tiktoken
OpenAIgithub.com/openai/tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models
Updated 5 h ago · first seen 11 Sept 2026
lib_01M29AAM3PJDM21AYWYZHG9NAJ
- Version
- 0.14.0
- T2 · 5 h ago
- Released
- 17 Aug 2026
- T2 · 5 h ago
Specification
- Repository
Source:PyPI public package metadataT2observed 5 h agomedium
- Author
- Shantanu Jain
Source:PyPI public package metadataT2observed 5 h agomedium
- Homepage
- https://github.com/openai/tiktoken
Source:PyPI public package metadataT2observed 5 h agomedium
- Latest release
- 17 Aug 2026
Source:PyPI public package metadataT2observed 5 h agomedium
- Latest version
- 0.14.0
Source:PyPI public package metadataT2observed 5 h agomedium
- Releases
- 20
Source:PyPI public package metadataT2observed 5 h agomedium
- PyPI
- tiktoken
Source:PyPI public package metadataT2observed 5 h agomedium
- Pypi release at
- 17 Aug 2026
Source:PyPI public package metadataT2observed 5 h agomedium
- Pypi url
- https://pypi.org/project/tiktoken/
Source:PyPI public package metadataT2observed 5 h agomedium
- Pypi version
- 0.14.0
Source:PyPI public package metadataT2observed 5 h agomedium
- Requires python
- >=3.9
Source:PyPI public package metadataT2observed 5 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
5 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 · Author
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 →
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| PyPI public package metadata | pypi.org/pypi/tiktoken/json | package | T2· Quality secondary | 5 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.