7 views
-/https://github.com/berriai/litellm/issues/7275
GitHub · issue

#7275 Unable to use any Azure AI models with `services.ai.azure.com` url

  • State: open
  • Author: @semidark
  • Labels: awaiting: user response, march 2025

### Discussed in https://github.com/BerriAI/litellm/discussions/7098 <div type='discussions-op-text'> <sup>Originally posted by **semidark** December 9, 2024</sup> **Hi Folks,** I just got started with LiteLLM as a proxy because I needed an OpenAI-compatible API for my Azure AI Service. I began by working with OpenAI models (`gpt-4o` and `gpt-4o-mini`), and everything worked perfectly. So I thought, *why not try some other models?* I attempted to use `Mistral-large`. Here’s my configuration: ```yaml model_list: - model_name: gpt-4o litellm_params: model: azure/gpt-4o api_base: "https://censored.openai.azure.com/" api_key: "censored" api_version: "2024-05-01-preview" - model_name: gpt-4o-mini litellm_params: model: azure/gpt-4o-mini api_base: "https://censored.openai.azure.com/" api_key: "censored" api_version: "2024-05-01-preview" - model_name: Mistral-large litellm_params: model: azure_ai/Mistral-large api_base: "https://censored.services.ai.azure.com/" api_key: "censored" api_version: "2024-05-01-preview" ``` I tried a few variations of the model strin…

GitHub resolver

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

Refresh page
vote history (2 events)
#0 of 0 · 31d19h6m15s ago — entered · #import:https:::github.com:berriai:litellm post #1970
The right issue is harder because it involves security-sensitive authorization semantics, compatibility with existing key-edit flows, regression coverage, and careful distinction between omitted, unchanged, and intentionally modified fields. The left issue is more narrowly scoped to provider-specific endpoint and request handling.
#0 of 0 · 31d18h11m27s ago — current · #import:https:::github.com:berriai:litellm post #2877
The right-hand task involves provider-specific endpoint handling, request construction, compatibility testing, and regression risk across Azure integrations; the left-hand task has no actionable technical scope, so it is unlikely to require meaningful implementation work.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search