litellm - 💡(How to fix) Fix WebRTC (gpt-realtime) cost tracking not working in LiteLLM v1.82.3 [1 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
BerriAI/litellm#25738Fetched 2026-04-16 06:36:57
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Participants
Timeline (top)
labeled ×1

Error Message

The backend logs show the following error:

RAW_BUFFERClick to expand / collapse

Hi,

I’d like to ask whether WebRTC-based models (e.g., Azure OpenAI gpt-realtime) are currently supported for cost tracking in LiteLLM.

I tested LiteLLM (v1.82.3) with Azure gpt-realtime using WebRTC, and the inference itself works correctly (audio streaming, responses, etc.). However, I noticed that:

No cost-related logs are generated The backend logs show the following error:

Cost tracking failed for model=gpt-realtime

extent analysis

TL;DR

The issue might be due to missing support for WebRTC-based models in LiteLLM's cost tracking feature, requiring a potential update or workaround.

Guidance

  • Verify the documentation for LiteLLM (v1.82.3) to confirm if WebRTC-based models like Azure OpenAI gpt-realtime are supported for cost tracking.
  • Check the LiteLLM configuration to ensure that cost tracking is enabled for the gpt-realtime model.
  • Investigate the backend logs for any additional error messages that might provide more insight into the "Cost tracking failed" error.
  • Consider reaching out to the LiteLLM community or support team to inquire about potential workarounds or upcoming support for WebRTC-based models.

Notes

The current version of LiteLLM (v1.82.3) may not support cost tracking for WebRTC-based models, which could be the root cause of the issue.

Recommendation

Apply workaround: Given the lack of clear support for WebRTC-based models in the current version, applying a workaround or seeking assistance from the LiteLLM community might be the best course of action until official support is added.

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