Core Features
| Agno Supported Models | Tool Support | Response Models | Knowledge | History / Storage | Async Execution | Async Tool Support |
|---|---|---|---|---|---|---|
| Anthropic Claude | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| AWS Bedrock | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| AWS Bedrock Claude | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Azure AI Foundry | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Azure OpenAI | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Cohere | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| DeepInfra | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| DeepSeek | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Fireworks | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Gemini | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Groq | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| HuggingFace | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| IBM WatsonX | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| InternLM | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| LangDB | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| LiteLLM | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| LiteLLMOpenAI | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| LM Studio | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Mistral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Nvidia | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Nebius | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Ollama | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| OllamaTools | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| OpenAIChat | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| OpenAIResponses | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| OpenRouter | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Perplexity | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Sambanova | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Together | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| XAI | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
HuggingFace supports tool calling through the Agno framework, but not for streaming
responses.
Perplexity supports tool calling through the Agno framework, but their models don't
natively support tool calls in a straightforward way. This means tool usage may
be less reliable compared to other providers.
Multimodal Support
| Agno Supported Models | Image Input | Audio Input | Audio Responses | Video Input | File Upload |
|---|---|---|---|---|---|
| Anthropic Claude | ✅ | ✅ | |||
| AWS Bedrock | ✅ | ||||
| AWS Bedrock Claude | ✅ | ||||
| Azure AI Foundry | ✅ | ||||
| Azure OpenAI | ✅ | ||||
| Cohere | |||||
| AWS Bedrock | ✅ | ||||
| AWS Bedrock Claude | ✅ | ||||
| Azure AI Foundry | ✅ | ||||
| Azure OpenAI | ✅ | ||||
| Cohere | ✅ | ||||
| DeepInfra | |||||
| DeepSeek | |||||
| Fireworks | |||||
| Gemini | ✅ | ✅ | ✅ | ✅ | |
| Groq | ✅ | ||||
| HuggingFace | ✅ | ||||
| IBM WatsonX | ✅ | ||||
| InternLM | |||||
| LangDB | ✅ | ✅ | |||
| LiteLLM | |||||
| LiteLLMOpenAI | |||||
| LM Studio | ✅ | ||||
| Mistral | ✅ | ||||
| Nvidia | |||||
| Nebius | |||||
| Ollama | ✅ | ||||
| OllamaTools | |||||
| OpenAIChat | ✅ | ✅ | ✅ | ||
| OpenAIResponses | ✅ | ✅ | ✅ | ✅ | |
| OpenRouter | |||||
| Perplexity | |||||
| Sambanova | |||||
| Together | ✅ | ||||
| XAI | ✅ |
Structured Outputs
| Agno Supported Models | Structured Outputs | JSON Mode |
|---|---|---|
| Anthropic Claude | ✅ | |
| AWS Bedrock | ✅ | |
| AWS Bedrock Claude | ✅ | |
| Azure AI Foundry | ✅ | |
| Azure OpenAI | ✅ | ✅ |
| Cohere | ✅ | |
| DeepInfra | ✅ | |
| DeepSeek | ✅ | |
| Fireworks | ✅ | ✅ |
| Gemini | ✅ | ✅ |
| Groq | ✅ | |
| HuggingFace | ✅ | |
| IBM WatsonX | ✅ | |
| InternLM | ✅ | ✅ |
| LangDB | ✅ | ✅ |
| LiteLLMOpenAI | ✅ | ✅ |
| LiteLLM | ✅ | |
| LM Studio | ✅ | ✅ |
| Mistral | ✅ | ✅ |
| Nvidia | ✅ | |
| Nebius | ✅ | ✅ |
| Ollama | ✅ | ✅ |
| OllamaTools | ✅ | ✅ |
| OpenAIChat | ✅ | ✅ |
| OpenAIResponses | ✅ | ✅ |
| OpenRouter | ✅ | ✅ |
| Perplexity | ✅ | ✅ |
| Sambanova | ✅ | |
| Together | ✅ | ✅ |
| XAI | ✅ | ✅ |
LM Studio supports JSON schema output, but not structured outputs.