status": "stable",
    "capabilities": [
      "text-generation",
      "chat",
      "vision",
      "streaming"
    ],
    "tags": [
      "multimodal",
      "fast",
      "cost-effective"
    ],
    "limits": {
      "contextWindow": 128000,
      "maxOutputTokens": 8192
    },
    "pricing": {
      "input": 0.15,
      "output": 0.15
    },
    "description": "Compact vision model for efficient multimodal tasks",
    "docsUrl": "https://llama.meta.com/docs"
  }
]