For teams that buy GPUs and inference

Find inference and compute vendors

Post your workload. Get offers. Compare L1, L2 and the best quality vendor side by side.

Backed byEntrepreneurs First

GPU prices

What GPUs cost, day by day

The average on-demand list price across providers. We track the same providers every day, so one new name can't move the line.

vendors with live prices
price listings read
lowest list price, last day ( providers)

List prices, not what people paid.

See every price, day by day

providers we read prices from. Your request goes to the ones that fit.

Vendors we read prices from

  • Modal
  • Lambda
  • Crusoe
  • Nebius
  • and 50+ more

How it works

You write the spec. We run the auction.

  1. 01

    We find who fits

    Vendors that can run your model at your traffic and latency.

  2. 02

    You see L1 and L2

    Every offer on the same spec. The two cheapest side by side, and the best on quality.

  3. 03

    We do the back and forth

    Quotes, follow ups, terms. You make the call.

Set your terms

Set your terms. Vendors quote against them.

Voice AISample

Gemma 4B on H100s

Workload
Voice agent, live calls
Optimise for
Latency
TTFT p95
200 ms
Peak load
40 requests a second
Uptime
99.9%
Region
US
Test
Shadow workload on a copy of live calls
Optimisation
FP8 allowed, under 1% quality loss

Document intelligenceSample

Qwen VL on L40S or H100

Workload
Extract fields from invoices and contracts
Optimise for
Cost
Volume
2M pages a month, batch overnight
Test
Golden dataset of 500 labelled documents
Compliance
SOC 2, data stays in region
Region
India
Term
6 months

Coding agentSample

Qwen and GLM on B200 or B300

Users
50 engineers
Optimise for
Throughput
TTFT p95
800 ms
TPOT p95
30 ms
Optimisation
Prompt and KV cache, lossless only
PD split
Custom
Term
12 months
Spend now
$28,000 a month

Samples. On the board, buyers' names and companies are never shown.

Got a workload? Tell us what you run.