Choose the Perfect Plan
Create your custom ChatGPT with no coding required, or let us custom-build one for you, at a competitive fee.
We offer affordable and transparent pricing for our Multi-Agent AI Chatbot framework. Explore our subscription plans and add-ons below:
FREE TRIAL
Free 30-Day
Our Free 30-Day Trial is your opportunity to explore the most of the advanced features and benefits of our platform, commitment-free.
- 2 Chatbots
- 4 AI Agents
- Storage 50MB
- Unlimited Message Credits via User Own OpenAI API Key + Free 50 Message/Credits
- Test advanced features
- OpenAI - GPT-3.5 | GPT-4 | GPT-4o | GPT-4o-mini | GPT-o3-mini | GPT-o1
- Claude - 3.5 Sonnet, 3 Opus, 3 Haiku, 3.5 Haiku, 3.7 Sonnet
- Gemini 1.5 Flash, Gemini 1.5 Pro, Gemini 2.0 Flash
- DeepSeek-R1, DeepSeek-V3
- Website/App Embedding
- Dashboard Visitor-Analytics
Review our full feature list and add-ons below
Essential
$10/month
The Essential plan gives you a powerful chatbot to cover your core needs.
- 1 Chatbot
- 2 AI Agents
- Storage 500MB
- Unlimited Message Credits via User Own OpenAI API Key + Free 50 Message/Credits/month
- ChatGPT 3.5
- Website/App Embedding
Review our full feature list and add-ons below
Professional
$50/month
Experience the power of our Professional-grade option, tailored to meet the unique needs of established individuals.
- 2 Chatbots
- 4 AI Agents
- Storage 1GB
- Unlimited Message Credits via User Own OpenAI API Key + Free 75 Message/Credits/month
- OpenAI - GPT-3.5 | GPT-4 | GPT-4o | GPT-4o-mini | GPT-o3-mini | GPT-o1
- Claude - 3.5 Sonnet, 3 Opus, 3 Haiku, 3.5 Haiku, 3.7 Sonnet
- Gemini 1.5 Flash, Gemini 1.5 Pro, Gemini 2.0 Flash
- DeepSeek-R1, DeepSeek-V3
- Website/App Embedding
Review our full feature list and add-ons below
Start-Up
$200/month
The perfect starting point for launching new projects, offering a dependable groundwork for creative ventures.
- 6 Chatbots
- 4 AI Agents (per Chatbot)
- Storage 6GB
- Unlimited Message Credits via User Own OpenAI API Key + Free 100 Message/Credits/month
- OpenAI - GPT-3.5 | GPT-4 | GPT-4o | GPT-4o-mini | GPT-o3-mini | GPT-o1
- Claude - 3.5 Sonnet, 3 Opus, 3 Haiku, 3.5 Haiku, 3.7 Sonnet
- Gemini 1.5 Flash, Gemini 1.5 Pro, Gemini 2.0 Flash
- DeepSeek-R1, DeepSeek-V3
- Website/App Embedding
- Dashboard Visitor-Analytics
Review our full feature list and add-ons below
Enterprise Lite
$380/month
A comprehensive, scalable business solution, expertly designed for small and medium-sized businesses.
- 12 Chatbots + Transferring
- 8 AI Agents (per Chatbot)
- Storage 24GB
- Unlimited Message Credits via User Own OpenAI API Key + Free 150 Message/Credits/month
- OpenAi - GPT-3.5 | GPT-4 | GPT-4o | GPT-4o-mini | GPT-o3-mini | GPT-o1
- Claude - 3.5 Sonnet, 3 Opus, 3 Haiku, 3.5 Haiku, 3.7 Sonnet
- Gemini 1.5 Flash, Gemini 1.5 Pro, Gemini 2.0 Flash
- DeepSeek-R1, DeepSeek-V3
- Website/App Embedding
- Dashboard Visitor-Analytics
Review our full feature list and add-ons below
Enterprise Max
$500/month
For businesses of any size requiring comprehensive solutions.
