Skip to content
AI News HubLIVE
Original source2 min read

The Indic Token Tax in 2026: Measuring Tokenizer Disparity and Its Cost for the Languages of India

Summary

A new study measures tokenizer disparity across nine public tokenizers for 25 Indian languages, finding that GPT-4o's tokenizer requires 1.57 to 5.01 times more tokens than English, and 13.7 times for Santali in Ol Chiki script, directly inflating API costs.

SourcearXiv Computational LinguisticsAuthor: Johin Johny Arimbur, Ankur Ashit Ghosh, Shervin Sam
The Indic Token Tax in 2026: Measuring Tokenizer Disparity and Its Cost for the Languages of India
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 9 Nov 2026]

Title:The Indic Token Tax in 2026: Measuring Tokenizer. Disparity and Its Cost for the Languages of India

View a PDF of the paper titled The Indic Token Tax in 2026: Measuring Tokenizer. Disparity and Its Cost for the Languages of India, by Johin Johny Arimbur and 2 other authors

View PDF HTML (experimental)

Abstract:Commercial language model APIs bill per token, so a tokenizer that needs more tokens for the same content in one language makes that language more expensive, slower, and able to fit less text in a fixed context window. We measure this disparity for nine public tokenizers, including those of GPT-4, GPT-4o, Qwen2.5, DeepSeek-V3, Mistral-Nemo and four Sarvam models, on all 25 languages of India available in FLORES-200 (2,009 professionally translated sentences aligned with English) and on 13,732 human-translated Hinglish-English social media pairs from PHINC. On GPT-4o's tokenizer the same content needs between 1.57 times (Hindi) and 5.01 times (Odia) the tokens of English, and 13.7 times for Santali in Ol Chiki script; GPT-4's tokenizer needs up to 12.8 times. Sarvam-30B/105B is the only third-party tokenizer that stays below 2.6 times on every language (median 1.53). In an illustrative scenario using official list prices accessed on 5 November 2026 and stated assumptions, a support bot handling 100,000 chats a month on GPT-4o would cost about INR 56,640 in English and INR 102,829 in Marathi; these are estimates, not measured production costs. Against an openly licensed Hindi and Marathi morphological segmentation set, no tokenizer places more than 35% of its word-internal boundaries on morpheme boundaries (boundary F1 at most 0.48). In a companion paper we present a tokenizer that reduces this tax. Code, pinned artifacts and raw token counts are available at this https URL.

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

Cite as: arXiv:2611.13058 [cs.CL]

(or arXiv:2611.13058v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2611.13058

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Johin Arimbur [view email] [v1] Mon, 9 Nov 2026 17:24:21 UTC (473 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled The Indic Token Tax in 2026: Measuring Tokenizer. Disparity and Its Cost for the Languages of India, by Johin Johny Arimbur and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CL

new | recent | 2026-11

Change to browse by:

cs cs.AI

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • GPT-4o's tokenizer needs 1.57x to 5.01x more tokens for Indian languages versus English; Santali reaches 13.7x
  • Sarvam-30B/105B is the only third-party tokenizer staying below 2.6x for all languages
  • Illustrative scenario: 100,000 monthly chats cost ~82% more in Marathi than English on GPT-4o
  • No tokenizer aligns more than 35% of word-internal boundaries with morpheme boundaries (boundary F1 ≤ 0.48)

Highlights and analysis are generated automatically and may contain errors. Check the original source.

The Indic Token Tax in 2026: Measuring Tokenizer Disparity and Its Cost for the Languages of India | AI News Hub