Skip to main content
The AI Gateway provides a robust and secure gateway to integrate various Large Language Models (LLMs) into applications, including Cohere’s generation, embedding, and reranking endpoints. With the AI Gateway, take advantage of features like fast AI gateway access, observability, prompt management, and more, while securely managing API keys through Model Catalog.

Quick Start

Get Cohere working in 3 steps:
Tip: You can also send x-portkey-provider: @cohere as a header and use just model="command-r-plus" in the request.

Add Provider in Model Catalog

  1. Go to Model Catalog → Add Provider
  2. Select Cohere
  3. Choose existing credentials or create new by entering your Cohere API key
  4. Name your provider (e.g., cohere-prod)

Complete Setup Guide →

See all setup options, code examples, and detailed instructions

Other Cohere Endpoints

Embeddings

Embedding endpoints are natively supported within the AI Gateway:

Re-ranking

Use Cohere reranking by calling POST /v1/rerank through the gateway with the body expected by Cohere’s reranking API:

Managing Cohere Prompts

Manage all prompt templates to Cohere in the Prompt Library. All current Cohere models are supported, and you can easily test different prompts. Call the POST /v1/prompts/{promptId}/completions endpoint to use the prompt in an application.

Next Steps

Add Metadata

Add metadata to your Cohere requests

Gateway Configs

Add gateway configs to your Cohere requests

Tracing

Trace your Cohere requests

Fallbacks

Setup fallback from OpenAI to Cohere
Last modified on September 15, 2026