{
  "key": "llama-3-1-8b-instruct",
  "name": "Llama 3.1 8B Instruct",
  "description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
  "lab": "meta",
  "family": "llama",
  "release_date": "2024-07-23",
  "knowledge": null,
  "open_weights": true,
  "has_free_offering": false,
  "published": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "capabilities": {
    "reasoning": false,
    "tool_call": true,
    "structured_output": null,
    "attachment": false,
    "reasoning_options": null
  },
  "limit": {
    "context": 131072,
    "output": 131072
  },
  "offerings": [
    {
      "provider": "abacus",
      "provider_model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct",
      "name": "Llama 3.1 8B Instruct",
      "variants": [
        {
          "org": "meta"
        }
      ],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.02,
        "output": 0.05,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 4096,
        "input": null
      },
      "status": null,
      "last_updated": "2024-07-23"
    },
    {
      "provider": "cortecs",
      "provider_model_id": "llama-3.1-8b-instruct",
      "name": "Llama-3.1-8B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.167,
        "output": 0.167,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 128000,
        "input": null
      },
      "status": null,
      "last_updated": "2024-07-23"
    },
    {
      "provider": "helicone",
      "provider_model_id": "llama-3.1-8b-instruct",
      "name": "Meta Llama 3.1 8B Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.02,
        "output": 0.049999999999999996,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 16384,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2024-07-23"
    },
    {
      "provider": "huggingface",
      "provider_model_id": "meta-llama/Llama-3.1-8B-Instruct",
      "name": "Llama-3.1-8B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.06,
        "output": 0.06,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 4096,
        "input": null
      },
      "status": null,
      "last_updated": "2024-07-23"
    },
    {
      "provider": "inference",
      "provider_model_id": "meta/llama-3.1-8b-instruct",
      "name": "Llama 3.1 8B Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.025,
        "output": 0.025,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 16000,
        "output": 4096,
        "input": null
      },
      "status": null,
      "last_updated": "2025-01-01"
    },
    {
      "provider": "kilo",
      "provider_model_id": "meta-llama/llama-3.1-8b-instruct",
      "name": "Llama-3.1-8B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.02,
        "output": 0.04,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 117964,
        "input": null
      },
      "status": null,
      "last_updated": "2024-07-23"
    },
    {
      "provider": "merge-gateway",
      "provider_model_id": "meta/llama-3.1-8b-instruct",
      "name": "Llama 3.1 8B",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.22,
        "output": 0.22,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 2048,
        "input": null
      },
      "status": null,
      "last_updated": "2024-07-23"
    },
    {
      "provider": "nano-gpt",
      "provider_model_id": "meta-llama/llama-3.1-8b-instruct",
      "name": "Llama 3.1 8b Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.0544,
        "output": 0.085,
        "cache_read": 0.0272,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 16384,
        "input": 131072
      },
      "status": null,
      "last_updated": "2024-07-23"
    },
    {
      "provider": "neon",
      "provider_model_id": "meta-llama-3-1-8b-instruct",
      "name": "Llama 3.1 8B Instruct",
      "variants": [
        {
          "org": "meta"
        }
      ],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.15,
        "output": 0.45,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 8192,
        "input": null
      },
      "status": null,
      "last_updated": "2024-07-23"
    },
    {
      "provider": "novita-ai",
      "provider_model_id": "meta-llama/llama-3.1-8b-instruct",
      "name": "Llama 3.1 8B Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.02,
        "output": 0.05,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 16384,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2024-07-24"
    },
    {
      "provider": "nvidia",
      "provider_model_id": "meta/llama-3.1-8b-instruct",
      "name": "Llama 3.1 8B Instruct",
      "variants": [],
      "free": false,
      "priced": false,
      "cost": {
        "input": 0,
        "output": 0,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 16000,
        "output": 4096,
        "input": null
      },
      "status": null,
      "last_updated": "2025-01-01"
    },
    {
      "provider": "openrouter",
      "provider_model_id": "meta-llama/llama-3.1-8b-instruct",
      "name": "Llama-3.1-8B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.05,
        "output": 0.08,
        "cache_read": 0.025,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 117964,
        "input": null
      },
      "status": null,
      "last_updated": "2024-07-23"
    },
    {
      "provider": "pioneer",
      "provider_model_id": "meta-llama/Llama-3.1-8B-Instruct",
      "name": "Llama 3.1 8B Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.2,
        "output": 0.2,
        "cache_read": 0.2,
        "cache_write": 0.2,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 8192,
        "input": null
      },
      "status": null,
      "last_updated": "2024-07-23"
    },
    {
      "provider": "wandb",
      "provider_model_id": "meta-llama/Llama-3.1-8B-Instruct",
      "name": "Llama 3.1 8B",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.22,
        "output": 0.22,
        "cache_read": 0.22,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 131072,
        "input": null
      },
      "status": null,
      "last_updated": "2024-07-23"
    }
  ]
}