Model

LLMs at your fingertips

AXAR AI supports multiple providers to interact with different language models. We can specify the provider and model identifier using the @model annotation when defining our agent.

Setting up provider API keys

To use a specific provider, set up the required API key as an environment variable. Each provider has a specific environment variable name. For example, if you're using Anthropic, you can set the API key like this:

export ANTHROPIC_API_KEY="sk-proj-YOUR-API-KEY"

In development, you can simplify API key management by using the dotenv package along with a .env file. Here’s how to set it up:

1. Install the dotenv package Use npm or yarn to install the dotenv package:

   npm install dotenv
   # or
   yarn add dotenv

2. Create a .env file In the root directory of your project, create a .env file and add your API keys:

   ANTHROPIC_API_KEY=sk-proj-YOUR-API-KEY

3. Load the .env file in your code Import and configure dotenv at the entry point of your application (e.g., index.ts):

   import * as dotenv from 'dotenv';
   // Load environment variables from .env file
   dotenv.config();

OpenAI

Supported models

Model	Usage
gpt-4o	@model('openai:gpt-4o')
gpt-4o-mini	@model('openai:gpt-4o-mini')
gpt-4-turbo	@model('openai:gpt-4-turbo')
gpt-4	@model('openai:gpt-4')
o1	@model('openai:o1')
o1-mini	@model('openai:o1-mini')

The API key for OpenAI is read from the OPENAI_API_KEY environment variable.

Anthropic

Supported models

Model	Usage
claude-3-5-sonnet-20241022	@model('anthropic:claude-3-5-sonnet-20241022')
claude-3-5-sonnet-20240620	@model('anthropic:claude-3-5-sonnet-20240620')
claude-3-5-haiku-20241022	@model('anthropic:claude-3-5-haiku-20241022')

The API key for Anthropic is read from the ANTHROPIC_API_KEY environment variable.

Google

Prerequisites

npm install @ai-sdk/google

The API key for Google is read from the GOOGLE_GENERATIVE_AI_API_KEY env variable.

Supported models

Model	Usage
gemini-2.0-flash-exp	@model('google:gemini-2.0-flash-exp')
gemini-1.5-flash	@model('google:gemini-1.5-flash')
gemini-1.5-pro	@model('google:gemini-1.5-pro')

DeepSeek

Prerequisites

npm install @ai-sdk/deepseek

The API key for DeepSeek is read from the DEEPSEEK_API_KEY env var.

Supported models

Model	Usage
deepseek-chat	@model('deepseek:deepseek-chat')

Cerebras

Prerequisites

npm install @ai-sdk/cerebras

The API key for Cerebras is read from theCEREBRAS_API_KEY environment variable.

Supported models

Model	Usage
llama3.1-8b	@model('cerebras:llama3.1-8b')
llama3.1-70b	@model('cerebras:llama3.1-70b')
llama3.3-70b	@model('cerebras:llama3.3-70b')

Groq

Prerequisites

npm install @ai-sdk/groq

The API key for Groq is read from the GROQ_API_KEY environment variable.

Supported models

Model	Usage
llama-3.3-70b-versatile	@model('groq:llama-3.3-70b-versatile')
llama-3.1-8b-instant	@model('groq:llama-3.1-8b-instant')
mixtral-8x7b-32768	@model('groq:mixtral-8x7b-32768')
gemma2-9b-it	@model('groq:gemma2-9b-it')

We can support all models and providers found here, if there's one missing or not working let us know: https://sdk.vercel.ai/docs/foundations/providers-and-models