Skip to content

LLM API and GPU cost calculator

Estimate your monthly spend on large language model APIs and cloud GPU rental from your own token volumes or GPU hours, and compare every model side by side, in pounds sterling.

Prices last verified between and against each provider’s published price list.See every source

Estimate your AI costs

Amounts in pounds sterling, converted from each provider’s US dollar price list at the rate shown with the results.

Model
Your traffic

API calls, not users. An agent or chain may make several calls per user action.

tokens

System prompt, chat history, retrieved documents and tool definitions together.

tokens

Include reasoning tokens if the model bills them as output.

Discounts
%

Share of input tokens billed at the cached input price.

%

Work that can wait for an asynchronous batch job instead of an instant reply.

The starting figures are examples. Replace them with your own.

GPT-6 Astra estimate

Per month
£5,673
Average month (365 ÷ 12 days)
Per year
£68,082
Per 1,000 requests
£18.65
Per request
£0.0187
Where the money goes (prompts up to 272k input tokens)
PriceTokens per dayCost per dayShare
Input10,000,000£74.6140%
Output3,000,000£111.9260%

Sources: developers.openai.com (checked )

Providers publish these prices in US dollars. Pound figures are converted at £1 = US$1.3403, the Bank of England spot rate for .

Compare every model for this workload

Same requests and token counts on each model, cheapest first. Select a column heading to sort, or a model name to see its breakdown above. List prices are the standard rates for the price tier your prompt length falls in.

Model costs for your workload, sorted by per month (ascending)
vs cheapest
Prompts up to 100,000 input tokensAnthropic£0.0746£0.00746£0.373£0.187£56.73Cheapest
Prompts up to 272K input tokensOpenAI£0.0746£0.00746£0.373£0.187£56.73Cheapest
Mistral AI£0.112n/a£0.448£0.246£74.891.3×
Google (Gemini API)£0.224£0.0224£1.87£0.783£238.294.2×
Mistral AI£0.522£0.0522£1.57£0.992£301.835.3×
Google (Gemini API)£0.56£0.056£2.80£1.40£425.517.5×
Prompts up to 272K input tokensOpenAI£0.746£0.0373£3.73£1.87£567.3510.0×
Anthropic£1.49£0.0746£7.46£3.73£1,13520.0×
Google (Gemini API)£1.49£0.0746£7.46£3.73£1,13520.0×
Prompts up to 272K input tokensOpenAI£1.49£0.0746£7.46£3.73£1,13520.0×
Anthropic£2.98£0.149£14.92£7.46£2,26940.0×
Anthropic£5.97£0.149£29.84£14.92£4,53980.0×
Prompts up to 272K input tokensOpenAI£7.46£0.746£37.31£18.65£5,673100.0×

Worked costs

  • By model

    Each model at five standard workloads.

  • By GPU

    Monthly rental cost across providers.

  • Comparisons

    Models in the same tier, head to head.

Frequently asked questions

Why are the prices converted from US dollars?
The providers in our data publish their prices in US dollars. This page converts them to pounds at £1 = US$1.3403, the Bank of England spot rate for 9 November 2026, so the figures are a guide to the sterling cost rather than an exact amount.
Will I be billed in pounds?
That depends on the provider and your account. Some bill in US dollars, in which case your bank or card issuer applies its own exchange rate and fees. Check your provider’s billing settings to see which currency you will be invoiced in.
Why might the pound figure change when the provider’s price has not?
Because the exchange rate moves. We update the rate when we recheck prices, so a pound figure can rise or fall slightly even when the US dollar list price is unchanged.

Want the reasoning behind the numbers? Our guides (written in US English, with examples in US dollars) cover pre-launch estimates, prompt caching and the break-even point for running your own GPUs.