- 24 Chatbots + Transferring
- 8 AI Agents (per Chatbot)
- Storage 50GB
- Unlimited Message Credits via User Own OpenAI API Key + Free 200 Message/Credits/month
- OpenAI - GPT-3.5 | GPT-4 | GPT-4o | GPT-4o-mini | GPT-o3-mini | GPT-o1
- Claude - 3.5 Sonnet, 3 Opus, 3 Haiku, 3.5 Haiku, 3.7 Sonnet
- Gemini 1.5 Flash, Gemini 1.5 Pro, Gemini 2.0 Flash
- DeepSeek-R1, DeepSeek-V3
- Website/App Embedding
- Dashboard Visitor-Analytics
Review our full feature list and add-ons below
- These are monthly subscriptions that you can cancel at any time.
- Using your own OpenAI API key allows you to purchase credit directly from OpenAI, thereby reducing operational costs. The free message credits included are intended for testing. Grab more via Add-Ons.
Feature Comparison
| Essential | Professional | Start-Up | Enterprise Lite | Enterprise Max | |
| Monthly Subscription | $10/month | $50/month | $200/month | $380/month | $500/month |
| Plan Features | |||||
| Chatbot count | 1 | 2 | 6 | 12 | 24 |
| Storage space | 500 MB | 1 GB | 6 GB | 24 GB | 50 GB |
| Context size token limit (per single input-output Memory) | 500,000 tokens/chatbot | 2 million tokens/chatbot | 5 million tokens/chatbot | 5 million tokens/chatbot | 5 million tokens/chatbot |
| 64K LLM Token Limit | ♥ | ♥ | ♥ | ♥ | ♥ |
| 128K LLM Token Limit | – | ♥ | ♥ | ♥ | ♥ |
| Use Own OpenAI API Key (Unlimited Message Credits) | ♥ | ♥ | ♥ | ♥ | ♥ |
| Free Message Credits | 50 | 75 | 100 | 150 | 200 |
| Collaborators | – | 1 | 3 | 5 | 10 |
| Personalization | |||||
| Dashboard | ♥ | ♥ | ♥ | ♥ | ♥ |
| Dashboard Visitor-Analytics | _ | _ | ♥ | ♥ | ♥ |
| Chatbot persona customization | Unlimited | Unlimited | Unlimited | Unlimited | Unlimited |
| Chat session logging | ♥ | ♥ | ♥ | ♥ | ♥ |
| Pre-Canned response (FAQ) | ♥ | ♥ | ♥ | ♥ | ♥ |
| Upload Images | _ | ♥ | ♥ | ♥ | ♥ |
| new YouTube Text Extract | _ | ♥ | ♥ | ♥ | ♥ |
| User info collection | ♥ | ♥ | ♥ | ♥ | ♥ |
| Chunk curation | ♥ | ♥ | ♥ | ♥ | ♥ |
| Frustration detection | _ | ♥ | ♥ | ♥ | ♥ |
| AI Agents | |||||
| AI Agents (per Chatbot) | 2 | 4 | 4 | 8 | 8 |
| Background Agents | _ | ♥ | ♥ | ♥ | ♥ |
| AI Supervisor Overrides | _ | ♥ | ♥ | ♥ | ♥ |
| Function calling (per agent) | 2 | 4 | 6 | 8 | 8 |
| Variables | ♥ | ♥ | ♥ | ♥ | ♥ |
| Automatic tags | _ | ♥ | ♥ | ♥ | ♥ |
| Branding | |||||
| Remove Watermark | – | – | ♥ | ♥ | ♥ |
| Chatbot Profile Picture | – | ♥ | ♥ | ♥ | ♥ |
| Custom Watermark | – | – | – | ♥ | ♥ |
| Own Domain | – | ♥ | ♥ | ♥ | ♥ |
| Advanced Features | |||||
| Debug Mode | ♥ | ♥ | ♥ | ♥ | ♥ |
