Skip to main content

Supported AI Providers and Models Reference

This reference provides a complete list of all AI providers and models currently supported in elvex.

Updated this week

Overview

elvex supports seven major AI providers, each offering multiple language models. This document lists all available providers, their supported models, and any provider-specific configuration requirements.

Note: To use any of these providers, you must first add them to your elvex account. See Adding an AI Provider for setup instructions.


OpenAI

Configuration Requirements:

Supported Models

Model Name

Notes

o3

Top reasoning capabilities

o3-mini

Smaller reasoning model

GPT-5.2

Latest GPT-5 series

GPT-5.1

GPT-5 series

GPT-5

GPT-5 base model

GPT-5 mini

Efficient GPT-5 variant

GPT-5 nano

Smallest GPT-5 variant

GPT-4.1

1M token context window

GPT-4.1 mini

Efficient GPT-4.1 variant

GPT-4.1 nano

Smallest GPT-4.1 variant

GPT-4o

Multimodal model

GPT-4o mini

Efficient multimodal model

GPT-4 Turbo

Fast GPT-4 variant

GPT-4

Base GPT-4 model

GPT-3.5 Turbo

Legacy model


Azure OpenAI

Configuration Requirements:

  • API Key

  • Endpoint URL (your Azure OpenAI resource endpoint)

  • Deployment ID (the name of your model deployment)

  • Model Name (the underlying model being deployed)

Note: Azure OpenAI uses the same models as OpenAI but requires deployment through Azure. You must create a deployment in Azure before configuring it in elvex.

Supported Models

Azure OpenAI supports the same model list as OpenAI (see above). The model you select must match your Azure deployment configuration.


Anthropic

Configuration Requirements:

Supported Models

Model Name

Notes

Claude 4.5 Opus

Most capable Claude 4.5 model

Claude 4.5 Sonnet

Balanced performance and speed

Claude 4.5 Haiku

Fast and efficient

Claude 4 Opus

Most capable Claude 4 model

Claude 4 Sonnet

Balanced Claude 4 model

Claude 3.5 Haiku

Fast Claude 3.5 model

Claude 3 Haiku

Fast Claude 3 model

Deprecated Models

The following Claude models are deprecated and will be automatically migrated to newer versions:

  • Claude 3 Sonnet (March 2024) → Claude 4.5 Sonnet

  • Claude 3.5 Sonnet (June 2024) → Claude 4.5 Sonnet

  • Claude 3.5 Sonnet (October 2024) → Claude 4.5 Sonnet

  • Claude 3.7 Sonnet (February 2025) → Claude 4.5 Sonnet

  • Claude 3 Opus (March 2024) → Claude 4.5 Opus

  • Claude 2.x and Claude 1.x series → Claude 4.5 Sonnet or Haiku


Google Gemini

Configuration Requirements:

  • API Key (from Google AI Studio)

Supported Models

Model Name

Notes

Gemini 3 Pro Preview

Latest preview model

Gemini 3 Flash Preview

Fast preview model

Gemini 2.5 Pro

Leading overall performance

Gemini 2.5 Pro Preview

Preview version

Gemini 2.5 Flash

Fast and efficient

Gemini 2.5 Flash Preview

Preview version

Gemini 2.5 Flash Lite

Lightweight model

Gemini 2.0 Flash

Previous generation

Gemini 2.0 Flash Lite

Lightweight previous gen

Deprecated Models

The following Gemini models are deprecated and will be automatically migrated:

  • Gemini 2.0 Flash → Gemini 2.5 Flash

  • Gemini 2.0 Flash Lite → Gemini 2.5 Flash Lite

  • Gemini 1.5 Pro → Gemini 2.5 Pro Preview

  • Gemini 1.5 Flash → Gemini 2.5 Flash


Cohere

Configuration Requirements:

  • API Key (from Cohere dashboard)

Supported Models

Model Name

Notes

Command A

Latest Command model

Command Nightly

Experimental features

Command Light Nightly

Lightweight experimental


Mistral

Configuration Requirements:

  • API Key (from Mistral AI platform)

Supported Models

Model Name

Notes

Mistral Large

Most capable model

Mistral Medium

Balanced performance

Ministral 8B

Efficient 8B parameter model

Ministral 3B

Efficient 3B parameter model

Deprecated Models

The following Mistral models are deprecated:

  • Ministral 8B → Mistral Large

  • Ministral 3B → Mistral Large


AWS Bedrock

Configuration Requirements:

  • AWS Access Key ID

  • AWS Secret Access Key

  • Model ID (the specific Bedrock model identifier)

  • AWS Region (configured in your Bedrock setup)

Note: AWS Bedrock requires additional setup including IAM user creation and model access enablement. See Adding an AI Provider - AWS Bedrock section for detailed instructions.

Supported Models

Model Name

Region

Claude 4.5 Sonnet

Standard

Claude 4.5 Sonnet (US)

US regions

Claude 4.5 Haiku

Standard

Claude 4.5 Haiku (US)

US regions

Claude 4.5 Opus

Standard

Claude 4.5 Opus (US)

US regions

Claude 4 Sonnet

Standard

Claude 4 Sonnet (US)

US regions

Claude 3 Haiku

Standard

Meta Llama 3 8B

Standard

Custom

For custom model deployments

Note: Models marked "(US)" are optimized for US regions and may have different availability or pricing.

Did this answer your question?