OverpayingForAIPricing desk

Sales email personalisation: what it costs and which AI to use

Write a tailored opening line or a whole outreach email for each lead from a short profile. Sales and growth teams running outbound at volume.

The short answer

At 5,000 emails a month, we estimate $0.595 on DeepSeek V4 Flash 0423 (the cheapest model that cleared our quality bar), $7.21 on Kimi K2.7 Code, and $59.60 on GPT-5.5. The flagship costs 8.3x the middle pick. Judged on rewriting and extraction tasks: tone, no invented facts about the lead.

Simulate your sales email personalisation

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.

5,000 emails a month, three ways to pay

Every model here cleared a score of 9.0 out of 10 on our rewrite, extract json benchmark tasks, ran without errors and fits a 8K-token window. 25 of 386 priced models qualify.

Budget pick

Cheapest model that clears the bar.

DeepSeek V4 Flash 0423

DeepSeek
$0.595a month
Per email
$0.0001
Benchmark
9.50 / 10 · 6 prompts
Context
1.05M tokens
Middle pick

Priced near the middle of the models that clear the bar; best score there.

Kimi K2.7 Code

Moonshotai
$7.21a month
Per email
$0.0014
Benchmark
9.50 / 10 · 6 prompts
Context
262K tokens
Flagship default

What many people reach for first.

GPT-5.5

OpenAI
$59.60a month
Per email
$0.012
Benchmark
9.50 / 10 · 6 prompts
Context
1.05M tokens

Choosing GPT-5.5 over Kimi K2.7 Code costs $52.39 more a month, $629 a year (8.3x 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.

Model1x · 5,0003x · 15K10x · 50K100x · 500K
DeepSeek V4 Flash 0423$0.595$1.79$5.95$59.51
Kimi K2.7 Code$7.21$21.63$72.10$721
GPT-5.5$59.60$179$596$5,960

What a budget buys

  • DeepSeek V4 Flash 0423
    840K
    emails a month, about 28K a day
  • Kimi K2.7 Code
    69K
    emails a month, about 2,311 a day
  • GPT-5.5
    8,389
    emails a month, about 279 a day

Every model, priced for your workload

41 models, 3 hidden because their window is smaller than 8K tokens.

ModelA monthPer emailBenchmarkContext
DeepSeek V4 Flash 0423
DeepSeekBudget pick
$0.595$0.00019.50 (6)1.05M
Ministral 3 8B 2512
Mistral AI
$0.738$0.00019.50 (6)262K
Llama 4 Scout
Meta
$0.871$0.00029.33 (6)1.31M
DeepSeek V4.1 Flash
DeepSeekbelow the bar
$0.888$0.00028.17 (6)1.05M
Qwen3.8 Flash
Alibababelow the bar
$1.19$0.00028.50 (6)1M
GLM 5.3 Flash
Z Ai
$1.26$0.00039.50 (6)1.05M
Mistral Small 4
Mistral AIa benchmark run failed
$1.37$0.00039.60 (5)262K
MiniMax M2.5
Minimax
$2.29$0.00059.50 (6)205K
GLM 5.3
Z Aibelow the bar
$2.34$0.00058.50 (6)1.05M
GPT-5.4 Nano
OpenAI
$2.45$0.00059.50 (6)400K
Muse Glimmer 30B
Meta
$2.76$0.00069.50 (6)131K
MiniMax M2.7
Minimaxbelow the bar
$2.80$0.00068.00 (6)205K

Benchmark = mean judge score out of 10 on the rewrite, 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

  • Five thousand emails a month.
  • Each call sends a lead profile and template, about 1,100 tokens.
  • Each email is about 180 words, roughly 280 tokens.
  • 40% of input (template and instructions) repeats.

These are typical numbers, not measurements of your business. Edit them in the simulator above.

What drives the cost

Volume again, with short outputs. The model sees a profile and a template and writes a few sentences.

Watch out for

  • The model call is the cheap part. Data enrichment and sending tools usually cost far more.
  • Invented details about a lead hurt more than a generic opening. Test for it before you scale.

Questions people ask

How much will sales email personalisation cost per month?

At 5,000 emails a month, we estimate $0.595 a month on DeepSeek V4 Flash 0423, the cheapest model that clears our quality bar for this job. Kimi K2.7 Code costs $7.21 and GPT-5.5 costs $59.60. 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 sales email personalisation?

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 sales email personalisation?

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, Kimi K2.7 Code, scored 9.5/10, while the flagship costs 8.3x 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 sales email personalisation grows ten times?

Pay-per-use pricing scales in a straight line, so ten times the emails 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 sales email personalisation expensive?

Volume again, with short outputs. The model sees a profile and a template and writes a few sentences.

Price a different job

Related

If our calculators helped you cut down on hidden AI wallet leaks, thanks for using them. A tiny fraction of your savings is what keeps our pricing indexes updated daily.

Not sure which AI is cheapest for your use case? Find out in 30 seconds — no signup required.

AI cost intelligence

Stop overpaying for AI tools

Join the OverpayingForAI list for pricing updates, cheaper alternatives, and practical buying guidance.

Now tracking 50+ AI tools, models, platforms, subscriptions, coding tools, and automation products.

We use your email only for OverpayingForAI updates. Unsubscribe anytime.