| Source tracking | – | ♥ | ♥ | ♥ | ♥ |
| Option to choose OpenAI – GPT-4, GPT-4o, GPT-4o-mini, new GPT-o1, + new GPT-o3-mini | – | ♥ | ♥ | ♥ | ♥ |
| Option to choose Gemini 1.5 Flash, Gemini 1.5 Pro, + new Gemini 2.0 Flash | – | ♥ | ♥ | ♥ | ♥ |
| Option to choose Claude – 3,7 Sonnet, 3.5 Sonnet, 3 Opus, 3.5 Haiku, + 3 Haiku | – | ♥ | ♥ | ♥ | ♥ |
| new Option to choose DeepSeek-R1 + DeepSeek-V3 | – | ♥ | ♥ | ♥ | ♥ |
| Auto chatbot re-train | – | – | – | ♥ | ♥ |
| API Access | – | ♥ | ♥ | ♥ | ♥ |
| Webhooks | – | ♥ | ♥ | ♥ | ♥ |
| Plugins | All | All | All | All | All |
| User Identity Verification | – | – | – | ♥ | ♥ |
| Human Escalation | – | ♥ | ♥ | ♥ | ♥ |
| Deploy / Integrations | |||||
| Website/App Embedding | Unlimited | Unlimited | Unlimited | Unlimited | Unlimited |
| Slack (coming) | ♥ | ♥ | ♥ | ♥ | ♥ |
| Shopify | ♥ | ♥ | ♥ | ♥ | ♥ |
| WordPress | ♥ | ♥ | ♥ | ♥ | ♥ |
| Wix | ♥ | ♥ | ♥ | ♥ | ♥ |
| Squarespace | ♥ | ♥ | ♥ | ♥ | ♥ |
| Notion | ♥ | ♥ | ♥ | ♥ | ♥ |
| Zapier | – | ♥ | ♥ | ♥ | ♥ |
| new Make | – | ♥ | ♥ | ♥ | ♥ |
| Meta -Instagram, Messenger, Whatsapp (coming) | – | ♥ | ♥ | ♥ | ♥ |
| new SMS – Ytel | – | ♥ | ♥ | ♥ | ♥ |
| Commercial Rights | |||||
| Charge users to use chatbot | _ | _ | ♥ | ♥ | ♥ |
| Resell chatbots you built using Chatsistant | _ | _ | _ | ♥ | ♥ |
| Transfer Chatbots To Other Accounts | – | – | – | ♥ | ♥ |
| Support | |||||
| Email support | ♥ | ♥ | ♥ | ♥ | ♥ |
| Discord | ♥ | ♥ | ♥ | ♥ | ♥ |
| Context size token limit*: characters / 6 ≈ token | |||||
Explore Our Add-Ons
1 Extra Chatbot
$5/month
Add an extra, versatile chatbot to your account for broader functionality. Get it now!
Remove Watermark
$25/month
Option to remove our watermark “Powered by Chatsistant” from your chatbot for a clean look. Get it now!
5 Extra Chatbots
$20/month
Add 5 extra, versatile chatbots to your account for broader functionality. Get it now!
Unlimited Storage
$49/month
Expand your chatbot’s capabilities with our Unlimited Storage add-on. Get it now!
3 AI Agents
$19/month
integrate an additional 3 AI Agents to your Chatbot. Get it now!
Chatbot Profile Pic
$3/month
Give a profile picture to your Chatbot. Get it now!
1000 Message Credit
$19/month
Increase your chatbot’s capacity with an additional 1000 message credits a month. Get it now!
1 Extra Collaborator
$9/month
Add one extra collaborator to your project for increased teamwork. Get it now!
5000 Message Credit
$59/month
Increase your chatbot’s capacity with an additional 5000 message credits a month. Get it now!
