💰Plans and limits
In Selarti you can choose suitable plans and services depending on your business needs. The cost depends on the selected plan, the volume of messages, and the volume of data in the dialogs themselves (depends on the chosen OpenAI language model). Understanding limits is important so that your accounts are not blocked.
Two options are available to connect Selarti:
Turnkey setup – comprehensive setup by our specialists.
Self-connection – self-configuration of the service with the selection of a standard tariff plan.
The «Turnkey setup» service
Use the service for comprehensive configuration tailored to your business tasks.
To connect the service — contact the sales department.
After implementation is completed, further use of the service is carried out on standard tariff plans.
Selarti tariff plans
A tariff plan includes certain functionality and allows you to choose the required volume of messages.
Tariff plans differ by limit of active tasks, incoming and outgoing communication capabilities, availability of reminders, number of connected communication channels, number of administrators, and many other parameters.
Tariffs are aimed at different scales and tasks of companies — from testing the service to use in large teams:
Lite — includes the service functionality for basic tasks and incoming communication.
Plus — provides additional features and settings for more complex tasks.
Pro — includes extended functionality with increased limits, the ability to use AI API features, and additional management parameters.
A tariff plan can be connected for 1, 3 or 12 months.
There is also a tariff Trial for the duration of the trial period. More details in the article.
In the end, the cost of using Selarti depends on several components:
fee for the selected tariff plan;
fee for the connected volume of messages;
fee for the volume of processed data (tokens).
Table 1. Selarti tariff plans
Monthly price
0$
30$
50$
100$
Agent creation
✅
✅
✅
✅
Agent limit
2
5
10
∞
Active task limit
2
3
5
∞
Incoming communication
✅
✅
✅
✅
Outbound communication
✅
❌
✅
✅
Reminders
✅
❌
✅
✅
Reminder limit per agent
1
0
5
∞
Conversation tags
✅
❌
✅
✅
Webhooks
✅
❌
✅
✅
AI API functions
✅
❌
✅
✅
File search
✅
✅
✅
✅
Web search
✅
❌
✅
✅
Voice transcription
✅
❌
✅
✅
Blacklist and whitelist
✅
❌
❌
✅
Admins and Operators
Chat reading
✅
✅
✅
✅
Interface responses
✅
❌
✅
✅
Transfer the conversation to an operator
✅
❌
✅
✅
Admin limit
2
3
5
∞
Telegram notifications
✅
❌
✅
✅
Daily reports
✅
❌
✅
✅
Channels and touchpoints
Connected channel limit
2
3
5
∞
Telegram bot
✅
✅
✅
✅
Telegram personal
✅
❌
✅
✅
Telegram for business
✅
✅
✅
✅
Vkontakte bot
✅
✅
✅
✅
VKontakte personal
✅
❌
✅
✅
✅
❌
✅
✅
WhatsApp business api
✅
❌
❌
✅
MAX
✅
❌
✅
✅
Avito
✅
❌
✅
✅
✅
❌
✅
✅
amoCRM
✅
❌
✅
✅
Kommo
✅
❌
✅
✅
Iframe
✅
✅
✅
✅
Widget
✅
✅
✅
✅
Page messenger
✅
✅
✅
✅
Connection of monthly message volume
Tariffs include a monthly number of messages - from 1 000 to 20 000.
Overspending of messages in excess of the package is paid at $0,03 per message. Payment is debited from the company's balance during the AI operation. At any time, you can change the available message volume by adding the required number.
Trial
250
$0
$0
$0
$0,03
Lite 1000
1000
$30
$27
$21
$0,03
Lite 2000
2000
$60
$54
$42
$0,03
Lite 5000
5000
$130
$117
$91
$0,03
Lite 10000
10000
$210
$189
$147
$0,03
Plus 2000
2000
$50
$45
$35
$0,03
Plus 5000
5000
$120
$108
$84
$0,03
Plus 10000
10000
$210
$199
$147
$0,03
Pro 5000
5000
$100
$90
$70
$0,03
Pro 10000
10000
$200
$180
$140
$0,03
Pro 20000
20000
$360
$324
$252
$0,03
Current prices and calculator are available in your personal account (.ru /.com).
Description of token calculation is below.
Amount of data in dialogues
When conversing with AI the cost or usage limit of the system is calculated based on the number of processed text units or characters — tokens.
Token — the amount of text that can be processed. On average one word takes about 1-2 tokens for text in Russian, so 1 token is approximately 3-4 characters.
Charges are applied only when the user responds.
Incoming and outgoing tokens
Incoming tokens — these are all the data sent to the model. They include the user’s message, bot instructions, and chat history. The instructions include the main prompt, references to the knowledge base and files, as well as requests from «Professional settings».
Incoming cache tokens — repeated and matching tokens of incoming data that the AI gradually «memories» (caches) for reuse in subsequent responses. These are most often prompts and information from files.
Outgoing tokens — response (including companion function calls and other requests) that the model generates and sends to the user.
