Start free. Pay when the workload grows.
Model usage is pay as you go, from $0.06 per million input tokens. Every account starts with a $25 credit and no card, and includes Models, Context, Documents, and Governance.
Pay as you go. What would a month cost?
Set your volume. At zero credit the API returns 402 rather than billing you. Every model’s rates are in the model library.
Estimate it by hand: input tokens times the input rate, plus output tokens times the output rate. The rates are in the model library.
- Model usage at list rates
- Context (illustrative)
This is more than the starting credit. Usage draws on account credit, so you would add credit as you go.
The Context line applies that measured saving to your input tokens; your own threads will differ, and prompt caching narrows it. See the measurement or work it out for your flow.
Enterprise, on-prem, or your own VPC. Talk to an engineer.
Committed-use pricing, the request-rate limit, deployment in your own VPC or fully air-gapped, SSO and SCIM, and SIEM export are arranged by contract.
What would each product save?
Each product has a calculator on its own page. Enter your numbers and read the with-and-without.
Need more than pay as you go?
Bring one month of usage. We will size higher limits, committed-use pricing, or a deployment in your own VPC.
Pick a time on Google Calendar, no form and no waiting on a reply. Prefer email? hello@tileward.com