Chatbot Auto Re-training
$35/month
Automate chatbot daily re-training to keep updated with user-specific knowledge. Get it now!
Human Escalation
$15/month
Integrate human escalation to enhance chatbot interaction capabilities. Get it now!
Per 200,000 tokens/month
$10/month
Unlock a monthly allocation of 200,000 tokens for your AI chatbot workflows. Get it now!
GPT Models Description and Credit Costs
Chatsistant now offers even more cutting-edge suite of OpenAI ChatGPT models, featuring the latest GPT-4o-mini-128K alongside new variants of GPT-o3-mini and GPT-o1. Engineered for efficiency, these models support RAG with token capacities up to 128k, all while using roughly 60% fewer message credits compared to GPT-3.5. Whether you need a compact model with 2k–8k tokens or a full-scale powerhouse with 16k–128k tokens, these options empower you to balance speed, cost, and performance for a wide range of applications.
| Model | Description | Credit Cost |
| GPT-3.5 | Roust and fastest model for general use. Not recommended when high accuracy is required | 1 /message |
| GPT-3.5-16k | Same as GPT-3.5, but processes ~4x more RAG context for better-informed output generation | 8 /message |
| GPT-4 1k | Designed for background operations with no output and no RAG; recommended for Background Agents with no RAG and no function-calling | 5 /message |
| GPT-4 2k | Designed for background operations with minimal RAG and limited function-calling; supports up to 2k total tokens | 10 /message |
| GPT-4 4k | Designed for quality interactions; supports up to 4k total tokens for RAG | 20 /message |
| GPT-4 8k | Similar to GPT-4-1106-4k; supports up to 8k total tokens for RAG | 35 /message |
| GPT-4 16k | Similar to GPT-4-1106-4k; supports up to 16k total tokens for RAG | 60 /message |
| GPT-4 32k | Similar to GPT-4-1106-4k; supports up to 32k total tokens for RAG | 120 /message |
| GPT-4 64k | Similar to GPT-4-1106-4k; supports up to 64k total tokens for RAG | 220 /message |
| GPT-4o-2K | The powerful GPT-4o; supports up to 2k total tokens for RAG for about 50% less message credits compared to GPT-4 model. | 5 /messages |
| GPT-4o-4K | The powerful GPT-4o; supports up to 4k total tokens for RAG for about 50% less message credits compared to GPT-4 model. | 10 /messages |
| GPT-4o-8K | The powerful GPT-4o; supports up to 8k total tokens for RAG for about 50% less message credits compared to GPT-4 model. | 20 /messages |
| GPT-4o-16K | The powerful GPT-4o; supports up to 16k total tokens for RAG for about 50% less message credits compared to GPT-4 model. | 40 /messages |
| GPT-4o-32K | The powerful GPT-4o; supports up to 32k total tokens for RAG for about 50% less message credits compared to GPT-4 model. | 60 /messages |
| GPT-4o-64K | The powerful GPT-4o; supports up to 64k total tokens for RAG for about 50% less message credits compared to GPT-4 model. | 120 /messages |
| new GPT-4o-128K | The powerful GPT-4o; supports up to 128k total tokens for RAG for about 50% less message credits compared to GPT-4 model. | 160 /messages |
| GPT-4o-mini-4K | The newest GPT-4o-mini; supports up to 4k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 1 /messages |
| GPT-4o-mini-16K | The newest GPT-4o-mini; supports up to 16k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 2/messages |
| GPT-4o-mini-32K | The newest GPT-4o-mini; supports up to 32k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 6 /messages |
| GPT-4o-mini-64K | The efficient GPT-4o-mini; supports up to 64k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 10 /messages |
| GPT-4o-mini-128K | The powerful GPT-4o-mini; supports up to 128k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 15 /messages |
| new GPT-o3-mini-2K | The efficient GPT-4o-mini; supports up to 64k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 1 /messages |
| new GPT-o3-mini-4K | The efficient GPT-4o-mini; supports up to 4k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 2 /messages |
