FROM REQUIREMENTS TO REQUESTS
A considered way to buy capacity.
Start with what your business needs. Agree the model, prices, and delivery terms. Then put your approved capacity to work.
01
Define your requirements
Compare model specifications. Choose a quantity of at least 100 million input-equivalent tokens and describe your token mix, region, retention, and throughput requirements.
02
Agree provider terms
Request a quote or review a firm offer. Check the rate card, expiry, delivery window, and available capacity. Commercial approval is required to accept.
03
Consume and keep track
Use an agreement-scoped API key for supported requests. See validated usage, recorded charges, and the remaining allowance in your workspace.
Spot: capacity for now
Immediate delivery after an offer is accepted and all prerequisites hold. Your agreement still names an end time, allowance, and throughput.
Future: delivery on your schedule
Choose a start at least one hour and up to one calendar year ahead, validated at acceptance. An approved replacement can preserve unused agreed value.
Know how your allowance works
Input, output, and supported cache classes have separate agreed prices. Your 100 MT allowance is input-equivalent consumption, not a promise of 100 million output tokens. Read the price guide.
YOUR NEXT MILLION TOKENS START HERE
Let’s put your AI demand
to work.
to work.
Tell us the models, scale, and delivery window you have in mind.