Customer support chatbot: what it costs and which AI to use
A bot that answers customer questions from your help centre and hands hard cases to a person. Small and mid-size businesses putting a chatbot on their site or help desk.
The short answer
At 3,000 conversations a month, we estimate $1.74 on DeepSeek V4 Flash 0423 (the cheapest model that cleared our quality bar), $7.07 on MiniMax M3, and $131 on GPT-5.5. The flagship costs 19x the middle pick. Judged on summarising, sorting and rewriting tasks: a wrong or rambling answer costs you a ticket.
Simulate your customer support chatbot
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.
3,000 conversations a month, three ways to pay
Every model here cleared a score of 9.0 out of 10 on our summarise, classify, rewrite benchmark tasks, ran without errors and fits a 32K-token window. 24 of 386 priced models qualify.
Cheapest model that clears the bar.
DeepSeek V4 Flash 0423
- Per conversation
- $0.0006
- Benchmark
- 9.56 / 10 · 9 prompts
- Context
- 1.05M tokens
Priced near the middle of the models that clear the bar; best score there.
MiniMax M3
- Per conversation
- $0.0024
- Benchmark
- 9.56 / 10 · 9 prompts
- Context
- 1.05M tokens
What many people reach for first.
GPT-5.5
- Per conversation
- $0.044
- Benchmark
- 9.56 / 10 · 9 prompts
- Context
- 1.05M tokens
Choosing GPT-5.5 over MiniMax M3 costs $124 more a month, $1,491 a year (19x the price).
Both scored 9.56 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 · 3,000 | 3x · 9,000 | 10x · 30K | 100x · 300K |
|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | $1.74 | $5.23 | $17.43 | $174 |
| MiniMax M3 | $7.07 | $21.21 | $70.69 | $707 |
| GPT-5.5 | $131 | $394 | $1,314 | $13,136 |
What a budget buys
- DeepSeek V4 Flash 0423172Kconversations a month, about 5,737 a day
- MiniMax M342Kconversations a month, about 1,414 a day
- GPT-5.52,283conversations a month, about 76 a day
Every model, priced for your workload
41 models, 15 hidden because their window is smaller than 32K tokens.
| Model | A month | Per conversation | Benchmark | Context |
|---|---|---|---|---|
| DeepSeek V4 Flash 0423 DeepSeekBudget pick | $1.74 | $0.0006 | 9.56 (9) | 1.05M |
| DeepSeek V4.1 Flash DeepSeekbelow the bar | $1.92 | $0.0006 | 7.89 (9) | 1.05M |
| Ministral 3 8B 2512 Mistral AI | $2.29 | $0.0008 | 9.44 (9) | 262K |
| Llama 4 Scout Meta | $2.73 | $0.0009 | 9.44 (9) | 1.31M |
| Qwen3.8 Flash Alibaba | $3.01 | $0.0010 | 9.33 (9) | 1M |
| Mistral Small 4 Mistral AIa benchmark run failed | $3.28 | $0.0011 | 9.63 (8) | 262K |
| GLM 5.3 Flash Z Ai | $3.31 | $0.0011 | 9.44 (9) | 1.05M |
| GLM 5.3 Z Ai | $5.05 | $0.0017 | 9.67 (9) | 1.05M |
| GPT-5.4 Nano OpenAI | $5.36 | $0.0018 | 9.56 (9) | 400K |
| MiniMax M2.5 Minimax | $5.67 | $0.0019 | 9.44 (9) | 205K |
| Qwen3.8 27B Alibababelow the bar | $6.47 | $0.0022 | 7.78 (9) | 1.02M |
| Muse Glimmer 30B Metabelow the bar | $6.73 | $0.0022 | 8.89 (9) | 131K |
Benchmark = mean judge score out of 10 on the summarise, classify, rewrite 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
- A conversation runs about six turns.
- Each turn re-sends the chat so far plus roughly 1,500 tokens of instructions and help-centre text, which averages about 9,000 input tokens a conversation.
- The bot writes about 120 tokens a turn, around 700 a conversation.
- 60% of input repeats between turns (instructions and knowledge base) and qualifies for cached-input pricing where the model offers it.
These are typical numbers, not measurements of your business. Edit them in the simulator above.
What drives the cost
Every reply re-sends the whole conversation so far plus your instructions and knowledge-base snippets, so input tokens grow with each turn.
Watch out for
- Long conversations cost far more than short ones because history is re-sent. Cap turns or summarise history.
- Prompt caching only helps if the repeated part comes first in the prompt.
- Do not pay flagship prices for questions a small model answers just as well; keep the big model for escalations.
Questions people ask
How much will customer support chatbot cost per month?
At 3,000 conversations a month, we estimate $1.74 a month on DeepSeek V4 Flash 0423, the cheapest model that clears our quality bar for this job. MiniMax M3 costs $7.07 and GPT-5.5 costs $131. 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 customer support chatbot?
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 9.6/10 on 9 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 customer support chatbot?
On our benchmark, GPT-5.5 scored 9.6/10 on this kind of work, and a model priced near the middle of the models that cleared the bar, MiniMax M3, scored 9.6/10, while the flagship costs 19x 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 customer support chatbot grows ten times?
Pay-per-use pricing scales in a straight line, so ten times the conversations 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 customer support chatbot expensive?
Every reply re-sends the whole conversation so far plus your instructions and knowledge-base snippets, so input tokens grow with each turn.
Price a different job
- 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
- Meeting notes and summariesFrom $0.575 a month at 400 meetings
- 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