Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Language models have graduated from being research prototypes to commercialized products offered as web APIs, and recent works have highlighted the multilingual capabilities of these products.The API vendors charge their users based on usage, more specifically on the number of "tokens" processed or generated by the underlying language models.What constitutes a token, however, is training data and model dependent with a large variance in the number of tokens required to convey the same information in different languages.In this work, we analyze the effect of this nonuniformity on the fairness of an API's pricing policy across languages.We conduct a systematic analysis of the cost and utility of OpenAI's language model API on multilingual benchmarks in 22 typologically diverse languages.We show evidence that speakers of a large number of the supported languages are overcharged while obtaining poorer results.These speakers tend to also come from regions where the APIs are less affordable to begin with.Through these analyses, we aim to increase transparency around language model APIs' pricing policies and encourage the vendors to make them more equitable.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Unsupervised Cross-lingual Representation Learning at Scale
Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzmán, F., Grave, E., Ott, M., Zettlemoyer, L., & Stoyanov, V. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.747 · Cited by 5,637
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
Cross-lingual Language Model Pretraining
Lample, G., & Conneau, A. (2019) · arXiv · doi:10.48550/arxiv.1901.07291 · Cited by 1,586
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441
Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates
Kudo, T. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1007 · Cited by 1,021
Is ChatGPT a General-Purpose Natural Language Processing Task Solver?
Qin, C., Zhang, A., Zhang, Z., Chen, J., Yasunaga, M., & Yang, D. (2023) · arXiv · doi:10.48550/arxiv.2302.06476 · Cited by 869
Crosslingual Generalization through Multitask Finetuning
Muennighoff, N., Wang, T., Sutawika, L., Roberts, A., Biderman, S., Le Scao, T., Bari, M. S., Shen, S., Yong, Z. X., Schoelkopf, H., et al. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.891 · Cited by 361
Social Biases in NLP Models as Barriers for Persons with Disabilities
Hutchinson, B., Prabhakaran, V., Denton, E., Webster, K., Zhong, Y., & Denuyl, S. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.487 · Cited by 274
Social Biases in NLP Models as Barriers for Persons with Disabilities
Hutchinson, B., Prabhakaran, V., Denton, E., Webster, K., Zhong, Y., & Denuyl, S. (2020) · arXiv · doi:10.48550/arxiv.2005.00813 · Cited by 274
Cited by
Bias in Large Language Models: Origin, Evaluation, and Mitigation
Guo, Y., Guo, M., Su, J., Yang, Z., Zhu, M., Li, H., Qiu, M., & Liu, S. S. (2024) · arXiv · doi:10.48550/arxiv.2411.10915 · Cited by 208
A review of LLMs and their applications in the architecture, engineering and construction industry
Kampelopoulos, D., Tsanousa, A., Vrochidis, S., & Kompatsiaris, I. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11241-7 · Cited by 69
Playing with words: Comparing the vocabulary and lexical diversity of ChatGPT and humans
Reviriego, P., Conde, J., Merino-Gómez, E., Martínez, G., & Hernández, J. A. (2024) · Machine Learning with Applications · doi:10.1016/j.mlwa.2024.100602 · Cited by 37
Language-Models-as-a-Service: Overview of a New Paradigm and its Challenges
La Malfa, E., Petrov, A., Frieder, S., Weinhuber, C., Burnell, R., Nazar, R., Cohn, A., Shadbolt, N., & Wooldridge, M. (2024) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.15865 · Cited by 9
Beyond Text Compression: Evaluating Tokenizers Across Scales
Lotz, J. F., Lopes, A. V., Peitz, S., Setiawan, H., & Emili, L. (2025) · arXiv · doi:10.48550/arxiv.2506.03101 · Cited by 1
Metadata
- Authors
- Ahia, O., Kumar, S., Gonen, H., Kasai, J., Mortensen, D., Smith, N., & Tsvetkov, Y.
- Venue
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Published
- 2023
- Pages
- 9904-9923
- OpenAlex
- W4389519066
- Cited by
- 40
- References
- 23
- FWCI
- 7.56
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models. https://app.cochat.ai/papers/10.18653/v1/2023.emnlp-main.614
- The paper
- Ahia, O., Kumar, S., Gonen, H., Kasai, J., Mortensen, D., Smith, N., & Tsvetkov, Y. (2023). Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2023.emnlp-main.614
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.