| new GPT-o3-mini-8K | The efficient GPT-4o-mini; supports up to 8k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 4 /messages |
| new GPT-o3-mini-16K | The efficient GPT-4o-mini; supports up to 16k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 8 /messages |
| new GPT-o3-mini-32K | The efficient GPT-4o-mini; supports up to 64k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 16 /messages |
| new GPT-o3-mini-64K | The efficient GPT-4o-mini; supports up to 64k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 24 /messages |
| new GPT-o3-mini-128K | The efficient GPT-4o-mini; supports up to 128k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 48 /messages |
| new GPT-o1 1K | The efficient GPT-4o-mini; supports up to 1k total for basic smart chatbots. | 8 /messages |
| new GPT-o1 2K | The efficient GPT-4o-mini; supports up to 2k total tokens, great for launching. | 16 /messages |
| new GPT-o1 4K | The efficient GPT-4o-mini; supports up to 4k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 36 /messages |
| new GPT-o1 8K | The efficient GPT-4o-mini; supports up to 8k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 72 /messages |
| new GPT-o1 16K | The efficient GPT-4o-mini; supports up to 16k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 120 /messages |
| new GPT-o1 32K | The efficient GPT-4o-mini; supports up to 64k total tokens for RAG for about 60% less message credits compared to GPT-3.5 model. | 200 /messages |
| new GPT-o1 64K | The efficient GPT-o1; supports up to 64k total tokens for RAG. | 360 /messages |
| new GPT-o1 128K | The New extremely powerful GPT-o1; supports up to 128k total tokens for RAG. | 600 /messages |
Tag and tag descriptions, variables and variable descriptions, as well as function descriptions all count towards LLM token limit.
If you exceed the limit, the query will not be successfully executed.
Claude Models Description and Credit Costs
Chatsistant’s Anthropic Claude suite now boasts a full range of high-performance models with up to 128k tokens of context. Our lineup features the newly added Claude 3.5 Haiku, available in both 128k and 4k variants for intricate, data-intensive workflows and agile, real-time interactions, alongside Claude 3.7 Sonnet, which delivers enhanced reasoning and deep contextual understanding for advanced problem-solving. These new additions complement the robust Claude 3 Opus, providing a comprehensive AI toolkit engineered for sophisticated multi-agent operations and dynamic automation.
| Model | Description | Credit Cost |
| new Claude 3.7 Sonnet-2k | A versatile model suitable for quick, concise interactions with solid performance. Not recommended when using high accuracy is required | 4 /message |
| new Claude 3.7 Sonnet 4k | Offers enhanced capabilities for more detailed conversations and tasks at a 2x more RAG context | 8 /message |
| new Claude 3.7 Sonnet 8k | Designed for light background operations with minimal output and RAG; recommended for Background Agents with no RAG and no function-calling | 16 /message |
| new Claude 3.7 Sonnet 16k | Designed for background operations with minimal RAG and limited function-calling; supports up to 16k total tokens | 27 /message |
| new Claude 3.7 Sonnet 32k | Designed for quality Background Agents handling interactions, function calling, and more; supports up to 32k total tokens for RAG | 45 /message |
| new Claude 3.7 Sonnet 64k | The most capable, designed for highly complex and in-depth applications; supports up to 64k total tokens for RAG and Best for Muli-Agent Chatbots | 75 /message |
| new Claude 3.7 Sonnet 128k | The most capable, designed for highly complex and in-depth applications; supports up to 128k total tokens for RAG and Best for Muli-Agent Chatbots | 135 /message |
| Claude 3.5 Sonnet-2k | A versatile model suitable for quick, concise interactions with solid performance. Not recommended when using high accuracy is required | 4 /message |
