Answer: ChatGPT Enterprise can process up to 110k tokens from uploaded documents in the context window; documents under that combined total are fully included, while a single document exceeding 110k tokens has only its first 110k tokens included and the remainder sent to the private search index. For multiple documents whose combined total exceeds 110k tokens, it extracts up to 55k tokens divided evenly, then allocates the remaining 55k tokens proportionally based on tokens left in each document, with any remaining tokens sent only to the private search index. Status: Confirmed Entry: tool/chatgpt/features/file-size-handling Revision: 3 Digest: sha256:eeaff07c2d4e6cc2 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:08:39Z Last changed: 2026-11-19T11:44:13Z (multimedia PDF estimate: 350 pages → —) Last verified: 2026-11-20T11:44:28Z Next check: 2026-11-21T11:44:28Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Unit | Source | As of context window token limit | 110k tokens | tokens | [1] | 2026-11-20 single document limit | 110k tokens | tokens | [1] | 2026-11-20 evenly divided allocation | 55k tokens | tokens | [1] | 2026-11-20 proportional allocation | 55k tokens | tokens | [1] | 2026-11-20 maximum context window | 128k tokens | tokens | [1] | 2026-11-20 Sources: [1] OpenAI. "Optimizing file uploads in ChatGPT Enterprise". https://help.openai.com/en/articles/10029836-optimizing-file-uploads-in-chatgpt-enterprise Role: primary. Accessed: 2026-11-20T11:44:30Z Retrieved via: DeepSeek Fetch API (Markdown conversion; the original server response was not captured) Quote: "ChatGPT Enterprise can process up to 110k tokens from uploaded documents in the context window." (Supports: context window token limit) Quote: "For a single document exceeding 110k tokens, only the first 110k tokens will be included, starting from the beginning." (Supports: single document limit) Quote: "Extract up to 55k tokens, divided evenly among the uploaded documents." (Supports: evenly divided allocation) Quote: "allocate the remaining 55k tokens proportionally based on the tokens left in each document." (Supports: proportional allocation) Quote: "ChatGPT Enterprise uses models with a maximum context window of 128k tokens (roughly 200 pages of text)." (Supports: maximum context window) Snapshot SHA-256: 9ce6fcbdb73062b983b6a5fc42b5aea3a7eeb612a189da3bc81c13ae1bd3dad5 (captured 2026-11-20T11:44:30Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. [1] was retrieved through the DeepSeek Fetch API because a direct request did not return usable content. Cross-check: not-available at 2026-11-20T11:44:28Z. No independent second source is configured for this entry Last successful check: 2026-11-20T11:44:28Z Last attempt: 2026-11-20T11:44:28Z Notes and limitations: Extracted automatically from a single official source (section "Handling files based on size"). Related: https://latestn.com/tool/chatgpt/features/file-type-handling How does ChatGPT Enterprise handle different file types like PDFs, spreadsheets, and images? https://latestn.com/tool/chatgpt/features/find-saved-flashcards Where can I find my saved flashcards later in ChatGPT? https://latestn.com/tool/chatgpt/features/find-saved-shared-content How do I find my saved or shared content in ChatGPT Space? https://latestn.com/tool/chatgpt/features/enable-writing-style-work How do I enable ChatGPT Work to match my writing style? https://latestn.com/tool/chatgpt/features/feature-maturity-levels-meaning What do the feature maturity labels (Under development, Experimental, Beta, Stable) mean for ChatGPT and Codex features? https://latestn.com/tool/chatgpt/features/file-and-audio-uploads Can I upload files and audio to ChatGPT? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-19T11:44:13Z | changed | multimedia PDF estimate: 350 pages → — | [1] 2026-11-15T11:46:42Z | changed | multimedia PDF estimate: — → 350 pages | [1] 2026-11-15T11:46:42Z | changed | single document limit: — → 110k tokens | [1] 2026-11-15T11:46:42Z | changed | single document inclusion limit: 110k tokens → — | [1] 2026-11-13T03:08:39Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/chatgpt/features/file-size-handling/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/chatgpt/features/file-size-handling POST: https://latestn.com/dispute/tool/chatgpt/features/file-size-handling with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/chatgpt/features/file-size-handling?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How does ChatGPT Enterprise handle large files based on size? Revision 3, last verified 2026-11-20T11:44:28Z. https://latestn.com/tool/chatgpt/features/file-size-handling (accessed 2026-11-21T09:59:07Z). @misc{LatestN_tool_chatgpt_features_file_size_handling_r3, title = {How does ChatGPT Enterprise handle large files based on size?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/chatgpt/features/file-size-handling}}, note = {Revision 3; digest sha256:eeaff07c2d4e6cc2; last verified 2026-11-20T11:44:28Z; accessed 2026-11-21T09:59:07Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/chatgpt/features/file-size-handling