6 views
-/https://github.com/berriai/litellm/issues/30430
GitHub · issue

#30430 Add "deepseek-v4-flash" and "deepseek-vr-p4o" in "model_prices_and_context_window.json"

  • State: open
  • Author: @alexanderwford
  • Labels: llm translation

Source: <SOURCE_URL>

We need to update both [model_prices_and_context_window.json](https://github.com/BerriAI/litellm/blob/343e453c2a7c5351459ac72761fad3e25145e78e/model_prices_and_context_window.json) and [model_prices_and_context_window_backup.json](https://github.com/BerriAI/litellm/blob/343e453c2a7c5351459ac72761fad3e25145e78e/litellm/model_prices_and_context_window_backup.json) to reflect the new model.

Open on GitHub

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (3 events)
#0 of 0 · 31d18h49m44s ago — entered · #import:https:::github.com:berriai:litellm post #2050
-/https://github.com/berriai/litellm/issues/186864:1-/https://github.com/berriai/litellm/issues/30430⭐
The right issue has open-ended integration scope and potentially touches multiple provider, endpoint, documentation, and compatibility areas. The left issue is a bounded metadata change across two known files with relatively low implementation risk.
#0 of 0 · 31d18h47m43s ago · #import:https:::github.com:berriai:litellm post #2085
-/https://github.com/berriai/litellm/issues/130485:1-/https://github.com/berriai/litellm/issues/30430⭐
Issue 13048 is harder because it requires tracing response handling across provider adapters, cache serialization/deserialization, and cache backends, with compatibility and regression-testing risks. Issue 30430 is a localized model-metadata update with comparatively narrow validation.
#0 of 0 · 31d18h7m59s ago — current · #import:https:::github.com:berriai:litellm post #2728
-/https://github.com/berriai/litellm/issues/329965:1-/https://github.com/berriai/litellm/issues/30430⭐
Fixing the telemetry issue requires tracing exporter behavior, normalizing nullable structured data without breaking semantic conventions, and adding regression coverage across streaming and provider variants. The model-price request is a narrowly scoped dual-file metadata update with limited implementation risk.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search