Cloudflare Workers AI

Our Gemma-SEA-LION-v4-27B-IT model is now supported on the Cloudflare Workers AI for on-demand inferencing, subject to Cloudflare's Data Usage and Pricing Plans.

This quickstart guide will instruct you through setting up your Workers AI account and REST API to easily experiment with Gemma-SEA-LION-v4-27B-IT. For more detailed information, you can refer directly to the latest guide on Cloudflare here

Step 1. Create a Cloudflare Account

Sign up for a Cloudflare account if you have not already done so.

Step 2. Get Cloudflare API token and Account ID

You need your API token and Account ID to use the REST API.

To get these values:

• In the Cloudflare dashboard, go to the Workers AI page and select REST API:

• Get your API token:

  • Select Create a Workers AI API Token.

  • Review the prefilled information.

  • Select Create API Token.

  • Select Copy API Token.

  • Save that value for future use.

• For Get Account ID, copy the value for Account ID. Save that value for future use.

3. Run Gemma-SEA-LION-v4-27B-IT via Cloudflare Workers AI API

After creating your API token, authenticate and make requests to the Worker AI API using your API token in the request.

curl

curl https://api.cloudflare.com/client/v4/accounts/{$CLOUDFLARE_ACCOUNT_ID}/ai/run/@cf/aisingapore/gemma-sea-lion-v4-27b-it \
  -X POST \
  -H 'Authorization: Bearer {$CLOUDFLARE_AUTH_TOKEN}' \
  -d '{
    "messages": [
        {
            "role": "system",
            "content": "You are a friendly assistant"
        },
        {
            "role": "user",
            "content": "Tell me a Singlish joke!"
        }
    ],
    "stream": false
    }'

python

Cloudflare also supports OpenAI compatible endpoints for text generation (/v1/chat/completions)

curl

curl --request POST \
  --url https://api.cloudflare.com/client/v4/accounts/{$CLOUDFLARE_ACCOUNT_ID}/ai/v1/chat/completions \
  -H 'Authorization: Bearer {$CLOUDFLARE_AUTH_TOKEN}' \
  -H 'Content-Type: application/json' \
  -d '{
      "model": "@cf/aisingapore/gemma-sea-lion-v4-27b-it",
      "messages": [
        {
          "role": "user",
          "content": "Tell me a Singlish joke"
        }
      ]
    }'

python