AI task costs · in pounds
What it costs to summarise a 50-page PDF with AI
gpt-oss-120b is the cheapest of the 24 models priced, at 2.2p for 20 PDFs a month (0.11p per PDF). The dearest, GPT-6 Astra, costs £5.88; the middle of the range is Mistral Large 4 at 38p.
How much does it cost to summarise a long PDF report with ChatGPT, Claude or Gemini through their APIs? The answer below covers price only, not quality.
Prices of from OpenRouter's public API price list · converted at the ECB reference rate of ($1 = £0.7538) · Urbano DX
Cost by model, cheapest first
The workload
- A 50-page PDF of about 500 words a page: 25,000 words of text.
- About 0.75 English words per token: 33,300 tokens of document text, plus 700 tokens of instructions. 34,000 input tokens in one request.
- A summary of about 750 words: 1,000 output tokens.
- No prompt cache: every PDF is different.
- 20 PDFs a month, about one each working day.
| Model | Per PDF | 20 PDFs a month | Rate used (USD) |
|---|---|---|---|
| gpt-oss-120bOpenAI | 0.11p | 2.2p | $0.037 in, $0.17 out per 1M tokens |
| DeepSeek V4.1 FlashDeepSeek | 0.12p | 2.4p | $0.02016 in, $0.891 out per 1M tokens |
| Gemma 4 31BGoogle | 0.26p | 5.1p | $0.09 in, $0.34 out per 1M tokens |
| Claude Haiku 5.5Anthropic | 0.29p | 5.9p | $0.10 in, $0.50 out per 1M tokens |
| GPT-6 LunaOpenAI | 0.29p | 5.9p | $0.10 in, $0.50 out per 1M tokens |
| Qwen3.8 FlashQwen | 0.42p | 8.4p | $0.15 in, $0.47 out per 1M tokens |
| Mistral Small 4Mistral | 0.43p | 8.6p | $0.15 in, $0.60 out per 1M tokens |
| Gemini 2.5 FlashGoogle | 0.96p | 19p | $0.30 in, $2.50 out per 1M tokens |
| Gemini 3.5 Flash LiteGoogle | 0.96p | 19p | $0.30 in, $2.50 out per 1M tokens |
| GPT-4.1 MiniOpenAI | 1.1p | 23p | $0.40 in, $1.60 out per 1M tokens |
| Llama 3.3 70B InstructMeta | 1.6p | 31p | $0.59 in, $0.79 out per 1M tokens |
| Mistral Large 4Mistral | 1.9p | 38p | $0.68 in, $2.09 out per 1M tokens |
| Gemini 3.8 FlashGoogle | 2.2p | 44p | $0.75 in, $3.75 out per 1M tokens |
| DeepSeek V4 Pro 0423DeepSeek | 2.6p | 52p | $0.9553 in, $1.911 out per 1M tokens |
| Claude Haiku 4.5Anthropic | 2.9p | 59p | $1.00 in, $5.00 out per 1M tokens |
| Muse Spark 1.3Meta | 3.5p | 70p | $1.25 in, $4.25 out per 1M tokens |
| Grok 4.7SpaceXAI | 5.6p | £1.12 | $2.00 in, $6.00 out per 1M tokens |
| Qwen3.8 Max (0902)Qwen | 5.6p | £1.12 | $2.00 in, $6.00 out per 1M tokens |
| Claude Sonnet 5.5Anthropic | 5.9p | £1.18 | $2.00 in, $10.00 out per 1M tokens |
| Gemini 4 ArgonGoogle | 5.9p | £1.18 | $2.00 in, $10.00 out per 1M tokens |
| GPT-6.1 SolOpenAI | 5.9p | £1.18 | $2.00 in, $10.00 out per 1M tokens |
| Claude Opus 5.5Anthropic | 12p | £2.35 | $4.00 in, $20.00 out per 1M tokens |
| Claude Fable 5.1Anthropic | 29p | £5.88 | $10.00 in, $50.00 out per 1M tokens |
| GPT-6 AstraOpenAI | 29p | £5.88 | $10.00 in, $50.00 out per 1M tokens |
How the numbers are worked out
- Each workload is written out on its page: tokens in and out, the share read from a prompt cache, audio minutes or images. Cost = workload × the model's listed rate, so you can check any figure with a calculator.
- Rates are OpenRouter's API prices in our snapshot of , the same ones on our model pricing pages. Buying from the developer directly can cost a little more or less. When rates move, the price change log records it.
- US dollars become pounds at the European Central Bank reference rate of : €1 = $1.1195 = £0.84385, so $1 = £0.7538. VAT, card fees and top-up fees are not included.
- About 0.75 English words make one token. Each model's tokenizer counts the same text a little differently, so treat a figure as a close estimate, not a quote.
- Models that reason before answering can add thinking tokens, billed as output. These figures count none, so a model with thinking switched on can cost more.
- This compares price only. It says nothing about which model does the job well: a cheap model that gets a tenth of the answers wrong can cost more in staff time than it saves.
Other tasks
- Draft replies to 1,000 customer emails
- Run a support chatbot: 10,000 chats a month
- Classify 10,000 support tickets
- Extract fields from 1,000 scanned invoices
- Transcribe 100 hours of calls
- Write 500 product descriptions
- Translate a 20,000-word website
- Generate 100 marketing images
- Answer questions over 10,000 internal documents
Want this running on your own data, with the cost measured? See the fixed-price AI pilot