Prompt
Summarize a PDF: the prompt, and its price by length
A prompt that summarizes a long PDF you attach for a busy reader. Copy it or open it in llmwise, and see which models can run it and what one run counts as on each.
Models and prices checked . Updated .
Short answer
GLM 5.3 Flash is the least expensive model that can run it: one run counts as 1 everyday message. It gets the PDF's text only; the least expensive that reads the whole file is Claude Haiku 5.5, at 2 everyday messages. 21 of the 21 models can run it; each one's price is below.
The prompt
Summarize the attached document for [who]. Start with the one-sentence takeaway, then up to five bullet points with the numbers that matter, then anything I need to decide or do.
Replace the parts in [brackets] with your own. It's in the prompt library with the others.
What it needs from a model
A PDF you attach, up to 100 pages. Most models read the whole file, pages and all; DeepSeek V4.1 Flash, DeepSeek V4 Pro, Kimi K3, GLM 5.3, GLM 5.3 Flash, and Mistral Large 4 get its text only, which misses charts and scans.
A 60-page PDF is about 90,000 tokens to a model that reads the whole file, and 60,000 as text alone, by llmwise's estimate. Past 64,000 tokens a reply counts as 2.
Which models, and what one run counts as
Start with the least expensive model that can run it, and move up only when the answer isn't good enough: the next model sees the whole chat.
| Models | One run on a plan | Runs on Plus | Runs on Pro |
|---|---|---|---|
| GLM 5.3 Flash and DeepSeek V4.1 FlashGets the PDF's text only · Everyday model: from the daily count | 1 everyday message | 30 a day | 60 a day |
| Claude Haiku 5.5 and GPT-6 LunaReads the whole PDF, pages and all · Everyday model: from the daily count | 2 everyday messages | 15 a day | 30 a day |
| Mistral Large 4, DeepSeek V4 Pro, and GLM 5.3Gets the PDF's text only | 1 message of the model | 125 a month | 250 a month |
| Gemini 3.8 Flash, Claude Haiku 4.5, GPT-6.1 Terra, and Grok 4.7Reads the whole PDF, pages and all | 2 messages of the model | 62 a month | 125 a month |
| Kimi K3Gets the PDF's text only | 1 message of the model | 62 a month | 125 a month |
| Claude Sonnet 5.5, Claude Sonnet 5, GPT-6.1 Sol, GPT-6 Sol, and Gemini 3.1 Pro (preview)Reads the whole PDF, pages and all | 2 messages of the model | 31 a month | 62 a month |
| Claude Opus 5.5 and Gemini 4 ArgonReads the whole PDF, pages and all | 2 messages of the model | 15 a month | 31 a month |
| Claude Fable 5.1 and GPT-6 AstraReads the whole PDF, pages and all | 2 messages of the model | Not on Plus | 15 a month |
Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Plus $3.75, Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.
Everyday models: for emails, short articles and quick TL;DRs.
Models with 125 to 250 messages a month on Pro: for reports, long articles and meeting notes.
Models with 31 to 62 messages a month on Pro: for dense or high-stakes material: contracts, research papers, anything you'll act on.
What to check in the reply
Before you use the reply, read it against the source you gave it; these are the places this prompt's answers go wrong.
Check the summary against the PDF's own headings: a good summary covers every section, not just the first chapters.
Look up any figure or quotation in the PDF before repeating it; summaries sometimes attach the right number to the wrong year.
If the PDF has tables or charts, ask what the summary did with them: text-only reading skips what a figure says.
How a PDF's length changes the price
A PDF counts toward the chat's length: a model that reads the whole file sees each page's image and text, one that gets the text sees less. Once the conversation sent to the model passes 64k tokens, each reply counts as 2; past 128k, as 4; past 200k the chat is full.
| Pages | Model reads the whole file | Model gets the text |
|---|---|---|
| 1 | 1 message | 1 message |
| 43 | 2 messages | 1 message |
| 65 | 2 messages | 2 messages |
| 86 | 4 messages | 2 messages |
| 100 | 4 messages | 2 messages |
Questions
Can I run this prompt for free?
No: there's no free plan or trial. It runs on every plan. Paid monthly from the day you start. Cancel in two clicks in Settings → Billing. On Pro ($20 a month) the least a run counts as is 1 everyday message, on GLM 5.3 Flash.
Which models can run it?
21 of the 21 models in llmwise can. Start on the least expensive and move up if the answer isn't good enough; the next model sees the whole chat.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, and Mistral, in one chat.
See what a message costs before you send it. Every plan is month to month: cancel in two clicks. Sign in with an email link, no password.