Using Cohere Embed v4.0 on Vercel AI Gateway

Implementation guide · Cohere Embed · Cohere

Serverless

Vercel AI Gateway exposes Cohere Embed v4.0 through model ID cohere/embed-v4.0. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-01. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Vercel AI Gateway and generate an API key.
  2. 2
    Use the Vercel AI Gateway SDK or REST API to call cohere/embed-v4.0 — see the documentation for request format.
  3. 3
    You'll be billed $0.12/1M input. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

Install
pip install openai
API key
AI_GATEWAY_API_KEY
Model ID
cohere/embed-v4.0

creator/model-name e.g. kwaipilot/kat-coder-pro-v2

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
    base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
    model="cohere/embed-v4.0",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing on Vercel AI Gateway

TypePrice (per 1M)
Input tokens$0.12

Capabilities

Multimodal

About Cohere Embed v4.0

Latest multimodal embedding model supporting text, images, and mixed content (e.g., PDFs). Embed v4.0 offers variable embedding dimensions (256, 512, 1024, 1536 default) and supports multiple similarity metrics (Cosine, Dot Product, Euclidean Distance). Ideal for semantic search, classification, and clustering across multimodal data.

Full model details →

Model Specs

Released2025-04-01
Context128k
ArchitectureEncoder Only

Also available on(2)

Microsoft Foundry$0.12/1MCohere API
Compare all providers →

Provider

Vercel AI Gateway

Vercel