AI task costs · in pounds
What it costs to classify 10,000 support tickets a month with AI
gpt-oss-120b is the cheapest of the 24 models priced, at 21p for 10,000 tickets a month (0.0021p per ticket). The dearest, GPT-6 Astra, costs £56.53; the middle of the range is Mistral Large 4 at £3.65.
How much does it cost to sort support tickets into categories and urgency with an AI model? 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
- 400 tokens of instructions and 20 category names, plus 250 tokens of ticket text: 650 input tokens.
- The answer is a category and an urgency level as JSON: 20 output tokens.
- No prompt cache: the shared instructions are shorter than the 1,024 tokens many prompt caches need.
| Model | Per ticket | 10,000 tickets a month | Rate used (USD) |
|---|---|---|---|
| gpt-oss-120bOpenAI | 0.0021p | 21p | $0.037 in, $0.17 out per 1M tokens |
| DeepSeek V4.1 FlashDeepSeek | 0.0023p | 23p | $0.02016 in, $0.891 out per 1M tokens |
| Gemma 4 31BGoogle | 0.0049p | 49p | $0.09 in, $0.34 out per 1M tokens |
| Claude Haiku 5.5Anthropic | 0.0057p | 57p | $0.10 in, $0.50 out per 1M tokens |
| GPT-6 LunaOpenAI | 0.0057p | 57p | $0.10 in, $0.50 out per 1M tokens |
| Qwen3.8 FlashQwen | 0.0081p | 81p | $0.15 in, $0.47 out per 1M tokens |
| Mistral Small 4Mistral | 0.0083p | 83p | $0.15 in, $0.60 out per 1M tokens |
| Gemini 2.5 FlashGoogle | 0.018p | £1.85 | $0.30 in, $2.50 out per 1M tokens |
| Gemini 3.5 Flash LiteGoogle | 0.018p | £1.85 | $0.30 in, $2.50 out per 1M tokens |
| GPT-4.1 MiniOpenAI | 0.022p | £2.20 | $0.40 in, $1.60 out per 1M tokens |
| Llama 3.3 70B InstructMeta | 0.03p | £3.01 | $0.59 in, $0.79 out per 1M tokens |
| Mistral Large 4Mistral | 0.036p | £3.65 | $0.68 in, $2.09 out per 1M tokens |
| Gemini 3.8 FlashGoogle | 0.042p | £4.24 | $0.75 in, $3.75 out per 1M tokens |
| DeepSeek V4 Pro 0423DeepSeek | 0.05p | £4.97 | $0.9553 in, $1.911 out per 1M tokens |
| Claude Haiku 4.5Anthropic | 0.057p | £5.65 | $1.00 in, $5.00 out per 1M tokens |
| Muse Spark 1.3Meta | 0.068p | £6.77 | $1.25 in, $4.25 out per 1M tokens |
| Grok 4.7SpaceXAI | 0.11p | £10.70 | $2.00 in, $6.00 out per 1M tokens |
| Qwen3.8 Max (0902)Qwen | 0.11p | £10.70 | $2.00 in, $6.00 out per 1M tokens |
| Claude Sonnet 5.5Anthropic | 0.11p | £11.31 | $2.00 in, $10.00 out per 1M tokens |
| Gemini 4 ArgonGoogle | 0.11p | £11.31 | $2.00 in, $10.00 out per 1M tokens |
| GPT-6.1 SolOpenAI | 0.11p | £11.31 | $2.00 in, $10.00 out per 1M tokens |
| Claude Opus 5.5Anthropic | 0.23p | £22.61 | $4.00 in, $20.00 out per 1M tokens |
| Claude Fable 5.1Anthropic | 0.57p | £56.53 | $10.00 in, $50.00 out per 1M tokens |
| GPT-6 AstraOpenAI | 0.57p | £56.53 | $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
- Summarise a 50-page PDF
- Draft replies to 1,000 customer emails
- Run a support chatbot: 10,000 chats a month
- 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