Kern

Compatibility Overview

Understand which features are supported across different model providers in Kern.

Kern provides comprehensive support across all major model providers, ensuring consistent functionality regardless of which models you choose. This page outlines the features and capabilities supported by each provider.

Core Features

All models on Kern supports:

  • Streaming responses
  • Tool calling
  • Structured outputs
  • Async execution
Note

HuggingFace supports tool calling through the Kern framework, but not for streaming responses.

Note

Perplexity supports tool calling through the Kern 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.

Note

Vercel V0 doesn't support native structured output, but does support use_json_mode=True.

Multimodal Support

Kern Supported ModelsImage InputAudio InputAudio ResponsesVideo InputFile Upload
AIMLAPI✅
Anthropic Claude✅✅
AWS Bedrock✅✅
AWS Bedrock Claude✅✅
Azure AI Foundry✅
Azure OpenAI✅
Cerebras
Cerebras OpenAI
Cohere✅
CometAPI✅
DashScope✅
DeepInfra
DeepSeek
Fireworks
Gemini✅✅✅✅
GeminiInteractions✅✅✅✅
Groq✅
HuggingFace✅
IBM WatsonX✅
InternLM
LangDB✅✅
LiteLLM✅✅
LiteLLMOpenAI✅
LlamaCpp
LM Studio✅
Llama✅
LlamaOpenAI✅
Mistral✅
Nebius
Neosantara
Nexus
Nvidia
Ollama✅
OpenAIChat✅✅✅
OpenAIResponses✅✅✅✅
OpenRouter
Perplexity
Portkey
Requesty
Sambanova
Siliconflow
Together✅
Vercel V0
VLLM
Vertex AI Claude✅
XAI✅

Developer Resources