Run or Rent

UK · pounds · no account

Is it cheaper to run the model, or rent the API?

For people who use Ollama, LM Studio or llama.cpp, and for small firms deciding whether to buy a GPU or keep paying the API. The sums are in pounds, and every number has a source or is labelled an estimate.

The job
Chatbot for a small teamSummarise 1,000 documentsCoding assistant all day

One person, 80 requests a day, 21 working days. 3,000 tokens in and 800 out. A heavy month of coding chat. An editor cache can cut the input.

Model and card

No shop price on file for this card.

Ofgem price cap, average electricity unit rate for a Direct Debit customer in England, Scotland and Wales on a single-rate default tariff. No VAT on electricity in this period, per Ofgem. The daily standing charge is not included. Your region and payment method can differ. Ofgem, 1 October 2026 to 31 December 2026.

Speed and power

Filled when a sourced run exists. Otherwise type the speed you see in Ollama, LM Studio or llama.cpp.

Starts at the card's maximum rated power. Lower it if you measured the draw.

Rent it

Rent. The API is £0.12 a month and the electricity is £1.31. The card costs more to run than to call, before you count buying it.

Upper estimate. 450 W × (3800 tokens ÷ 160.8 tokens/sec ÷ 3,600) ÷ 1,000 × 26.32p/kWh

That expression is pence for one job. Divide by 100 for pounds, then multiply by the jobs in the month. Inputs: 450 W maximum rated power, 3,800 tokens, 160.8 tokens/sec, 26.32p/kWh.

API this month
£0.12
Electricity this month
£1.31 · 4.96 kWh
GPU purchase
Not on file
Break-even
Does not break even
  • API cost is input tokens and output tokens, priced per million, times jobs per month. No caching, batch discount, or free tier.
  • Pound figures use the stored exchange rate. They are not a quote from the company that trained the model.
  • Upper estimate. Every token, in and out, is divided by the reported tokens per second. Prompt tokens are usually faster than that, and a card rarely holds its maximum rated power for the whole job, so the real bill is often lower.
  • Formula, in pence per job: 450 W × (3800 tokens ÷ 160.8 tokens/sec ÷ 3,600) ÷ 1,000 × 26.32p/kWh. Divide by 100 for pounds, then multiply by the jobs in the month.
  • The tokens per second are one published run, not a promise for your PC. Context length and software change it.
  • The watts are the card's maximum rated graphics power. Real draw during inference is usually lower.
  • The standing charge on a home bill is not added. A GPU does not create a second one.
  • API price: £0.0149 in and £0.0298 out per million tokens, from $0.0200 and $0.0400 at 0.74501 dollars to the pound on 2026-11-10. OpenRouter feed 2026-11-11.
  • Speed: 160.8 reply tokens/sec, 4283.1 prompt tokens/sec, Q4_K_M, llama.cpp b11803. Run r_32ipo1hbbwl, marked Measured by llm-speed. Chat-short workload. Power draw was not published, so electricity uses the card's official total graphics power and is labelled an estimate. Page read 11 November 2026.
  • GeForce RTX 4090: 24 GB GDDR6X. Total graphics power: 450 W. Specs read 2026-11-11.
  • Speed is the cited run, not a guess.
  • Upper estimate, based on the official total graphics power of 450 W.

OpenRouter prices · Exchange rate · GPU spec · Speed source · Ofgem unit rate