Skip to content
Genkit JavaGenkit JavaJava (Unofficial)

Cohere

Installation

Section titled “Installation”
<dependency>
    <groupId>com.google.genkit</groupId>
    <artifactId>genkit-plugin-cohere</artifactId>
    <version>1.0.0-SNAPSHOT</version>
</dependency>

Configuration

Section titled “Configuration”
Terminal window
export COHERE_API_KEY=your-api-key

Usage

Section titled “Usage”
import com.google.genkit.plugins.cohere.CoherePlugin;


Genkit genkit = Genkit.builder()
    .plugin(CoherePlugin.create())
    .build();


ModelResponse response = genkit.generate(
    GenerateOptions.builder()
        .model("cohere/command-a-03-2025")
        .prompt("Tell me about AI")
        .build());

Available models

Section titled “Available models”
  • cohere/command-a-plus-05-2026 — flagship (Mixture-of-Experts, text + vision)
  • cohere/command-a-reasoning-08-2025
  • cohere/command-a-vision-07-2025
  • cohere/command-a-03-2025
  • cohere/command-r7b-12-2024
  • cohere/command-r-08-2024
  • cohere/command-r-plus-08-2024

Embeddings

Section titled “Embeddings”

Cohere embedding models are available through the OpenAI-compatible endpoint:

  • cohere/embed-v4.0
  • cohere/embed-multilingual-v3.0
  • cohere/embed-english-v3.0
EmbedResponse response = genkit.embed("cohere/embed-v4.0", documents);

Features

Section titled “Features”
  • Text generation, tool calling, RAG support, SSE streaming, embeddings

Sample

Section titled “Sample”

See the cohere sample.