{
  "key": "llama-3-3-70b-instruct",
  "name": "Llama-3.3-70B-Instruct",
  "description": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting",
  "lab": "meta",
  "family": "llama",
  "release_date": "2024-12-06",
  "knowledge": "2023-12",
  "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-3.3-70B-Instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [
        {
          "org": "meta"
        }
      ],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.59,
        "output": 0.79,
        "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": "2024-12-06"
    },
    {
      "provider": "azure",
      "provider_model_id": "llama-3.3-70b-instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.71,
        "output": 0.71,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 32768,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "azure-cognitive-services",
      "provider_model_id": "llama-3.3-70b-instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.71,
        "output": 0.71,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 32768,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "cloudferro-sherlock",
      "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct",
      "name": "Llama 3.3 70B Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 2.92,
        "output": 2.92,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 70000,
        "output": 70000,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "cortecs",
      "provider_model_id": "llama-3.3-70b-instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.129,
        "output": 0.399,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131000,
        "output": 131000,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "crusoe",
      "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.25,
        "output": 0.75,
        "cache_read": 0.13,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 4096,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "edenai",
      "provider_model_id": "deepinfra/meta-llama/Llama-3.3-70B-Instruct",
      "name": "Llama-3.3-70B-Instruct (Deep Infra)",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.1,
        "output": 0.32,
        "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": "2024-12-06"
    },
    {
      "provider": "edenai",
      "provider_model_id": "ionos/meta-llama/Llama-3.3-70B-Instruct",
      "name": "Llama-3.3-70B-Instruct (IONOS)",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.750035,
        "output": 0.750035,
        "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": "2024-12-06"
    },
    {
      "provider": "edenai",
      "provider_model_id": "nebius/meta-llama/Llama-3.3-70B-Instruct",
      "name": "Llama-3.3-70B-Instruct (Nebius)",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.13,
        "output": 0.4,
        "cache_read": 0.13,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 4096,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "edenai",
      "provider_model_id": "scaleway/llama-3.3-70b-instruct",
      "name": "Llama-3.3-70B-Instruct (Scaleway)",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1.03851,
        "output": 1.03851,
        "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": "2024-12-06"
    },
    {
      "provider": "greenpt",
      "provider_model_id": "llama-3.3-70b-instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 1.254,
        "output": 1.254,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 100000,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "helicone",
      "provider_model_id": "llama-3.3-70b-instruct",
      "name": "Meta Llama 3.3 70B Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.13,
        "output": 0.39,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 16400,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "huggingface",
      "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.59,
        "output": 0.79,
        "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": "2024-12-06"
    },
    {
      "provider": "hyper",
      "provider_model_id": "llama-3.3-70b-instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.6066,
        "output": 1.0386,
        "cache_read": 0.3033,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 12800,
        "input": null
      },
      "status": null,
      "last_updated": "2026-07-22"
    },
    {
      "provider": "io-net",
      "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct",
      "name": "Llama 3.3 70B Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.13,
        "output": 0.38,
        "cache_read": 0.065,
        "cache_write": 0.26,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 4096,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "kilo",
      "provider_model_id": "meta-llama/llama-3.3-70b-instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.1,
        "output": 0.32,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "llama",
      "provider_model_id": "llama-3.3-70b-instruct",
      "name": "Llama-3.3-70B-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": 128000,
        "output": 4096,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "llmgateway",
      "provider_model_id": "llama-3.3-70b-instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.135,
        "output": 0.4,
        "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": "2024-12-06"
    },
    {
      "provider": "llmgateway-providers",
      "provider_model_id": "cerebras/llama-3.3-70b-instruct",
      "name": "Llama 3.3 70B Instruct (Cerebras)",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.85,
        "output": 1.2,
        "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": "2024-12-06"
    },
    {
      "provider": "llmgateway-providers",
      "provider_model_id": "novita/llama-3.3-70b-instruct",
      "name": "Llama 3.3 70B Instruct (NovitaAI)",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.135,
        "output": 0.4,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 120000,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "meganova",
      "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct",
      "name": "Llama 3.3 70B Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.1,
        "output": 0.3,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "merge-gateway",
      "provider_model_id": "meta/llama-3.3-70b-instruct",
      "name": "Llama 3.3 70B Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.22,
        "output": 0.5,
        "cache_read": 0.11,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 32768,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "nano-gpt",
      "provider_model_id": "meta-llama/llama-3.3-70b-instruct",
      "name": "Llama 3.3 70b Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.05,
        "output": 0.23,
        "cache_read": 0.025,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 16384,
        "input": 131072
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "neon",
      "provider_model_id": "meta-llama-3-3-70b-instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [
        {
          "org": "meta"
        }
      ],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.5,
        "output": 1.5,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 8192,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "novita-ai",
      "provider_model_id": "meta-llama/llama-3.3-70b-instruct",
      "name": "Llama 3.3 70B Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.135,
        "output": 0.4,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 120000,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-07"
    },
    {
      "provider": "nvidia",
      "provider_model_id": "meta/llama-3.3-70b-instruct",
      "name": "Llama 3.3 70b 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": 128000,
        "output": 4096,
        "input": null
      },
      "status": null,
      "last_updated": "2024-11-26"
    },
    {
      "provider": "openrouter",
      "provider_model_id": "meta-llama/llama-3.3-70b-instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.1,
        "output": 0.32,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "ovhcloud",
      "provider_model_id": "meta-llama-3_3-70b-instruct",
      "name": "Meta-Llama-3_3-70B-Instruct",
      "variants": [
        {
          "org": "meta"
        }
      ],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.74,
        "output": 0.74,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 131072,
        "input": null
      },
      "status": null,
      "last_updated": "2025-04-01"
    },
    {
      "provider": "pioneer",
      "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.9,
        "output": 0.9,
        "cache_read": 0.9,
        "cache_write": 0.9,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 16384,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-06"
    },
    {
      "provider": "regolo-ai",
      "provider_model_id": "llama-3.3-70b-instruct",
      "name": "Llama 3.3 70B Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.6,
        "output": 2.7,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2025-04-28"
    },
    {
      "provider": "scaleway",
      "provider_model_id": "llama-3.3-70b-instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.9,
        "output": 0.9,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 100000,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2026-03-17"
    },
    {
      "provider": "wandb",
      "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct",
      "name": "Llama 3.3 70B",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.71,
        "output": 0.71,
        "cache_read": 0.71,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 128000,
        "input": null
      },
      "status": null,
      "last_updated": "2024-12-01"
    },
    {
      "provider": "watsonx",
      "provider_model_id": "meta-llama/llama-3-3-70b-instruct",
      "name": "Llama-3.3-70B-Instruct",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.7526,
        "output": 0.7526,
        "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": "2024-12-06"
    }
  ]
}