{
  "_meta": {
    "source": "https://apipriceindex.com/api/cloudflare/llama-3.3-70b",
    "attribution": "apipriceindex.com",
    "license": "CC BY 4.0",
    "license_url": "https://creativecommons.org/licenses/by/4.0/",
    "note": "Free to reuse with attribution to apipriceindex.com.",
    "generated_at": "2026-09-05T08:15:06.076Z"
  },
  "id": "cloudflare:llama-3.3-70b",
  "name": "Llama 3.3 70B Instruct (Cloudflare)",
  "base_model": "llama-3.3-70b",
  "provider": {
    "id": "cloudflare",
    "name": "Cloudflare",
    "url": "https://www.cloudflare.com/developer-platform/workers-ai"
  },
  "category": "llm-chat",
  "capabilities": [
    "text"
  ],
  "context_window": 131072,
  "max_output": 21600,
  "pricing": {
    "model_id": "cloudflare:llama-3.3-70b",
    "input": 0.293,
    "output": 2.253,
    "cached_input": null,
    "source_url": "https://openrouter.ai/meta-llama/llama-3.3-70b-instruct",
    "verified_at": "2026-09-05T08:00:57Z",
    "sources": [
      {
        "name": "OpenRouter",
        "input": 0.293,
        "output": 2.253,
        "url": "https://openrouter.ai/meta-llama/llama-3.3-70b-instruct",
        "verified_at": "2026-09-05T08:00:57Z"
      },
      {
        "name": "LiteLLM",
        "input": 0.293,
        "output": 2.253,
        "url": "https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json",
        "verified_at": "2026-09-03T20:47:46Z"
      },
      {
        "name": "models.dev",
        "input": 0.293,
        "output": 2.253,
        "url": "https://models.dev/",
        "verified_at": "2026-09-04T10:52:49Z"
      }
    ],
    "confidence": "corroborated",
    "delta_pct": 0
  },
  "price_history": [
    [
      "2026-09-03",
      0.293,
      2.253
    ]
  ],
  "latency": [
    {
      "model_id": "cloudflare:llama-3.3-70b",
      "region": "eu-paris",
      "ttft_ms": {
        "p50": null,
        "p95": null
      },
      "total_ms": {
        "p50": null,
        "p95": null
      },
      "tokens_per_s": null,
      "samples": 0,
      "error_rate": 1,
      "token_source": "n/a",
      "measured_at": "2026-09-04T18:47:38Z"
    }
  ],
  "license": {
    "license": "Llama Community License",
    "tier": "conditional",
    "open_weights": true,
    "source_url": "https://www.llama.com/llama4/license/"
  },
  "cutoff": {
    "cutoff": "2024-12",
    "label": "December 2024",
    "source_url": "https://www.llama.com/docs/overview/"
  },
  "intelligence": null,
  "quality": {
    "elo": 1317,
    "arena_name": "Llama 3.3 70B",
    "verified_at": "2026-09-04",
    "benchmark_label": "LMArena (Chatbot Arena)",
    "source_url": "https://lmarena.ai/leaderboard/text"
  },
  "api": {
    "base_url": "https://api.cloudflare.com/client/v4/accounts/CLOUDFLARE_ACCOUNT_ID/ai/v1",
    "model": "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
    "via": "first-party",
    "key_env": "CLOUDFLARE_AI_TOKEN",
    "docs_url": null
  },
  "facts": [
    "Llama 3.3 70B Instruct (Cloudflare) costs $0.29 input / $2.25 output per 1M tokens.",
    "A chatbot workload (1000 in / 500 out tokens) costs $1.42 per 1,000 requests.",
    "Cross-checked: LiteLLM's public price index independently lists Cloudflare's llama-3.3-70b at $0.29/$2.25 per 1M — corroborating the price shown here (within 0%).",
    "Handles a 131,072-token context window, up to 21,600 output tokens.",
    "Open weights under Llama Community License — conditional licence.",
    "Training knowledge cutoff: December 2024.",
    "Scores 1317 on the LMArena (Chatbot Arena) (human-preference leaderboard) for llama-3.3-70b.",
    "506% pricier than the cheapest llama-3.3-70b endpoint ($0.42 on DeepInfra).",
    "Value: 1317 Elo at $2.55 blended = 517 Elo points per dollar — ranking #208 of 321 priced & rated endpoints in the index."
  ]
}