Chat Models Comparison

This table compares various Chat Models supported by Spring AI, detailing their capabilities:

  • Multimodality: The types of input the model can process (e.g., text, image, audio, video).

  • Tools/Functions: Whether the model supports function calling or tool use.

  • Streaming: If the model offers streaming responses.

  • Retry: Support for retry mechanisms.

  • Observability: Features for monitoring and debugging.

  • Built-in JSON: Native support for JSON output.

  • Local deployment: Whether the model can be run locally.

  • OpenAI API Compatibility: If the model is compatible with OpenAI’s API.

Provider Multimodality Tools/Functions Streaming Retry Observability Built-in JSON Local OpenAI API Compatible

Anthropic Claude

text, image
yes
yes
yes
yes
no
no
no

Azure OpenAI

text, image
yes
yes
yes
yes
yes
no
yes

Google VertexAI Gemini

text, image, audio, video
yes
yes
yes
yes
yes
no
yes

Groq (OpenAI-proxy)

text, image
yes
yes
yes
yes
no
no
yes

HuggingFace

text
no
no
no
no
no
no
no

Mistral AI

text
yes
yes
yes
yes
yes
no
yes

MiniMax

text
yes
yes
yes
yes
no
no

Moonshot AI

text
no
yes
yes
yes
no
no

NVIDIA (OpenAI-proxy)

text, image
yes
yes
yes
yes
no
no
yes

OCI GenAI/Cohere

text
no
no
no
yes
no
no
no

Ollama

text, image
yes
yes
yes
yes
yes
yes
yes

OpenAI

text, image
yes
yes
yes
yes
yes
no
yes

QianFan

text
no
yes
yes
yes
no
no
no

ZhiPu AI

text
yes
yes
yes
yes
no
no
no

Watsonx.AI

text
no
yes
no
no
no
no
no

Amazon Bedrock/Cohere

text
no
yes
no
no
no
no
no

Amazon Bedrock/Jurassic

text
no
no
no
no
no
no
no

Amazon Bedrock/Llama

text
no
yes
no
no
no
no
no

Amazon Bedrock/Titan

text
no
yes
no
no
no
no
no

Amazon Bedrock/Anthropic 3

text
no
yes
no
no
no
no
no