vllm - 💡(How to fix) Fix [Feature]: Support responses api in tokenize endpoint [1 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
vllm-project/vllm#40556Fetched 2026-04-22 07:43:49
View on GitHub
Comments
1
Participants
2
Timeline
2
Reactions
0
Timeline (top)
commented ×1labeled ×1
RAW_BUFFERClick to expand / collapse

🚀 The feature, motivation and pitch

Hi, I see here that the /tokenize api supports chat completions input: https://discuss.vllm.ai/t/tell-me-about-the-current-status-of-the-tokenize-endpoint-in-vllm/2089 . I would like to request that this endpoint also supports the responses api input as it would be great if for any supported input format you could pass the request to tokenize to determine the input tokens the model will receive. Thank you.

Also side note, but the docs here do not make it clear that the /tokenize endpoint even works with chat completions here: https://docs.vllm.ai/en/latest/serving/openai_compatible_server/#tokenizer-api

Alternatives

No response

Additional context

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

extent analysis

TL;DR

The /tokenize API should be updated to support responses API input in addition to chat completions input.

Guidance

  • Review the documentation for the /tokenize endpoint to ensure it accurately reflects the supported input formats.
  • Consider updating the /tokenize endpoint to accept responses API input, allowing for more flexible tokenization.
  • Verify that the updated endpoint can handle both chat completions and responses API input correctly.
  • Check the discussion thread https://discuss.vllm.ai/t/tell-me-about-the-current-status-of-the-tokenize-endpoint-in-vllm/2089 for any additional context or insights.

Notes

The issue lacks technical details about the current implementation of the /tokenize endpoint, so a more detailed solution cannot be provided.

Recommendation

Apply workaround: Update the /tokenize endpoint to support responses API input, as this would provide more flexibility and consistency in tokenization.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

vllm - 💡(How to fix) Fix [Feature]: Support responses api in tokenize endpoint [1 comments, 2 participants]