Cohere provider

Related Documentation
Minimum Version
AI Gateway - 2.0
Incompatible with
on-prem
Tags
#ai
Previous Versions of this page

You can proxy requests to Cohere AI models through AI Gateway by creating AI Model Provider and AI Model entities. This reference documents all supported AI capabilities, configuration requirements, and provider-specific details needed for proper integration.

Upstream paths

AI Gateway automatically routes requests to the appropriate Cohere API endpoints. The following table shows the upstream paths used for each capability.

Capability

Path template

Description

Upstream path or API

Generate /chat/completions, /completions, or /responses Text generation for chat completions and responses /v1/chat
Embeddings /embeddings Vector embeddings from text input /v2/embed
Rerank /rerank Semantic reranking of documents /v1/rerank or /v2/rerank

Supported capabilities

The following tables show the AI capabilities supported by the Cohere provider when configuring AI Models.

By default, AI Gateway uses the path templates shown in the tables below (e.g., /chat/completions, /embeddings, etc.). To customize these paths, configure the config.paths field in your AI Model entity. Custom paths take the form {configured_path}/{template_path} — for example, if you set a custom path of /v2, requests to /embeddings would be routed to /v2/embeddings.

Text generation

Support for Cohere text generation capabilities:

Capability

Streaming

Model example

Path template

Min version

generate Supported command-a-03-2025 /chat/completions, /completions, or /responses 2.0

Embeddings

Support for Cohere embeddings generation:

Capability

Model example

Path template

Min version

embeddings embed-english-v3.0 /embeddings 2.0

Rerank

Support for Cohere reranking capabilities:

Capability

Model example

Path template

Min version

rerank n/a /rerank 2.0

Cohere base URL

The base URL is https://api.cohere.com:443/{capability_path}. The {capability_path} is determined by the AI capability.

AI Gateway uses this URL automatically. You only need to configure a URL if you’re using a self-hosted or Cohere-compatible endpoint, in which case set the upstream_url option in your AI Model configuration.

Supported native LLM formats for Cohere

By default, AI Gateway uses OpenAI-compatible request formats. Configure a native format in your AI Model to use Cohere-specific APIs and features.

The following native Cohere formats are supported:

LLM format

Supported APIs

cohere
  • /v1/rerank
  • /v2/rerank

Configure Cohere

To use Cohere with AI Gateway, configure a new AI Model Provider. You can then access supported AI Models from Cohere.

Here’s a minimal configuration for chat completions:

FAQs

Configure an AI Model with a Cohere AI Model Provider and send queries with candidate documents. The model filters for relevance and returns answers with citations.

Help us make these docs great!

Kong Developer docs are open source. If you find these useful and want to make them better, contribute today!