Using Vercel AI Gateway With Kilo Code

The AI Gateway provides a unified API to access hundreds of models through a single endpoint. It gives you the ability to set budgets, monitor usage, load-balance requests, and manage fallbacks.

Useful links:

Team dashboard: https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai
Models catalog: https://vercel.com/ai-gateway/models
Docs: https://vercel.com/docs/ai-gateway

Getting an API Key

An API key is required for authentication.

Sign Up/Sign In: Go to the Vercel Website and sign in.
Get an API Key: Go to the API Key page in the AI Gateway tab. Create a new key.
Copy the Key: Copy the API key.

Supported Models

The Vercel AI Gateway supports a large and growing number of models. Kilo Code automatically fetches the list of available models from the https://ai-gateway.vercel.sh/v1/models endpoint. Only language models are shown.

The default model is anthropic/claude-sonnet-4 if no model is selected.

Refer to the Vercel AI Gateway Models page for the complete and up-to-date list.

Model Capabilities

Vision Support: Many models support image inputs.
Tool/Computer Use: Select models support function calling and computer use.

Check the model description in the dropdown for specific capabilities.

Configuration in Kilo Code

{% tabs %} {% tab label="VSCode (Legacy)" %}

Open Kilo Code Settings: Click the gear icon ({% codicon name="gear" /%}) in the Kilo Code panel.
Select Provider: Choose "Vercel AI Gateway" from the "API Provider" dropdown.
Enter API Key: Paste your Vercel AI Gateway API key into the "Vercel AI Gateway API Key" field.
Select Model: Choose your desired model from the "Model" dropdown.

{% /tab %} {% tab label="VSCode" %}

Open Settings (gear icon) and go to the Providers tab to add Vercel AI Gateway and enter your API key.

The extension stores this in your kilo.json config file. You can also edit the config file directly — see the CLI tab for the file format.

{% /tab %} {% tab label="CLI" %}

Set the API key as an environment variable or configure it in your kilo.json config file:

Environment variable:

bash

export AI_GATEWAY_API_KEY="your-api-key"

Config file (~/.config/kilo/kilo.json or ./kilo.json):

jsonc

{
  "provider": {
    "vercel": {
      "env": ["AI_GATEWAY_API_KEY"],
    },
  },
}

Then set your default model:

jsonc

{
  "model": "vercel/anthropic/claude-sonnet-4",
}

{% /tab %} {% /tabs %}

Prompt Caching

Vercel AI Gateway supports automatic prompt caching for select models including Anthropic Claude and OpenAI GPT models. This reduces costs by caching frequently used prompts.

Tips and Notes

Model Selection: The Vercel AI Gateway offers a wide range of models. Experiment to find the best one for your needs.
Pricing: The Vercel AI Gateway charges based on the underlying model's pricing, including costs for cached prompts. See the Vercel AI Gateway Models page for details.
Temperature: The default temperature is 0.7 and is configurable per model.
Bring Your Own Key (BYOK): The Vercel AI Gateway has no markup if you decide to use your own key for the underlying service.
More info: Vercel does not add rate limits. Upstream providers may. New accounts receive $5 credits every 30 days until the first payment.

Using Vercel AI Gateway with Kilo Code