{
 "@context": {
  "@language": "en",
  "@vocab": "https://schema.org/",
  "citeAs": "cr:citeAs",
  "column": "cr:column",
  "conformsTo": "dct:conformsTo",
  "cr": "http://mlcommons.org/croissant/",
  "rai": "http://mlcommons.org/croissant/RAI/",
  "data": {
   "@id": "cr:data",
   "@type": "@json"
  },
  "dataType": {
   "@id": "cr:dataType",
   "@type": "@vocab"
  },
  "dct": "http://purl.org/dc/terms/",
  "equivalentProperty": "cr:equivalentProperty",
  "examples": {
   "@id": "cr:examples",
   "@type": "@json"
  },
  "extract": "cr:extract",
  "field": "cr:field",
  "fileProperty": "cr:fileProperty",
  "fileObject": "cr:fileObject",
  "fileSet": "cr:fileSet",
  "format": "cr:format",
  "includes": "cr:includes",
  "isLiveDataset": "cr:isLiveDataset",
  "jsonPath": "cr:jsonPath",
  "key": "cr:key",
  "md5": "cr:md5",
  "parentField": "cr:parentField",
  "path": "cr:path",
  "recordSet": "cr:recordSet",
  "references": "cr:references",
  "regex": "cr:regex",
  "repeated": "cr:repeated",
  "replace": "cr:replace",
  "samplingRate": "cr:samplingRate",
  "sc": "https://schema.org/",
  "separator": "cr:separator",
  "source": "cr:source",
  "subField": "cr:subField",
  "transform": "cr:transform"
 },
 "@type": "sc:Dataset",
 "conformsTo": "http://mlcommons.org/croissant/1.0",
 "name": "Real cost by language: what the same text costs on each LLM model and provider",
 "description": "Cost to send and receive the same text in English, Arabic MSA, Gulf Arabic, Egyptian Arabic, Levantine Arabic, Najdi Arabic, Mesopotamian Arabic, Arabizi, Hindi, Urdu, Chinese, French, Spanish, Code, JSON, per 1M characters and per 1,000 words, for 618 standard-tier price rows (108 models, 35 third-party providers plus BroadNet), using token counts measured with 16 official tokenizers and prices read from each provider's own pricing page.",
 "url": "https://broadrouter.com/data/real-cost-by-language/",
 "version": "1.1",
 "datePublished": "2026-11-15",
 "dateModified": "2026-11-15",
 "license": "https://creativecommons.org/licenses/by/4.0/",
 "creator": {
  "@type": "Organization",
  "@id": "https://broadrouter.com/#org",
  "name": "BroadRouter",
  "url": "https://broadrouter.com"
 },
 "publisher": {
  "@type": "Organization",
  "@id": "https://broadrouter.com/#org",
  "name": "BroadRouter",
  "url": "https://broadrouter.com"
 },
 "citeAs": "@misc{broadrouter_real_cost_by_language,\n  author       = {BroadRouter},\n  title        = {Real cost by language: what the same text costs on each LLM model and provider},\n  year         = {2026},\n  version      = {1.1},\n  publisher    = {BroadNet Technologies},\n  howpublished = {\\url{https://broadrouter.com/data/real-cost-by-language/}},\n  note         = {Data set, data as of 2026-11-15},\n}",
 "isAccessibleForFree": true,
 "keywords": [
  "LLM API cost by language",
  "Arabic LLM cost",
  "Hindi LLM cost",
  "language tax",
  "token tax",
  "cost per character",
  "cost per word",
  "tokenizer",
  "LLM API pricing"
 ],
 "inLanguage": [
  "en",
  "ar",
  "fr",
  "es",
  "hi",
  "ur",
  "zh"
 ],
 "distribution": [
  {
   "@type": "cr:FileObject",
   "@id": "real-cost-by-language.csv",
   "name": "real-cost-by-language.csv",
   "description": "CSV, one row per price row (provider and model) and language (long format). 9270 rows, 18 columns, UTF-8, header row. Licence: Our compilation and measurements (token counts, the model-to-tokenizer mapping, cost per character and per word, findings, tables and method): CC BY 4.0. Each price is a fact published by the provider named in its row, at the source URL given per row; we do not license those pages to you. Credit the provider as the source of each price. The texts behind the token counts keep their own licences (see the tokenizer efficiency dataset); FLORES-200 sentences (CC BY-SA 4.0) are not included anywhere in our files, only our counts.",
   "contentUrl": "https://broadrouter.com/data/real-cost-by-language.csv",
   "encodingFormat": "text/csv",
   "contentSize": "1896879 B",
   "sha256": "2fdf9b54f8194bd5aa23a78b11890e0a519414ce5e04b6047c4a04a81a2387dd"
  },
  {
   "@type": "cr:FileObject",
   "@id": "real-cost-by-language.json",
   "name": "real-cost-by-language.json",
   "description": "JSON with metadata, method, column dictionary, tokenizers, per-language token bases with parallel-text intervals, findings (cheapest per language, language tax), the model-to-tokenizer mapping and every cost row. Licence: Our compilation and measurements (token counts, the model-to-tokenizer mapping, cost per character and per word, findings, tables and method): CC BY 4.0. Each price is a fact published by the provider named in its row, at the source URL given per row; we do not license those pages to you. Credit the provider as the source of each price. The texts behind the token counts keep their own licences (see the tokenizer efficiency dataset); FLORES-200 sentences (CC BY-SA 4.0) are not included anywhere in our files, only our counts.",
   "contentUrl": "https://broadrouter.com/data/real-cost-by-language.json",
   "encodingFormat": "application/json",
   "contentSize": "1366631 B",
   "sha256": "6ef316afea41eabd87a83a4883187304e62354ae811fa32886f6d9c87dee7f1a"
  }
 ],
 "recordSet": [
  {
   "@type": "cr:RecordSet",
   "@id": "real-cost-by-language",
   "name": "real-cost-by-language",
   "description": "The CSV file: one record per price row (provider and model) and language (long format).",
   "key": [
    {
     "@id": "real-cost-by-language/provider_id"
    },
    {
     "@id": "real-cost-by-language/model_slug"
    },
