Skip to content

Model Catalog

Our comprehensive model catalog provides a diverse array of models for your selection. To configure your agents to leverage any of these models, please refer to our project configuration guidelines. Below, you will find a list of the models currently supported. We are dedicated to the continuous enhancement and expansion of our model catalog, so please visit this page regularly for the latest updates.

LLMs & VLMs

The table below lists the LLMs and VLMs currently supported:

LLM / VLM Input Modalities Output
meta-llama/Llama-3.1-8B-Instruct text text
meta-llama/Llama-3.1-70B-Instruct text text
meta-llama/Llama-3.3-70b-Instruct text text
meta-llama/Llama-4-Maverick-17B-128E-Instruct text text
meta-llama/Llama-3.2-90B-Vision-Instruct text, image text
mistralai/Mistral-7B-Instruct-v0.3 text text
mistralai/Mistral-Small-3.1-24B-Instruct-2503 text, image text
Qwen/Qwen3-32B text text

Configuring LLMs & VLMs for Your Project

To integrate any of the supported models into your project, update the relevant configuration section within the base_config or the config block of any utility agents in your YAML file. For models that support image input, ensure the agent is capable of handling images (e.g., ImageUnderstandingAgent). Make sure the model parameter is set to one of the supported model names listed above, and ensure that any required capabilities—such as image input—are supported by the selected agent.

Using LLMs through Our Inference API

You can also directly use any of the models listed above through our inference API. See an example below:

import os

from air import AIRefinery

from air import login

auth = login(
    account=str(os.getenv("ACCOUNT")), # your account 
    api_key=str(os.getenv("API_KEY")), # your API key
)
base_url = os.getenv("AIREFINERY_ADDRESS", "")

client = AIRefinery(**auth.openai(base_url=base_url))

# Create a chat request  
response = client.chat.completions.create(
    messages=[{"role": "user", "content": "What is the capital of France?"}],
    model="meta-llama/Llama-3.1-70B-Instruct", # an LLM from the list  above
)

Embedding Models

The list of models that we support for embedding your data are as follows:

Using Embedding Models in Your Project

To utilize any of these embedding models in your project, simply update the embedding_config within the base_config or within the aisearch_config section of the ResearchAgent. Ensure that the model_name parameter of the embedding_config is set to one of the names listed above.

Embedding Your Data Using Our Inference API

You can also directly use any of the models listed above to embed your data using our inference API. See an example below:

import os

from air import AIRefinery

from air import login

auth = login(
    account=str(os.getenv("ACCOUNT")), # your account 
    api_key=str(os.getenv("API_KEY")), # your API key
)
base_url = os.getenv("AIREFINERY_ADDRESS", "")

client = AIRefinery(**auth.openai(base_url=base_url))

# Create an embedding request  
response = client.embeddings.create(  
    input=["What is the capital of France?"],  
    model="nvidia/nv-embedqa-mistral-7b-v2",  # required
    encoding_format="float",  # required
    extra_body={"input_type": "query", "truncate": "NONE"}  # extra_body is required for "nvidia" models
    # where "input_type" can be either "query" or "passage"
)

Compressors

The list of prompt compression models that we support are:

To utilize any of these prompt compression models in your project, simply update the compression_config within the base_config of your project. To learn more about prompt compression, see this tutorial. Ensure that the model parameter of the compression_config is set to one of the names listed above.

Rerankers

The list of reranker models that we support are:

To utilize any of these reranker models in your project, simply update the reranker_config within the base_config of your project. To learn more about reranking, see this tutorial. Ensure that the model parameter of the reranker_config is set to one of the names listed above.

Diffusers

The list of diffusers we support are:

These diffusers can be used for our image generation agent, and the Images API.