How a request is formed
One request consists of:
user messages - added to incoming tokens or incoming cache tokens if matched;
bot instructions (promt, knowledge base, «Professional settings») - included in incoming tokens or incoming cache tokens;
chat history (context) - with each request, information is re-sent to the model and taken into account in incoming tokens or incoming cache tokens;
model response - consumes outgoing tokens.
The total cost of the request is equal to the sum of incoming, incoming cache and outgoing tokens.
Features of working with tokens
Each new request is processed along with the correspondence history, so the consumption increases with long dialogs.
If the AI request contains repeating information, it can be counted as incoming cache tokens and considered cheaper than regular incoming tokens.
Not all models have cache tokens.
If the token limit is exceeded, the early part of the history is automatically deleted.
Even in test mode, responses are generated by the model, so there is also a write-off from the balance sheet.
Calculation example
User message: «Yes, yes, I'm very interested. Write down the price.» — 13 tokens. Bot instructions: «Reply politely, in simple language. Request contact» and functions — 101 tokens. Chat history: used so the bot understands the context — 395 tokens. Model response: information about prices and the catalog — 191 tokens.
Incoming = 13 + 101 + 395 = 509 tokens (at the rate of the chosen model). Outgoing = 191 tokens (at the rate of the chosen model).
Total cost 700 tokens (incoming tokens + incoming cache tokens + outgoing tokens).
Incoming tokens, incoming cache tokens, and outgoing tokens are charged separately. Usually incoming tokens are cheaper than outgoing ones, and incoming cache tokens are cheaper than regular incoming ones.
Costs of using different models
To choose between models you can use an article.
gpt-5.4-pro
$36
-
$216
gpt-5.4
$3
$0,30
$18
gpt-5.3-chat-latest
$2.10
$0.21
$0.21
gpt-5.2
$2.10
$0.21
$0.21
gpt-5.2-pro
$25.20
-
$201.60
gpt-5.1
$1.50
$0.15
$12.00
gpt-5
$1.5
$0.15
$12
gpt-5-mini
$0.3
$0.03
$2.4
gpt-5-nano
$0.06
$0.006
$0.48
gpt-4.1
$2.4
$0.6
$9.6
gpt-4.1-mini
$0.48
$0.12
$1.92
gpt-4.1-nano
$0.12
$0.03
$0.48
gpt-4.5-preview
$90
-
$180
o1
$18
$9
$72
o1-pro
$180
-
$720
o3
$2.4
$0.6
$9.6
o3-deep-research
$12
$3
$48
o3-pro
$24
-
$96
o3-mini
$1.32
$0.66
$5.28
o4-mini
$1.32
$0.6
$5.28
o4-mini-deep-research
$2.4
$0.66
$9.6
gpt-4o
$3
$1.5
$12
gpt-4o-mini
$0.18
$0.09
$0.72
gpt-4-turbo
$12
-
$36
gpt-4-turbo-preview
$12
-
$36
WhatsApp Business API (WABA) pricing
To improve interaction between WhatsApp services and Selarti you can use the WhatsApp Business API integration.
WhatsApp Business API allows companies to integrate WhatsApp with Selarti for message automation, sending notifications, and customer support.
Rate $0.03 - $0.08 for opening a 24-hour conversation. The cost varies depending on the country. For Russia $0.085, rates for other countries you can see here.
Protection against bots.
If an AI encounters a bot in any of the channels, it will be blocked to avoid an endless dialogue. When blocked, the dialogue is marked as «bot» and «closed». Incoming messages will arrive in the personal account, but the AI will not respond.
- maximum $1 per conversation; - maximum 6 identical messages in a conversation.
Message sending limits
To avoid blocks from services you need to adhere to the limits.
There are no limits on processing incoming dialogues. The outgoing communication limit is specific to each channel. When creating a task with the work format «Incoming and outgoing communication» choose the daily dialog limit with users depending on the channel:
Telegram Premium (Telegram cloud)
10
20
30
40
Vkontakte user
10
20
25
30
WhatsApp Web
5
5
7
10
WhatsApp Business API (WABA)
issued by the WABA service upon registration: 200 and more
issued by the WABA service upon registration: 200 and more
issued by the WABA service upon registration: 200 and more
issued by the WABA service upon registration: 200 and more
Vkontakte bot
issued by the VK service upon registration: 200 and more
issued by the VK service upon registration: 200 and more
issued by the VK service upon registration: 200 and more
issued by the VK service upon registration: 200 and more
For correct operation of the Telegram cloud channel it is recommended to connect Telegram Premium.
The «More than a month» column shows the maximum recommended daily dialog limit. Exceeding it threatens blocks.
For new accounts (recently registered or purchased on an exchange) these limits are the maximum. Long-standing accounts that have been operating for years may send more messages, but the risks of blocking still remain.
When configuring a task these limits must be specified in the «Daily limit per channel» field.
Last updated