You can use Model endpoint management to register any text embedding, multimodal embedding, ranking, or generic model endpoints. model endpoint management also includes models with built-in support and pre-registered Vertex AI models. For more information about different model types, see Model type .
Models with built-in support
This section lists the model names and types for the Vertex AI, OpenAI, and Anthropic models.
Vertex AI
| Model type | Model name |
|---|---|
text-embedding
|
text-embedding-004
|
text-embedding
|
text-embedding-005
|
text-embedding
|
text-embedding-preview-0815
|
text-embedding
|
text-multilingual-embedding-002
|
text-embedding
|
text-embedding-large-exp-03-07
*
|
multimodal_embedding
|
multimodalembedding@001
|
reranking
|
semantic-ranker-default-003
|
- The
text-embedding-large-exp-03-07model is available only in theus-central1region.
OpenAI
| Model type | Qualified model name |
|---|---|
text-embedding
|
text-embedding-ada-002
|
text-embedding
|
text-embedding-3-small
|
text-embedding
|
text-embedding-3-large
|
Anthropic
| Model type | Qualified model name |
|---|---|
generic
|
claude-3-opus-20240229
|
generic
|
claude-3-sonnet-20240229
|
generic
|
claude-3-haiku-20240307
|
Pre-registered Vertex AI models
The following table lists the types, IDs, and extension versions of pre-registered Vertex AI models.
Model type
Model ID
Extension version
generic
-
gemini-1.5-pro:streamGenerateContent -
gemini-1.5-pro:generateContent -
gemini-1.0-pro:generateContent
version 1.4.2 and later
text-embedding
gemini-embedding-001
version 1.3 and later
