8 views
-/https://github.com/berriai/litellm/issues/28306
GitHub · issue

#28306 Add "deepseek" and "llama-4-scout" "model_prices_and_context_window.json"

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

Source: https://openrouter.ai/deepseek/deepseek-v4-flash:free) and [meta-llama/llama-4-scout](https://openrouter.ai/meta-llama/llama-4-scout)

We need to update both [model_prices_and_context_window.json](https://github.com/BerriAI/litellm/blob/79b45786719778117debd57e38b9262283431ce2/model_prices_and_context_window.json) and [model_prices_and_context_window_backup.json](https://github.com/BerriAI/litellm/blob/79b45786719778117debd57e38b9262283431ce2/litellm/model_prices_and_context_window_backup.json) to reflect the new model.

GitHub resolver

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

Refresh page
vote history (2 events)
#0 of 0 · 31d18h40m28s ago — entered · #import:https:::github.com:berriai:litellm post #2493
The right issue is harder because it requires tracing and correcting authentication middleware behavior across MCP request handling, OAuth challenge generation, error mapping, and client compatibility, with integration and regression testing. The left issue is a bounded metadata update affecting static pricing/context records with straightforward validation.
#0 of 0 · 31d18h29m13s ago — current · #import:https:::github.com:berriai:litellm post #2680
The left issue requires diagnosing and safely changing asynchronous shutdown behavior across worker lifecycle boundaries, with database-driver error handling, concurrency, regression testing, and deployment-specific validation. The right issue is primarily a contained metadata update with straightforward schema and verification work.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search