Meeting notes and summaries: what it costs and which AI to use
Turn call and meeting transcripts into minutes, action items and follow-up emails. Teams automating note-taking across sales calls, stand-ups and customer interviews.
The short answer
At 400 meetings a month, we estimate $0.575 on DeepSeek V4 Flash 0423 (the cheapest model that cleared our quality bar), $3.34 on Mistral Large 3 2512, and $38.80 on GPT-5.5. The flagship costs 12x the middle pick. Judged on summarising and extraction tasks: action items and owners have to be right.
Simulate your meeting notes and summaries
Pick a job, set how much of it you do, and see what every model would cost. Defaults are typical, not yours. Change them.
Prompt, history, documents
What the model writes
Advanced: caching, reasoning, retries, discounts
Share that can use cached-input prices where a model offers them
1 = none. 2 = hidden thinking doubles billed output
Extra calls on top of the base count
Batch jobs or committed spend. Check your provider; we assume none by default
Lowest benchmark score a model can have and still be picked. Higher is stricter.
Limit to certain providers
Untick any provider you cannot use, for data-residency, contract or policy reasons. Picks are recalculated.
400 meetings a month, three ways to pay
Every model here cleared a score of 9.0 out of 10 on our summarise, extract json benchmark tasks, ran without errors and fits a 32K-token window. 21 of 386 priced models qualify.
Cheapest model that clears the bar.
DeepSeek V4 Flash 0423
- Per meeting
- $0.0014
- Benchmark
- 9.50 / 10 · 6 prompts
- Context
- 1.05M tokens
Priced near the middle of the models that clear the bar; best score there.
Mistral Large 3 2512
- Per meeting
- $0.0084
- Benchmark
- 9.50 / 10 · 6 prompts
- Context
- 262K tokens
What many people reach for first.
GPT-5.5
- Per meeting
- $0.097
- Benchmark
- 9.50 / 10 · 6 prompts
- Context
- 1.05M tokens
Choosing GPT-5.5 over Mistral Large 3 2512 costs $35.46 more a month, $426 a year (12x the price).
Both scored 9.50 out of 10 on this kind of work. The extra money buys safety margin our benchmark cannot measure: it is 24 short prompts, and most passing models score near the top. If a wrong answer is costly for you, that margin can be worth it. Test on your own data before you decide.
If it grows
Pay-per-use cost scales in a straight line. Monthly cost at 1x, 3x, 10x and 100x today's volume.
| Model | 1x · 400 | 3x · 1,200 | 10x · 4,000 | 100x · 40K |
|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | $0.575 | $1.73 | $5.75 | $57.51 |
| Mistral Large 3 2512 | $3.34 | $10.02 | $33.40 | $334 |
| GPT-5.5 | $38.80 | $116 | $388 | $3,880 |
What a budget buys
- DeepSeek V4 Flash 042370Kmeetings a month, about 2,318 a day
- Mistral Large 3 251212Kmeetings a month, about 399 a day
- GPT-5.51,030meetings a month, about 34 a day
Every model, priced for your workload
41 models, 15 hidden because their window is smaller than 32K tokens.
