"GCP - Other Models" refers to API
requests to custom endpoints created in Vertex AI. These
endpoints can be used to serve custom or fine tuned models.
Requests to these endpoints will have the above API
structure, as defined by GCP.
Other Models: Fallback Model Name
Amazon Bedrock
AWS - Titan Text G1 - Express
amazon.titan-text-express-v1
Amazon Bedrock
AWS - Titan Text G1 - Lite
amazon.titan-text-lite-v1
Amazon Bedrock
AWS - Titan Embeddings G1 - Text
amazon.titan-embed-text-v1
Amazon Bedrock
AWS - Claude
anthropic.claude-v2/anthropic.claude-v2:1
Amazon Bedrock
AWS - Claude 3 Sonnet
anthropic.claude-3-sonnet-20240229-v1:0
Amazon Bedrock
AWS - Claude 3 Haiku
anthropic.claude-3-haiku-20240307-v1:0
Amazon Bedrock
AWS - Claude Instant
anthropic.claude-instant-v1
Amazon Bedrock
AWS - Jurassic-2 Mid
ai21.j2-mid-v1
Amazon Bedrock
AWS - Jurassic-2 Ultra
ai21.j2-ultra-v1
Amazon Bedrock
AWS - Cohere Command
cohere.command-text-v14
Amazon Bedrock
AWS - Cohere Command Light
cohere.command-light-text-v14
Amazon Bedrock
AWS - Cohere Embed English
cohere.embed-english-v3
Amazon Bedrock
AWS - Cohere Embed Multilingual
cohere.embed-multilingual-v3
Amazon Bedrock
AWS - Llama 2 Chat 13B
meta.llama2-13b-chat-v1
Amazon Bedrock
AWS - Llama 2 Chat 70B
meta.llama2-70b-chat-v1
Amazon Bedrock
AWS - Mistral 7B Instruct
mistral.mistral-7b-instruct-v0:2
Amazon Bedrock
AWS - Mixtral 8X7B Instruct
mistral.mixtral-8x7b-instruct-v0:1
Amazon Bedrock
AWS - Mistral Large
mistral.mistral-large-2402-v1:0
Amazon Bedrock
AWS - Other Models
For example,
arn:aws:bedrock:us-east-1:654654158677:provisioned-model/p1vgneruau99
"AWS - Other Models" refers to any
model on AWS Bedrock that uses provisioned throughput,
including custom and fine-tuned models
Azure OpenAI
Azure OpenAI - Language Models
gpt-35-turbo
gpt-35-turbo-16k
gpt-35-turbo-instruct
gpt-4 (0314, 0613)
gpt-4-32k (0314, 0613)
gpt-4 (1106-Preview)
gpt-4 (0125-Preview)
gpt-4 (turbo-2024-04-09)
gpt-4 (vision-preview)
gpt-4-32k (0314)
gpt-4 (turbo-2024-04-09)
gpt-4 (vision-preview)
gpt-4o == gpt-4o-2024-05-13
gpt-4o-mini
Azure OpenAI
Azure OpenAI - Embedding Models
text-embedding-3-large
text-embedding-3-small
text-embedding-ada-002
Azure OpenAI
Azure OpenAI - Other Models
-
Azure OpenAI
Azure OpenAI - Other Models
Note: This name refers to the above list of model IDs,
as well as fine tuned versions of GPT-3.5 and GPT-4.
<model name>.ft-<random string>-<user defined
suffix>
OpenAI
OpenAI - GPT 3.5 Turbo
gpt-3.5-turbo
gpt-3.5-turbo-16k
gpt-3.5-turbo-instruct
gpt-3.5-turbo-1106
Current Default = gpt-3.5-turbo-0125
OpenAI
OpenAI - GPT 4 Turbo and GPT 4
gpt-4 == gpt-4-0613
gpt-4-32kgpt-4-0314
gpt-4-1106-Preview
gpt-4-0125-Preview
gpt-4-turbo == gpt-4-turbo-2024-04-09
gpt-4-turbo-preview
OpenAI
OpenAI - Text Embedding V3 large
text-embedding-3-large
OpenAI
OpenAI - Text Embedding V3 small
text-embedding-3-small
OpenAI
OpenAI - Text Embedding Ada 002
text-embedding-ada-002
OpenAI
OpenAI - Other Models
ft:<model name>:<org_name>:<user defined
project name>:<random string>
"OpenAI - Other Models" refer to fine-tuned versions of
GPT-3.5 and GPT-4