    {
     "@id": "real-cost-by-language/language"
    }
   ],
   "field": [
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/provider",
     "name": "provider",
     "description": "Who sells the model. \"BroadNet Inference\" rows are BroadNet, the owner of this site.",
     "dataType": "sc:Text",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "provider"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/provider_id",
     "name": "provider_id",
     "description": "Provider ID, as in the LLM API provider price database.",
     "dataType": "sc:Text",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "provider_id"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/model",
     "name": "model",
     "description": "Model name as the provider lists it.",
     "dataType": "sc:Text",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "model"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/model_slug",
     "name": "model_slug",
     "description": "Model ID in our price database; /llm-api-pricing/<model_slug>/ has every provider.",
     "dataType": "sc:Text",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "model_slug"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/tokenizer",
     "name": "tokenizer",
     "description": "Measured tokenizer this model uses (see tokenizer_mapping).",
     "dataType": "sc:Text",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "tokenizer"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/tokenizer_mapping",
     "name": "tokenizer_mapping",
     "description": "Why the model maps to that tokenizer: measured, identical (byte-identical file), same-core (same vocabulary, merges and pre-tokenizer, identical counts), tiktoken (OpenAI's model table) or broadnet (BroadNet build of the measured model, assumed to keep its tokenizer).",
     "dataType": "sc:Text",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "tokenizer_mapping"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/language",
     "name": "language",
     "description": "Language or content kind: en, ar-msa, ar-gulf, ar-egyptian, ar-levantine, ar-najdi, ar-mesopotamian, arabizi, hi, ur, zh, fr, es, code, json.",
     "dataType": "sc:Text",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "language"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/input_usd_per_1m_tokens",
     "name": "input_usd_per_1m_tokens",
     "description": "Standard-tier input price per 1M tokens, from the provider's page.",
     "dataType": "sc:Float",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "input_usd_per_1m_tokens"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/output_usd_per_1m_tokens",
     "name": "output_usd_per_1m_tokens",
     "description": "Standard-tier output price per 1M tokens.",
     "dataType": "sc:Float",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "output_usd_per_1m_tokens"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/tokens_per_1k_chars",
     "name": "tokens_per_1k_chars",
     "description": "Measured tokens per 1,000 characters of this language with this tokenizer.",
     "dataType": "sc:Float",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "tokens_per_1k_chars"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/tokens_per_1k_words",
     "name": "tokens_per_1k_words",
     "description": "Measured tokens per 1,000 words (Intl.Segmenter words; for Chinese, segmented words).",
     "dataType": "sc:Float",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "tokens_per_1k_words"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/input_usd_per_1m_chars",
     "name": "input_usd_per_1m_chars",
     "description": "Cost to send 1M characters of this language: tokens per character × input price.",
     "dataType": "sc:Float",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "input_usd_per_1m_chars"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/output_usd_per_1m_chars",
     "name": "output_usd_per_1m_chars",
     "description": "Cost to receive 1M characters of this language as output.",
     "dataType": "sc:Float",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "output_usd_per_1m_chars"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/input_usd_per_1k_words",
     "name": "input_usd_per_1k_words",
     "description": "Cost to send 1,000 words.",
     "dataType": "sc:Float",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "input_usd_per_1k_words"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/output_usd_per_1k_words",
     "name": "output_usd_per_1k_words",
     "description": "Cost to receive 1,000 words.",
     "dataType": "sc:Float",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "output_usd_per_1k_words"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/promo",
     "name": "promo",
     "description": "yes if the provider marks the price as promotional; such rows are not ranked in the findings.",
     "dataType": "sc:Text",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "promo"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/source_url",
     "name": "source_url",
     "description": "Where the price was read.",
     "dataType": "sc:Text",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "source_url"
      }
     }
    },
    {
     "@type": "cr:Field",
     "@id": "real-cost-by-language/checked",
     "name": "checked",
     "description": "Date the price was checked.",
     "dataType": "sc:Date",
     "source": {
      "fileObject": {
       "@id": "real-cost-by-language.csv"
      },
      "extract": {
       "column": "checked"
      }
     }
    }
   ]
  }
 ]
}