| Claude 3.5 Sonnet 4k | Offers enhanced capabilities for more detailed conversations and tasks at a 2x more RAG context | 8 /message |
| Claude 3.5 Sonnet 8k | Designed for light background operations with minimal output and RAG; recommended for Background Agents with no RAG and no function-calling | 16 /message |
| Claude 3.5 Sonnet 16k | Designed for background operations with minimal RAG and limited function-calling; supports up to 16k total tokens | 27 /message |
| Claude 3.5 Sonnet 32k | Designed for quality Background Agents handling interactions, function calling, and more; supports up to 32k total tokens for RAG | 45 /message |
| Claude 3.5 Sonnet 64k | The most capable, designed for highly complex and in-depth applications; supports up to 64k total tokens for RAG and Best for Muli-Agent Chatbots | 75 /message |
| new Claude 3.5 Sonnet 128k | The most capable, designed for highly complex and in-depth applications; supports up to 128k total tokens for RAG and Best for Muli-Agent Chatbots | 135 /message |
| Claude 3 Opus 2k | Optimized for short, efficient interactions with high accuracy. Not recommended for background agents and function calling | 16 /message |
| Claude 3 Opus 4k | Suitable for more detailed exchanges with increased robustness. Great for running an agent with no function calling | 40 /message |
| Claude 3 Opus 8k | A powerful option for handling substantial conversational depth and complexity. Perfect for light multi-agent setups | 80 /message |
| Claude 3 Opus 16k | Provides strong performance for complex workflows and data-heavy tasks. Great for background agents and high token RAG use | 135 /messages |
| Claude 3 Opus 32k | Designed for advanced tasks requiring detailed context and high processing power at 32K RAG tokens for function calling and more | 225 /messages |
| Claude 3 Opus 64k | A robust, built for the most demanding and extensive applications. Handle high RAG, multiple agents, function calling and all the works. | 375 /messages |
| new Claude 3 Opus 128k | The newest most robust, built for the most demanding and extensive applications. Handle high 128k RAG, multiple agents, function calling and all the works. | 675 /messages |
| new Claude 3.5 Haiku 2k | Lightweight and efficient, ideal for quick, straightforward tasks | 1 /messages |
| new Claude 3.5 Haiku 4k | Lightweight and efficient, ideal for quick, straightforward tasks utilizing 4k RAM | 2 /messages |
| new Claude 3.5 Haiku 8k | Balances performance and complexity, suitable for moderate tasks; not recommended for function calling or high RAW contexts | 4 /messages |
| new Claude 3.5 Haiku 16k | A capable model for more detailed interactions with broader scope; great for multi-agent, RAG, function calling, and more | 7 /messages |
| new Claude 3.5 Haiku 32k | Handles intricate workflows with efficiency and good performance; perfect for mult-agent, RAG, function calling and more | 12 /messages |
| new Claude 3.5 Haiku 64k | Offers strong support for complex tasks with significant data requirements; best for multi-agent, high RAG context, function calling and so much more for workflow automation | 20 /messages |
| Claude 3 Haiku 8k | Balances performance and complexity, suitable for moderate tasks; not recommended for function calling or high RAW contexts | 2 /messages |
| Claude 3 Haiku 16k | A capable model for more detailed interactions with broader scope; great for multi-agent, RAG, function calling, and more | 3 /messages |
| Claude 3 Haiku 32k | Handles intricate workflows with efficiency and good performance; perfect for mult-agent, RAG, function calling and more | 4 /messages |
| Claude 3 Haiku 64k | Offers strong support for complex tasks with significant data requirements; best for multi-agent, high RAG context, function calling and so much more for workflow automation | 6 /messages |
Tag and tag descriptions, variables and variable descriptions, as well as function descriptions all count towards LLM token limit.
If you exceed the limit, the query will not be successfully executed.
