There are two versions: ByteGPT e ByteGPT+ (Plus)
You can find two versions of ByteGPT, which can be found in the integrations listed in Kommo:
ByteGPT:
- Only works with OpenAI
- Only allows 1 single assistant
ByteGPT+ (Plus):
- Works with multiple GPT providers in addition to OpenAI
- Allows connection with multiple different assistants.
Plans and Prices
| Requests (up to) | BRL price (monthly) | |
| 2k | 2.000 | R$ 60,00 |
| 5k | 5.000 | R$ 110,00 |
| 10 k | 10.000 | R$ 175,00 |
| 20 k | 20.000 | R$ 250,00 |
| 30 k | 30.000 | R$ 320,00 |
in the context of ByteGPT, a “request” refers to a request sent to the OpenAI language model (such as GPT-3.5, GPT-4). Every time the ByteGPT asks the OpenAI AI model a question and receives a response, this counts as a request.
Didactic Example 1:
Let's imagine you have a chatbot integrated into your Kommo. In this chatbot, a user asks the following question:
- “What are your company’s opening hours?”
To answer this question, the ByteGPT uses the OpenAI API to generate a response. This process, from asking the question to obtaining the answer, is considered a request.
Important Note:
In salesbot flows in Kommo, there can be multiple requests in a single flow, depending on the number of webhooks (handlers) present. For example, if a conversation flow requires three iterations with the ByteGPT, this will count as three separate requests.
Didactic Example 2:
Let's assume your salesbot is configured to:
1. Collect the user name (Request 1).
2. Ask about interest in a specific product (Request 2).
3. Provide more details about the product (Request 3).
In this scenario, if the user interacts with all these steps, the ByteGPT will make three requests to OpenAI.
Cost of Requests:
Requests may vary in the number of tokens (text units) processed during the interaction. The cost is generally calculated based on the amount of tokens used. The signatures of ByteGPT are defined by the number of requests allowed per month, with different pricing plans to adjust to usage needs based on the volume of requests.
GPT Model and Price:
The GPT model chosen (such as GPT-3.5 or GPT-4) may affect the price charged by a provider such as OpenAI. However, this does not affect the monthly fee for the ByteGPT, which is charged only for the number of requests passed through its API, regardless of the number of tokens or the model chosen.
Summary:
- Request: A chatbot interaction that generates a request to GPT and a response, accounting for one unit.
- Request Variation: In complex flows, each interaction can represent a new request.
- Cost: Based on tokens processed, determined by the provider (OpenAI).
- Anual Subscription ByteGPT: Covers the number of monthly requests, regardless of tokens or GPT model.
For more information about customizing and optimizing your use of ByteGPT No. Kommo, consult our detailed guides or hire one of our services at: https://suporte.bytebio.com/servicos/.
O ByteGPT It works with all models available from OpenAI, including GPT-4o.
O pattern of the ChatGPT Webhook, existing in ByteGPT, Is GPT-4o.
You can change this model, as well as the number of tokens to be processed.
Already for the OpenAI Assistant, the model will be the one chosen by you in your account.
Payment Information
- Trial Periods: 14 days (2k Plan).
- We will not ask for payment information during installation.
- A subscription reminder will be sent by email, accompanied by a notification via WhatsApp a few days before the expiration date.
- On the invoice, you can choose the desired payment method, including credit card, Mercado Pago, PayPal, Stripe, among others.
- You will choose the plan you want when making your first payment.
- The values of the plans ByteGPT are based on the number of requests and are consistent across all versions of the ByteGPT.
- Each version of ByteGPT is charged independently. For example, if you use the version ByteGPT with the 2k Plan and also have the ByteGPT+ (Plus) with the 2k Plan, there will be two separate invoices.
- To upgrade or downgrade your plan, please send an email to [email protected]. Include your account ID and order details. For plan requests exceeding 30.000 requests, also use this contact.
- The price charged refers exclusively to the widget ByteGPT. Costs with GPT providers, such as OpenAI, are handled and paid directly by the customer, without intermediation from the Bytebio or ByteGPT.
Simulate costs with OpenAI
Carry out a simulation with an average number of messages or requests from your business, to get an approximate idea of the cost with OpenAI, to generate the messages or process the GPT.
In addition to the plan ByteGPT, additional costs may include:
- License Kommo: From 25 USD per user on the advanced plan.
- Costs of Requests/Messages Generated by the GPT Provider: Like OpenAI. This amount is paid directly by the customer into the provider's (OpenAI) account.
- Hiring a GPT Provider (if not OpenAI): If you choose providers such as Dify, Chatbase, retune or others, you may need to subscribe to plans with these providers.