6 views
-/https://github.com/berriai/litellm/issues/27463
GitHub · issue

#27463 [Bug]: Billing units and models are automatically refreshed and loaded.

  • State: open
  • Author: @JosonQian
  • Labels: bug, llm translation

### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

Hello, I have two questions. First, many new models have been added, such as deepseek-v4, gpt-5.5, and opus-4.7, but they cannot be loaded directly from litellm. I can only get the model I want by manually configuring and restarting. Second, the models used in this way do not have price unit statistics, and these prices are not actually in the model_prices_and_context_window.json file, which causes the actual budget to be exceeded when using them.Looking forward to your reply, thank you.

### Steps to Reproduce

1. 2. 3.

### Relevant log output

```shell

```

### What part of LiteLLM is this about?

_No response_

### What LiteLLM version are you on ?

litellm/litellm:main-v1.83.10-stable

### Twitter / LinkedIn details

_No response_

GitHub resolver

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

Refresh page
vote history (1 events)
#0 of 0 · 31d18h41m13s ago — entered · #import:https:::github.com:berriai:litellm post #2387
27463 has broader cross-cutting scope: registry synchronization, pricing metadata integrity, refresh lifecycle, and billing validation, with greater compatibility and correctness risk. 26151 is comparatively localized to tracing and repairing a secret-resolution call path.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search