Model providers
Genkit talks to models through provider plugins. You configure a plugin once, then call any model it exposes through the same generate API. Because the interface is the same across providers, you can swap one model for another, or combine several in one app, without rewriting your application code.
Available providers
Section titled “Available providers”- Google Generative AI: Gemini, Gemma, Veo, and embedding models through the Google AI Studio API (
genkit-google-genai). - Gemini Enterprise: Gemini, Veo, Virtual Try-On, and embedding models via Vertex AI (
genkit-google-genai). - Model Garden in Gemini Enterprise: Claude, Llama, Mistral, and other partner models on Vertex AI (
genkit-vertexai). - Anthropic (Claude): Claude models through the Anthropic Messages API (
genkit-anthropic). - OpenAI: GPT, o-series, and embedding models through the OpenAI API (
genkit-openai). - AWS Bedrock: Claude, Amazon Nova, Llama, Mistral, Cohere, and Stability models on Amazon Bedrock (
genkit-amazon-bedrock). - xAI (Grok): Grok models through xAI’s OpenAI-compatible API (
genkit-openai). - DeepSeek: DeepSeek models through DeepSeek’s OpenAI-compatible API (
genkit-openai).
Local models
Section titled “Local models”- Ollama: Run open models such as Gemma and Llama locally, with no API key.
OpenAI-compatible APIs
Section titled “OpenAI-compatible APIs”- OpenAI-compatible APIs: Connect to any provider that exposes an OpenAI-compatible endpoint.