| Model | A month | Per meeting | Benchmark | Context |
|---|---|---|---|---|
| DeepSeek V4.1 Flash DeepSeekbelow the bar | $0.432 | $0.0011 | 8.33 (6) | 1.05M |
| DeepSeek V4 Flash 0423 DeepSeekBudget pick | $0.575 | $0.0014 | 9.50 (6) | 1.05M |
| Llama 4 Scout Meta | $0.668 | $0.0017 | 9.50 (6) | 1.31M |
| Ministral 3 8B 2512 Mistral AI | $0.894 | $0.0022 | 9.33 (6) | 262K |
| GLM 5.3 Z Aibelow the bar | $0.895 | $0.0022 | 8.67 (6) | 1.05M |
| Qwen3.8 Flash Alibababelow the bar | $1.01 | $0.0025 | 8.17 (6) | 1M |
| GLM 5.3 Flash Z Ai | $1.02 | $0.0025 | 9.33 (6) | 1.05M |
| Mistral Small 4 Mistral AI | $1.06 | $0.0026 | 9.50 (6) | 262K |
| Qwen3.8 27B Alibababelow the bar | $1.51 | $0.0038 | 5.83 (6) | 1.02M |
| GPT-5.4 Nano OpenAI | $1.57 | $0.0039 | 9.50 (6) | 400K |
| MiniMax M2.5 Minimax | $1.85 | $0.0046 | 9.33 (6) | 205K |
| Muse Glimmer 30B Metabelow the bar | $2.11 | $0.0053 | 8.50 (6) | 131K |
Benchmark = mean judge score out of 10 on the summarise, extract json prompts of the Model Playground, with the number of prompts in brackets. Models marked n/a have no benchmark run, so we do not guess their quality. How the benchmark works.
What we assumed
- Four hundred meetings a month.
- A 45-minute meeting transcribes to about 9,000 words, roughly 14,000 tokens.
- Minutes and action items run about 650 words, roughly 900 tokens.
- Speech-to-text cost is not included.
These are typical numbers, not measurements of your business. Edit them in the simulator above.
What drives the cost
A one-hour meeting is a long transcript, so input is large and the summary is short.
Watch out for
- Transcription often costs more than the summary. Check that line on your bill too.
- Very long meetings can pass the context window of small models.
Questions people ask
How much will meeting notes and summaries cost per month?
At 400 meetings a month, we estimate $0.575 a month on DeepSeek V4 Flash 0423, the cheapest model that clears our quality bar for this job. Mistral Large 3 2512 costs $3.34 and GPT-5.5 costs $38.80. These are estimates from the assumptions listed on this page, not a quote. Change the numbers to match your own volume.
What is the cheapest AI model for meeting notes and summaries?
On current OpenRouter prices, DeepSeek V4 Flash 0423 from DeepSeek is the cheapest model that cleared our bar of 9.0 out of 10, scoring 9.5/10 on 6 benchmark prompts for this kind of work. The benchmark is small, so treat it as a shortlist and test on your own data before switching.
Is it worth paying for a flagship model for meeting notes and summaries?
On our benchmark, GPT-5.5 scored 9.5/10 on this kind of work, and a model priced near the middle of the models that cleared the bar, Mistral Large 3 2512, scored 9.5/10, while the flagship costs 12x as much. A flagship buys safety margin the benchmark cannot measure. If a wrong answer is expensive for you, that can be worth paying for. If not, you are probably overpaying.
What happens to the cost if meeting notes and summaries grows ten times?
Pay-per-use pricing scales in a straight line, so ten times the meetings is ten times the bill. Use the growth table on this page to see 3x, 10x and 100x for the same three models.
What makes meeting notes and summaries expensive?
A one-hour meeting is a long transcript, so input is large and the summary is short.
Price a different job
- Customer support chatbotFrom $1.74 a month at 3,000 conversations
- Coding assistant for a teamFrom $4.12 a month at 4,400 requests
- Document summarisationFrom $1.86 a month at 2,000 documents
- Blog and content writingFrom $0.083 a month at 120 articles
- Knowledge base Q&A (RAG)From $5.62 a month at 15K questions
- Invoice and form data extractionFrom $4.65 a month at 20K documents
- Ticket and content classificationFrom $11.30 a month at 500K items
- AI agent workflowsFrom $7.44 a month at 1,500 runs
- Sales email personalisationFrom $0.595 a month at 5,000 emails
- Code review for pull requestsFrom $0.840 a month at 600 pull requests
- Personal AI assistant for a founderFrom $0.478 a month at 1,500 messages
- Text-to-SQL data analystFrom $2.54 a month at 6,000 queries