Cloudflare Workers AI
Description
Cloudflare Workers AI provides hosted inference for open-source models. The gateway routes requests to the per-account Workers AI endpoint at https://api.cloudflare.com/client/v4/accounts/<ACCOUNT_ID>/ai/v1/chat/completions. The wire format is OpenAI-compatible.
| Feature | Limitation |
|---|---|
| Chat completions | — |
| Streaming responses (SSE) | — |
| Tool use | Depends on the underlying model. |
| Vision input | Depends on the underlying model. |
| Embeddings | Not exposed by the gateway. |
Required gateway configuration
| Key | Required | Description |
|---|---|---|
cf_account_id |
yes | The Cloudflare account ID. The gateway substitutes this value into the per-account Workers AI URL. |
If cf_account_id is unset, the gateway substitutes the literal string ACCOUNT_ID and the request fails.
BYOK key format
The BYOK value for the cloudflare provider is a Cloudflare API token with the Workers AI:Read permission. The gateway sends the token in the Authorization: Bearer <KEY> header.
Adding the key
The procedure for storing a BYOK key is the same for every provider. See Provider keys (BYOK) for the steps. Select cloudflare in the Provider drop-down list and paste the API token in the API Key field.