Skip to content

[FAQ] #295

Description

@youssef-ham

Course

llm-zoomcamp

Question

How can I configure Kestra to use a different LLM provider instead of Google Gemini ?

Answer

Kestra supports multiple LLM providers through its AI Provider plugins, so you're not limited to Google Gemini.

To use a different provider:

  1. Choose one of the supported providers, such as OpenAI, Anthropic, DeepSeek, Ollama, OpenRouter, Hugging Face, Azure OpenAI, or Amazon Bedrock.
  2. Configure the provider with the required credentials (typically an API key or endpoint).
  3. Update your flow or Kestra configuration to use the selected provider instead of GoogleGemini.

For example, if you want to use OpenRouter, replace the provider configuration with the OpenRouter provider and supply your OpenRouter API key. If you want to run models locally, you can use the Ollama provider by pointing Kestra to your local Ollama endpoint.

The currently supported providers include:

  • Google Gemini
  • OpenAI
  • Anthropic
  • OpenRouter
  • DeepSeek
  • Ollama
  • Hugging Face
  • Mistral AI
  • Azure OpenAI
  • Amazon Bedrock
  • GitHub Models
  • Google Vertex AI
  • LocalAI
  • IBM watsonx.ai
  • Cloudflare Workers AI
  • DashScope
  • OCI Generative AI
  • ZhiPu AI

For the latest configuration examples for each provider, refer to the Kestra AI Provider documentation:

https://kestra.io/plugins/plugin-ai/provider

Checklist

  • I have searched existing FAQs and this question is not already answered
  • The answer provides accurate, helpful information
  • I have included any relevant code examples or links

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions