DeepSeek · Summarization
DeepSeek for summarization
llmwise has 2 of DeepSeek's models, from DeepSeek V4.1 Flash (up to 60 messages a day on Pro) to DeepSeek V4 Pro (up to 250 messages a month). We ran the same summarization prompts on every one and published every reply: which DeepSeek model to use, from the results, what each costs per message, and how to get more out of it.
Based on 10 of our test runs on , through OpenRouter with the app's own prompt and settings. Updated .
Short answer
In our test runs on October 8, 2026, all 2 models passed 5 of 5 summarization prompts, so these prompts don't pick one for hard problems. For value, DeepSeek V4 Pro (5 of 5), 250 a month on Pro; for everyday summarization, DeepSeek V4.1 Flash (5 of 5), from the daily count.
Our picks for summarization
Hard problems
Shared by 2 models
All 2 models passed 5 of 5, both hard ones: DeepSeek V4.1 Flash and DeepSeek V4 Pro. These prompts don't tell them apart, so they share the pick.
Best value
Passed 5 of 5 summarization prompts, with 250 a month on Pro.
Everyday
Passed 5 of 5 summarization prompts; an everyday model, so its messages come from the daily count (60 a day on Pro), not the monthly allowance.
These picks aren't our opinion: they're what the results below give, by these rules, among the DeepSeek models in llmwise. They change when the results do.
- Hard problems: the model that passed the most prompts and, of those, the most hard ones. Models level on both share the pick: the prompts don't tell them apart, so we don't break the tie by price or by name.
- Best value: among the models that draw on the monthly allowance, the one with the most messages on Pro that passed no more than one prompt fewer than the top model. Ties go to the one that passed more, then to the lower cost per reply.
- Everyday: among the cheapest models on the page (the everyday models, which come from the daily count, when the page has any), the one that passed the most. Ties go to the one that passed more of the hard prompts, then to the lower cost per reply.
Our summarization test runs, model by model
How each model did on our 5 summarization prompts, what each reply counted as on Pro, and what it cost to run.
| Model | Passed | Hard ones | Messages used on Pro | Cost per reply | Time per reply |
|---|---|---|---|---|---|
| DeepSeek V4 ProDeepSeek | 5 of 5 | 2 of 2 | 1 each, of 250 a month on Pro | $0.0009 | 2.6 s |
| DeepSeek V4.1 FlashDeepSeek | 5 of 5 | 2 of 2 | 1 each, of 60 a day on Pro | $0.0002 | 0.9 s |
One prompt, side by side
Each model's reply to “A quarterly memo for the CEO”, as it came, with whether it passed and what it cost.
The prompt: A quarterly memo for the CEO (hard)
Summarize this memo for the CEO in at most 4 sentences, keeping every number exact. Q3 at Fernway: revenue was $2.4M, up 18% on Q2, driven by the new team plan, which now makes up 41% of new sign-ups. Churn fell from 3.1% to 2.6% a month. Gross margin slipped from 71% to 68% because of higher hosting costs, which the platform team expects to bring back down by the end of Q4 after moving storage providers. We ended the quarter with 14 months of runway. Hiring is frozen until Q2 next year, except for two support roles already approved. The biggest risk is our largest customer, 9% of revenue, whose contract is up for renewal in November.
DeepSeek V4.1 Flash
Passed: Graded 4.7 of 5 on average (lowest 4).
Q3 revenue reached $2.4M, up 18% on Q2, driven by the new team plan, now 41% of new sign-ups. Monthly churn fell from 3.1% to 2.6%, but gross margin slipped from 71% to 68% on higher hosting costs, which the platform team expects to restore by the end of Q4 after switching storage providers. We ended the quarter with 14 months of runway, hiring is frozen until Q2 next year except for two already-approved support roles. The biggest risk is our largest customer, 9% of revenue, whose contract renews in November.
545 tokens in, 145 out (10 of them reasoning) · 0.4 s · $0.0003 · 1 message on Pro · answered by deepseek/deepseek-v4.1-flash via Together ·
DeepSeek V4 Pro
Passed: Graded 4.0 of 5 on average (lowest 3).
Q3 revenue was $2.4M, up 18% on Q2, driven by the new team plan, which now accounts for 41% of new sign-ups. Monthly churn fell from 3.1% to 2.6%, while gross margin slipped from 71% to 68% due to higher hosting costs the platform team expects to reverse by the end of Q4 after moving storage providers. We ended the quarter with 14 months of runway; hiring is frozen until Q2 next year, except for two support roles already approved. The biggest risk is our largest customer, 9% of revenue, whose contract is up for renewal in November.
517 tokens in, 312 out (173 of them reasoning) · 2.3 s · $0.0014 · 1 message on Pro · answered by deepseek/deepseek-v4-pro-0813 via Wafer ·
The summarization prompts, and how they're scored
Rubric (graded). The grader model scores the reply from 1 to 5 on each published criterion. It passes with an average of 4 or more and no criterion under 3, and only if it also meets the prompt's automatic rules (length, words it must or mustn't use).
The grader is Claude Opus 5.5 at low reasoning effort; its own replies are graded by GPT-6 Astra, so no model grades itself. Its prompt and every rubric are on the methods page.
Each prompt was sent the way llmwise sends a message in a side-by-side comparison, which offers no tools: the app's own system prompt, the model's own settings, and Pro's reply size limit (8,000 tokens). Read all five summarization prompts and how every reply was scored.
Prompts like these to try yourself
DeepSeek in llmwise
| Model | On Pro | On Free | Context window | Images | PDFs | Reasoning | API price per 1M, in / out |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 ProDeepSeek | 250/mo on Pro | Yes | 1.05M tokens | No | Text only | Yes | $0.40 / $4.00 |
| DeepSeek V4.1 FlashDeepSeek | 60/day on Pro | Yes | 1.05M tokens | Yes | Text only | Yes | $0.30 / $1.20 |
Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: 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.
DeepSeek V4 Pro and DeepSeek V4.1 Flash get a PDF's text rather than the whole file.
What matters for summarization
How much it can read
A model can only summarize what fits in its context window, listed for each model below.
Staying faithful
A summary is only useful if it's faithful. Ask for key numbers and quotes so you can check them.
The right length
Say who the summary is for and how long it should be; a one-line TL;DR and a one-page brief are different jobs.
DeepSeek for summarization in llmwise
Attach your documents
Attach PDFs (up to 100 pages), images, Word, Excel, and PowerPoint files, and text or code files (plain text, Markdown, and CSV, JSON and more), up to 10 files a message.
Summarize a link
Paste a link and the model reads the page. It counts as one web search.
Keep the summary
Ask for the summary as a document to edit it, keep its versions and download it as PDF, Word or Markdown.
Long chats, stated up front
Past 64k tokens each reply counts as 2, past 128k as 4, and a chat stops at 200k; the composer says so before you send. One document per chat keeps it short.
DeepSeek models are served only through OpenRouter, by endpoints that don't store or train on prompts. See the Privacy Policy.
Tips
Say who the summary is for and how long it should be.
Ask for the key numbers and quotes, with page references.
Ask what the summary leaves out.
Use one chat per long document.
Questions
Is DeepSeek good for summarization?
In our test runs on October 8, 2026, DeepSeek V4 Pro passed 5 of 5, DeepSeek V4.1 Flash passed 5 of 5 of our summarization prompts, against a best result of 5 of 5 among all 19 models. Every reply is published on this page and the methods page, so you can judge them yourself.
Which DeepSeek model should I use for summarization?
Start with DeepSeek V4.1 Flash for emails, short articles and quick TL;DRs, and move up to DeepSeek V4 Pro for reports, long articles and meeting notes.
Can I use DeepSeek for summarization for free?
Yes: DeepSeek V4 Pro and DeepSeek V4.1 Flash are on the Free plan (a one-time trial of 5 messages).
How long a document can I summarize?
PDFs up to 100 pages and files up to 20 MB, within the model's context window (listed below).
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, and Mistral, in one chat.
See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.