tiktoken — Library

Specification

Repository: github.com/openai/tiktoken
Source:PyPI public package metadataT2observed 6 h agomedium
Author: Shantanu Jain
Source:PyPI public package metadataT2observed 6 h agomedium
Homepage: https://github.com/openai/tiktoken
Source:PyPI public package metadataT2observed 6 h agomedium
Latest release: 17 Aug 2026
Source:PyPI public package metadataT2observed 6 h agomedium
Latest version: 0.14.0
Source:PyPI public package metadataT2observed 6 h agomedium
Releases: 20
Source:PyPI public package metadataT2observed 6 h agomedium
PyPI: tiktoken
Source:PyPI public package metadataT2observed 6 h agomedium
Pypi release at: 17 Aug 2026
Source:PyPI public package metadataT2observed 6 h agomedium
Pypi url: https://pypi.org/project/tiktoken/
Source:PyPI public package metadataT2observed 6 h agomedium
Pypi version: 0.14.0
Source:PyPI public package metadataT2observed 6 h agomedium
Requires python: >=3.9
Source:PyPI public package metadataT2observed 6 h agomedium

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

12

Source tiers

T212

Freshest observation

6 h ago

Conflicts

None

Developed by: OpenAI

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

12 claims · 12 properties

Repositoryrepository_url1

Claim history for Repository
Value	Valid from → to	Status	Source	Confidence	Extractor
https://github.com/openai/tiktoken	11 Sept 2026 22:45 UTC → current	current	PyPI public package metadataT2	medium	deterministic

Authorauthor1

Claim history for Author
Value	Valid from → to	Status	Source	Confidence	Extractor
Shantanu Jain	11 Sept 2026 22:45 UTC → current	current	PyPI public package metadataT2	medium	deterministic

Descriptiondescription1

Claim history for Description
Value	Valid from → to	Status	Source	Confidence	Extractor
tiktoken is a fast BPE tokeniser for use with OpenAI's models	11 Sept 2026 22:45 UTC → current	current	PyPI public package metadataT2	medium	deterministic

Homepagehomepage1

Claim history for Homepage
Value	Valid from → to	Status	Source	Confidence	Extractor
https://github.com/openai/tiktoken	11 Sept 2026 22:45 UTC → current	current	PyPI public package metadataT2	medium	deterministic

Latest releaselatest_release_at1

Claim history for Latest release
Value	Valid from → to	Status	Source	Confidence	Extractor
17 Aug 2026	11 Sept 2026 22:45 UTC → current	current	PyPI public package metadataT2	medium	deterministic

Latest versionlatest_version1

Claim history for Latest version
Value	Valid from → to	Status	Source	Confidence	Extractor
0.14.0	11 Sept 2026 22:45 UTC → current	current	PyPI public package metadataT2	medium	deterministic

Releasesmetric.releases1

Claim history for Releases
Value	Valid from → to	Status	Source	Confidence	Extractor
20	11 Sept 2026 22:45 UTC → current	current	PyPI public package metadataT2	medium	deterministic

PyPIpypi1

Claim history for PyPI
Value	Valid from → to	Status	Source	Confidence	Extractor
tiktoken	11 Sept 2026 22:45 UTC → current	current	PyPI public package metadataT2	medium	deterministic

Pypi release atpypi_release_at1

Claim history for Pypi release at
Value	Valid from → to	Status	Source	Confidence	Extractor
17 Aug 2026	11 Sept 2026 22:45 UTC → current	current	PyPI public package metadataT2	medium	deterministic

Pypi urlpypi_url1

Claim history for Pypi url
Value	Valid from → to	Status	Source	Confidence	Extractor
https://pypi.org/project/tiktoken/	11 Sept 2026 22:45 UTC → current	current	PyPI public package metadataT2	medium	deterministic

Pypi versionpypi_version1

Claim history for Pypi version
Value	Valid from → to	Status	Source	Confidence	Extractor
0.14.0	11 Sept 2026 22:45 UTC → current	current	PyPI public package metadataT2	medium	deterministic

Requires pythonrequires_python1

Claim history for Requires python
Value	Valid from → to	Status	Source	Confidence	Extractor
>=3.9	11 Sept 2026 22:45 UTC → current	current	PyPI public package metadataT2	medium	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New libraryLibrarytiktokenOpenAI
New library: tiktoken (OpenAI)
pypi
pypi.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
PyPI public package metadata	pypi.org/pypi/tiktoken/json	package	T2· Quality secondary	6 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.