> ## Documentation Index
> Fetch the complete documentation index at: https://spacesail.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# What are Models?
> Language Models are machine-learning programs that are trained to understand natural language and code.
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.
```python theme={null}
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](/concepts/models/model-as-string) (`"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.
```python theme={null}
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 Claude models integration.
Cohere language models integration.
Alibaba Cloud DashScope models.
DeepSeek AI models integration.
Google Gemini models integration.
Meta AI models integration.
Mistral AI models integration.
OpenAI models integration.
OpenAI response format handling.
Perplexity AI models integration.
Vercel AI models integration.
xAI models integration.
### Local Model Providers
LlamaCpp local model inference.
LM Studio local model integration.
Ollama local model integration.
VLLM high-throughput inference.
### Cloud Model Providers
Amazon Web Services Bedrock models.
Anthropic Claude models via AWS Bedrock.
Microsoft Azure AI Foundry models.
Microsoft Azure OpenAI models.
Anthropic Claude models via Google Vertex AI.
IBM WatsonX models integration.
### Model Gateways & Aggregators
AI/ML API model provider integration.
Cerebras AI models integration.
Cerebras OpenAI-compatible models.
CometAPI model provider integration.
DeepInfra model provider integration.
Fireworks AI models integration.
Groq fast inference models.
Hugging Face models integration.
LangDB model provider integration.
LiteLLM unified model interface.
LiteLLM OpenAI-compatible models.
Nebius AI Studio models.
Nexus model provider integration.
NVIDIA AI models integration.
OpenRouter model aggregation.
Portkey model gateway integration.
Requesty model provider integration.
SambaNova AI models integration.
SiliconFlow model provider.
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.