Skip to content
build.io Docs

Infer To Go (AI Inference)

Infer To Go is Build’s AI model inference add-on, currently in beta. It serves an OpenAI-compatible API, so existing OpenAI client libraries work by pointing them at the Infer To Go base URL.

Provisioning

Section titled “Provisioning”
bld addons:create infer-to-go:basic -a my-app

Two config vars are set on your app:

  • INFER_TO_GO_BASE_URL: the API base URL
  • INFER_TO_GO_API_KEY: the bearer token for requests

Making a request

Section titled “Making a request”
curl "$INFER_TO_GO_BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer $INFER_TO_GO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen3", "messages": [{"role": "user", "content": "Hello"}]}'

Plans

Section titled “Plans”

More tiers are planned.

PlanProvisioning namePrice / mo
Basicinfer-to-go:basic$5

Prices are monthly list prices. The Infer To Go marketplace page carries the current plan list and available models. For attaching, detaching, and removing add-ons, see Add-on Services.