ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: clarify Gemini vs Vertex AI model prefix behavior (#19443)

Browse Source 
Add documentation explaining the difference between model formats:
- `gemini/model` → Gemini API (simple API key)
- `vertex_ai/model` → Vertex AI (GCP credentials)
- `model` (no prefix) → defaults to Vertex AI

This addresses user confusion when models without prefix require
GCP authentication instead of simple API key auth.

Ref #8424
This commit is contained in:
Cesar Garcia 2026-01-20 20:22:52 -03:00 committed by GitHub
parent 2b44d02682
commit 94055741d4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 22 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
docs/my-website/docs/providers/gemini.md
View File

@ -15,6 +15,17 @@ import TabItem from '@theme/TabItem';
<br />
:::tip Gemini API vs Vertex AI
| Model Format | Provider | Auth Required |
|-------------|----------|---------------|
| `gemini/gemini-2.0-flash` | Gemini API | `GEMINI_API_KEY` (simple API key) |
| `vertex_ai/gemini-2.0-flash` | Vertex AI | GCP credentials + project |
| `gemini-2.0-flash` (no prefix) | Vertex AI | GCP credentials + project |
**If you just want to use an API key** (like OpenAI), use the `gemini/` prefix.
Models without a prefix default to Vertex AI which requires full GCP authentication.
:::
## API Keys

11
docs/my-website/docs/providers/vertex.md
View File

@ -14,6 +14,17 @@ import TabItem from '@theme/TabItem';
| Base URL | 1. Regional endpoints<br/>`https://{vertex_location}-aiplatform.googleapis.com/`<br/>2. Global endpoints (limited availability)<br/>`https://aiplatform.googleapis.com/`|
| Supported Operations | [`/chat/completions`](#sample-usage), `/completions`, [`/embeddings`](#embedding-models), [`/audio/speech`](#text-to-speech-apis), [`/fine_tuning`](#fine-tuning-apis), [`/batches`](#batch-apis), [`/files`](#batch-apis), [`/images`](#image-generation-models), [`/rerank`](#rerank-api) |
:::tip Vertex AI vs Gemini API
| Model Format | Provider | Auth Required |
|-------------|----------|---------------|
| `vertex_ai/gemini-2.0-flash` | Vertex AI | GCP credentials + project |
| `gemini-2.0-flash` (no prefix) | Vertex AI | GCP credentials + project |
| `gemini/gemini-2.0-flash` | Gemini API | `GEMINI_API_KEY` (simple API key) |
**If you just want to use an API key** (like OpenAI), use the `gemini/` prefix instead. See [Gemini - Google AI Studio](./gemini.md).
Models without a prefix default to Vertex AI which requires GCP authentication.
:::
<br />
<br />