Skip to main content
When we discuss Models, we are normally referring to Large Language Models (LLMs). These models act as the brain of your Agents - enabling them to reason, act, and respond to the user. The better the model, the smarter the Agent. 
from agno.agent import Agent
from agno.models.openai import OpenAIChat

agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    description="Share 15 minute healthy recipes.",
    markdown=True,
)
agent.print_response("Share a breakfast recipe.", stream=True)
Use model strings ("provider:model_id") for simpler configuration. For advanced use cases requiring custom parameters like temperature or max_tokens, use the full model class syntax.

​
Error handling

You can set exponential_backoff to True on the Agent to automatically retry requests that fail due to third-party model provider errors. 
agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    exponential_backoff=True,
    retries=2,
    retry_delay=1,
)

​
Supported Models

Agno supports the following model providers organized by category:

​
Native Model Providers

Anthropic

Anthropic Claude models integration.

Cohere

Cohere language models integration.

DashScope

Alibaba Cloud DashScope models.

DeepSeek

DeepSeek AI models integration.

Google Gemini

Google Gemini models integration.

Meta

Meta AI models integration.

Mistral

Mistral AI models integration.

OpenAI

OpenAI models integration.

OpenAI Responses

OpenAI response format handling.

Perplexity

Perplexity AI models integration.

Vercel

Vercel AI models integration.

xAI

xAI models integration.

​
Local Model Providers

LlamaCpp

LlamaCpp local model inference.

LM Studio

LM Studio local model integration.

Ollama

Ollama local model integration.

VLLM

VLLM high-throughput inference.

​
Cloud Model Providers

AWS Bedrock

Amazon Web Services Bedrock models.

Claude via AWS Bedrock

Anthropic Claude models via AWS Bedrock.

Azure AI Foundry

Microsoft Azure AI Foundry models.

Azure OpenAI

Microsoft Azure OpenAI models.

Vertex AI Claude

Anthropic Claude models via Google Vertex AI.

IBM WatsonX

IBM WatsonX models integration.

​
Model Gateways & Aggregators

AI/ML API

AI/ML API model provider integration.

Cerebras

Cerebras AI models integration.

Cerebras OpenAI

Cerebras OpenAI-compatible models.

CometAPI

CometAPI model provider integration.

DeepInfra

DeepInfra model provider integration.

Fireworks

Fireworks AI models integration.

Groq

Groq fast inference models.

Hugging Face

Hugging Face models integration.

LangDB

LangDB model provider integration.

LiteLLM

LiteLLM unified model interface.

LiteLLM OpenAI

LiteLLM OpenAI-compatible models.

Nebius AI Studio

Nebius AI Studio models.

Nexus

Nexus model provider integration.

NVIDIA

NVIDIA AI models integration.

OpenRouter

OpenRouter model aggregation.

Portkey

Portkey model gateway integration.

Requesty

Requesty model provider integration.

Sambanova

SambaNova AI models integration.

SiliconFlow

SiliconFlow model provider.

Together

Together AI models integration.
Each provider offers a different set of models, with different capabilities and features. By default, Agno supports all models provided by the mentioned providers.