NVNVGPU

Project planner

Plan your GPU session.

Choose a GPU. Set your session. Compare the total.

Rates dated Sep 24, 2026–Sep 27, 2026

Publication dates, not live quotes. Confirm the current rate and capacity with the provider.

Catalog generated .

Some listed rates are over 72 hours old. Confirm current rates.

Start with an exact model →

Model → workload → exact configuration

Find a GPU for DeepSeek-R1-Distill-Qwen-14B (publisher BF16)

Single-GPU text inference. Estimates remain unknown where exact hardware, runtime or charges lack evidence. NVGPU does not reserve stock or stop your instance.

Input includes system instructions, history and tool text. Total context is 8,192 tokens for each request. The current profile supports up to 16,384 tokens and one simultaneous request.

Base and high are your scenarios, not probability bounds. Each launch includes setup, useful work, idle, export and shutdown. Count overlapping startup activities once using their total elapsed allowance. Sessions use one instance at a time.

Session group 1
Export, idle and shutdown stages
Storage copies, transfers and other charges

List each physical copy once. Running, stopped and retained durations for the same copy cannot overlap. Catalog disk capacity does not establish that its price is included. A blank rate uses a current reviewed tariff only for an explicitly selected supported product; its monthly conversion still needs your input.

Include repeated downloads and output exports in the total volume. A free destination tariff does not establish free source-cloud egress.

An explicit zero means you assume no charge. Unknown fees prevent a complete total or within-budget claim.

Confirmed credits and account funding

Ordinary cost and budget checks stay separate from one-time credits. No signup award or eligibility is assumed. Funding is cash placed in an account, not an extra resource charge.

Billing assumption for products without a current policy

A current product-scoped provider policy takes priority. These inputs are assumptions and never change the whole-instance quote.

Runtime allowance assumption

Blank remains unknown. This allowance does not establish hardware compatibility, measured memory or a tested runtime.

Submit your workload to compare exact configurations.
Start with a reviewed workflow →
Interconnect and procurement requirements

Unknown evidence does not match a requirement. Provider statements are labeled separately from reviewed reports. No compliance reports have been reviewed yet. HIPAA use needs the appropriate service scope, configuration and BAA. Advertised bandwidth is not a measured guarantee.

Exact configurations

Loading…

Live stock is not connected. Catalog prices remain available; stock is unknown.

Session planner preview

Plan the whole session

Comparing 0 selected configurations from your shortlist. Compute uses the whole-instance rate, including every GPU.

Base and high are your scenarios, not probability bounds. Each launch includes setup, useful work, idle, export and shutdown. Count overlapping startup activities once using their total elapsed allowance. Sessions use one instance at a time.

Session group 1
Export, idle and shutdown stages
Storage copies, transfers and other charges

List each physical copy once. Running, stopped and retained durations for the same copy cannot overlap. Catalog disk capacity does not establish that its price is included. A blank rate uses a current reviewed tariff only for an explicitly selected supported product; its monthly conversion still needs your input.

Include repeated downloads and output exports in the total volume. A free destination tariff does not establish free source-cloud egress.

An explicit zero means you assume no charge. Unknown fees prevent a complete total or within-budget claim.

Confirmed credits and account funding

Ordinary cost and budget checks stay separate from one-time credits. No signup award or eligibility is assumed. Funding is cash placed in an account, not an extra resource charge.

Billing assumption for products without a current policy

A current product-scoped provider policy takes priority. These inputs are assumptions and never change the whole-instance quote.