Supported LLM providers

Supported LLM providers

The AI Enabler Proxy integrates with various Large Language Model (LLM) providers, enabling efficient request routing based on complexity and cost. This document outlines the supported providers and their available models for routing and proxying.

Provider overview

Below is a comprehensive table of supported providers, their API identifiers, any additional required fields, and the models they support for routing and proxying:

ProviderAPI IdentifierAdditional Required FieldsRoutable ModelsProxyable Models
OpenAIOPENAIN/Agpt-4o-2024-05-13, gpt-4o-mini-2024-07-18, gpt-4o-2024-08-06ft:gpt-4-0613, ft:gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4-0125-preview, gpt-3.5-turbo, ft:gpt-4o-2024-08-06, gpt-4-0314, gpt-4-32k-0613, gpt-4-turbo-preview, gpt-4-32k, gpt-4o-2024-05-13, gpt-4o-mini, gpt-3.5-turbo-1106, gpt-4-0613, gpt-4-turbo, gpt-3.5-turbo-0125, gpt-4, gpt-4o, gpt-4o-mini-2024-07-18, gpt-4-32k-0314, gpt-4-turbo-2024-04-09, gpt-4-1106-preview, gpt-4o-2024-08-06, ft:gpt-4o-mini-2024-07-18, ft:gpt-3.5-turbo-0125, ft:gpt-3.5-turbo-0613, ft:gpt-3.5-turbo-1106
AzureAZUREurl and apiVersiongpt-4o-2024-08-06gpt-4o, gpt-3.5-turbo, gpt-3.5-turbo-0125, gpt-4-1106-preview, gpt-4-0613, gpt-4-0125-preview, gpt-4-32k-0613, gpt-4-turbo-2024-04-09, gpt-3.5-turbo-16k, gpt-4-32k, command-r-plus, gpt-4-turbo, gpt-3.5-turbo-1106, gpt-4o-mini, gpt-4o-2024-08-06, gpt-4, mistral-large-2402
AzureAIAZUREAIurlN/Amistral-small, mistral-large
AnthropicANTHROPICN/Aclaude-3-5-sonnet-20240620claude-3-sonnet-20240229, claude-instant-1, claude-2, claude-3-5-sonnet-20240620, claude-3-opus-20240229, claude-instant-1.2, claude-3-haiku-20240307, claude-2.1
GeminiGEMININ/Agemini-1.5-progemini-1.5-pro-001, gemini-pro, gemini-gemma-2-27b-it, gemini-1.5-pro, gemini-gemma-2-9b-it, gemini-1.5-flash
VertexAI (Gemini)VERTEXAIGEMINIurlgemini-1.5-progemini-1.0-ultra-001, gemini-1.0-pro-001, gemini-1.5-pro, gemini-1.5-flash, gemini-pro, gemini-1.5-pro-001, gemini-1.0-pro
VertexAI (Anthropic)VERTEXAIANTHROPICurlclaude-3-5-sonnet-20240620claude-3-haiku-20240307, claude-3-5-sonnet-20240620, claude-3-sonnet-20240229, claude-3-opus-20240229
GroqGROQN/Allama3:8b, llama3:70bllama3.1:8b, llama3:8b, llama3.1:70b, llama3:70b, llama2:70b, mixtral-8x7b-32768, gemma-7b-it
MistralMISTRALN/AN/Amistral-large-2407, mistral-large-2402, mixtral-8x7b-32768, mistral-medium-2312, open-mixtral-8x22b, codestral-2405, mistral-small, open-mistral-7b, open-mistral-nemo-2407, mistral-tiny
OllamaOLLAMAurlllama3:70b, llama3:8b, llama2:7bllama3:70b, llama3:8b, llama2:7b, llama2:13b, llama2:70b
CohereCOHEREN/AN/Acommand-r-08-2024, command-r-plus-08-2024, command-r-plus, command-r, command-light
DatabricksDATABRICKSurlllama3:70bdatabricks-mpt-30b-instruct, databricks-mpt-7b-instruct, databricks-dbrx-instruct, llama3:70b, llama2:70b
CodestralCODESTRALN/AN/Acodestral-2405

This table provides a quick reference for the supported providers, their API identifiers, any additional fields required for configuration, and the models available for routing and proxying. For detailed information on configuring and using these providers with the CAST AI LLM Proxy, please refer to the getting started guide.