Gemini Models Description and Credit Costs
Chatsistant’s Gemini LLM suite always delivers state-of-the-art performance with full 128k token capacity across all models. Gemini 1.5 Pro offers scalable token limits for deep, context-rich operations, while Gemini 1.5 Flash ensures rapid, high-speed processing with a full 128k context window. The latest Gemini 2.0 Flash pushes the envelope further, delivering unparalleled speed and efficiency for real-time, multi-agent interactions—all powered by 128k tokens. These enhancements provide an exceptional balance of scalability, precision, and advanced contextual understanding for even the most demanding AI workflows.
| Model | Description | Credit Cost |
| new Gemini 2.0 Flash 128k | A powerful new model suitable utilizing 128 RAG, perfect for consistent and concise interactions with solid performance. Recommended when using function calling and when high accuracy is required at a low cost | 1 /message |
| Gemini 1.5 Flash 64k | A versatile model suitable for quick, concise interactions with solid performance. Recommended when using high accuracy is required at a low cost | 1 /message |
| new Gemini 1.5 Flash 128k | A higher 128 RAG vversatile model suitable for quick, concise to complicated interactions with solid performance. Recommended when using high accuracy is required at a low cost | 1 /message |
| Gemini 1.5 Pro 2k | A model good for low context Chatbots and not using multi-agents, RAG, or function calling | 3 /message |
| Gemini 1.5 Pro 4k | Designed for light background operations with minimal output and RAG; not recommended for Background Agents, RAG, or function-calling | 7 /message |
| Gemini 1.5 Pro 8k | Designed for background operations with minimal RAG and limited function-calling; supports up to 8k total tokens | 14 /message |
| Gemini 1.5 Pro 16k | Designed for Background Agents handling interactions, light function calling; supports up to 16k total tokens for RAG | 24 /message |
| Gemini 1.5 Pro 32k | The most capable, designed for highly complex and in-depth applications; supports up to 64k total tokens for RAG and Best for Muli-Agent Chatbots | 45 /message |
| Gemini 1.5 Pro 64k | The most capable, Robust, 64k token limit model for multi-agents, function calling, high context RAG, and so much more | 80 /message |
| Gemini 1.5 Pro 64k | Extremely robust and high workflow capable, Robust, 64k token limit model for multi-agents, function calling, high context RAG, and so much more | 80 /message |
| new Gemini 1.5 Pro 128k | The most capable, Robust, 128k token limit model for multi-agents, function calling, high context RAG, and so much more | 80 /message |
Tag and tag descriptions, variables and variable descriptions, as well as function descriptions all count towards LLM token limit.
If you exceed the limit, the query will not be successfully executed.
DeepSeek Models Description and Credit Costs
NEWEST LLM ↑↓
Chatsistant’s DeepSeek suite now pushes the boundaries of AI performance with a 64k token capacity, delivering exceptional depth and precision for even the most demanding tasks. DeepSeek-R1 is engineered for intricate, data-intensive workflows, providing robust contextual understanding, advanced function calling, and multi-agent coordination—ideal for enterprise-grade automation and research. Meanwhile, DeepSeek-V3 is optimized for high-efficiency operations, balancing rapid processing with deep contextual insights for dynamic, real-time interactions. Together, these models empower you to unlock deeper insights and achieve superior outcomes across a wide range of applications.
| Model | Description | Credit Cost |
| new DeepSeek-R1 4k | A versatile model suitable for quick, concise interactions with solid performance. Recommended when using high accuracy is required at a low cost | 1 /message |
| new DeepSeek-R1 8k | A model good for low context Chatbots and not using multi-agents, RAG, or function calling | 2 /message |
| new DeepSeek-R1 16k | Designed for light background operations with minimal output and 16k RAG; not recommended for Background Agents, RAG, or function-calling | 4 /message |
| new DeepSeek-R1 32k | Designed for background operations with minimal RAG and limited function-calling; supports up to 32k total tokens | 8 /message |
| new DeepSeek-R1 64k | Designed for Background Agents handling interactions, light function calling; supports up to 64k total tokens for RAG | 16 /message |
| new DeepSeek-V3 8k | The most capable, designed for highly complex and in-depth applications; supports up to 8k total tokens for RAG and Best for Muli-Agent Chatbots | 1 /message |
| new DeepSeek-V3 16k | The most capable, Robust, 16k token limit model for multi-agents, function calling, high context RAG, and so much more | 2 /message |
| new DeepSeek-V3 32k | The most capable, Robust, 32k token limit model for multi-agents, function calling, high context RAG, and so much more | 4 /message |
Tag and tag descriptions, variables and variable descriptions, as well as function descriptions all count towards LLM token limit.
