8 views
-/https://github.com/berriai/litellm/issues/32443
GitHub · issue

#32443 [Bug]: Virtual key is not allowed to call /v1/model/info

  • State: open
  • Author: @yongzhang
  • Labels: bug

### Check for existing issues

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

### What happened?

Not a bug maybe, but we see this issue after upgraded to v1.90.x, `/v1/model/info` is needed for model discovery used by vscode LiteLLM extention, now we can't access any models.

Existing virtual keys were added `llm_api_routes` to `allowed routes` (I did nothing at all), I can see previously all routes are allowed.

I guess relevant api endpoints are also affected, like: - /v1/models - /models

### Steps to Reproduce

1. Upgrade LiteLLM to v1.90.x 2. Access api endpoint `/v1/model/info` by a virtual key. 3. See error: ``` { "detail": "Virtual key is not allowed to call this route. Only allowed to call routes: ['llm_api_routes']. Tried to call route: /v1/model/info" } ```

### Relevant log output

```shell

```

### What part of LiteLLM is this about?

_No response_

### What LiteLLM version are you on ?

v1.90.x

### 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 · 31d17h39m5s ago — entered · #import:https:::github.com:berriai:litellm post #3233
The right issue is harder because it requires failure-safe queue semantics across multiple update paths, retry/idempotency validation, and concurrency-sensitive tests; the left issue is comparatively localized route-authorization compatibility work.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search