SHARED-COMPUTE PRICING
Selected models. Compare the offer.
Offer for eligible open-weight models: 50% below comparable hosted rates. Confirm the model version, comparison provider, usage mix and service terms before onboarding.
What would you save?
Enter a comparable hosted cost for a selected model. This illustration applies the 50% price difference; it does not quote a live provider rate or set billing terms.
$500 less for the same comparison period.
Match the model version, input/output mix, caching, and service terms. Eligibility and the comparison rate are confirmed with your team.
How the comparison works.
What is the comparison?
The same selected open-weight model hosted by a model lab or neocloud provider. Compare matching model versions, input and output usage, cache treatment, and service terms.
Which models qualify?
The offer applies to selected models. We confirm the eligible model, comparison provider, and applicable rates with you before onboarding.
Is this a monthly token pack?
No. Shared compute is priced around model-specific hosted inference rates. The previous monthly token-pack offer no longer applies.
What does the calculator show?
An illustration of the 50% price difference using a comparable hosted cost you enter. It is not a published model rate or a billing quote.
YOUR NEXT STEP
Request hosted access.
Tell us about your workload to confirm availability and rates. A console account alone does not enable inference access.
Create a console account
Already have an account? Sign in ↗