If you exceed the limit, the query will not be successfully executed.
OpenAI API Pricing Page
Frequently Asked Questions 🙋🏼
What is Chatsistant?
Chatsistant is an AI chatbot builder. It links to the data you provide as context and uses it as reference when responding to queries. You can upload data directly, import data from our cloud drive partners, supply a URL for automatic scraping or provide direct text input. You can embed the chatbot onto your own website or use it in Slack.
Does Chatsistant offer a free plan version of the framework?
Yes! Chatsistant offers a free forever plan called Launch Free for basic AI chatbot needs. Simply register for a free account, which activates a premium (test all features) 30-day free trial. During or after the trial, go to your subscription page to upgrade to the free forever plan. Make sure you are logged in to your account and click the top right corner dropdown menu to access your subscription on the popup window. Click Purchase to access our plans page. 🙂
Since this is an upgrade (even though it’s free), you’ll need to enter payment details to enable it. Your card won’t be charged—the total remains $0/month. You can remove your payment info when checking out or anytime if you choose.
What’s Included in Launch Free?
✅ ChatGPT 3.5 model + BYOK (Bring Your Own Key) via OpenAI
✅ 1 chatbot, 1 agent, 1 function call per agent
✅ Source training
✅ 25 free message credits/month (Unlimited with your own OpenAI API key)
For more, visit our pricing page.
Upgrade & Add-ons
- Easily upgrade to paid plans anytime.
- Buy message credits if you need more without opening an OpenAI account.
- Affordable add-ons to scale as your business grows.
We’ve packed enough into our Launch Free plan so you can build an AI chatbot that acts as your best sales or customer service rep, cutting costs and increasing conversions.
Where is my data stored?
We are a Software-as-a-Service. This means that our app, along with data you upload to us, resides online. We use Amazon Web Services (AWS) for hosting. Our servers are located in Oregon, USA.
Does it support other languages?
Yes. Our service currently uses OpenAI’s GPT-3.5 and GPT-4 large language models (LLMs) for generative AI functionality. The models are trained on publicly available data across the internet in over 95 languages, so Chatsistant also supports over 95 languages.
What should my data look like?
We support most text document formats (.pdf, .docx, .txt, .md, .tex, .csv, .xlsx, .xls). You can also provide an URL for automatic scraping of text content (this is not automatically updated on target website refresh), or input your own text directly.
Does Chatsistant Support GPT-3.5, GPT-4, GPT-4o, GPT-4o-mini, GPT-o3, and GPT-o1?
At Chatsistant, our back-end is engineered for unparalleled versatility in LLM selection, ensuring we stay ahead in AI innovation. Each model in our lineup is supercharged with up to 128k tokens—perfect for both lightning-fast interactions and deep, context-rich conversations. 🚀
OpenAI ChatGPT Models:
- GPT-3.5-turbo: The reliable workhorse for general and detailed responses.
- GPT-4: An advanced model for versatile, sophisticated interactions.
- GPT-4o & GPT-4o-mini: Now updated to deliver up to 128k tokens for optimized performance.
- GPT-o1 & GPT-o3 mini: Our newest cost-efficient variants that offer powerful performance while using about 60% fewer message credits compared to GPT-3.5.
Anthropic Claude Suite:
- Claude 3.5 Haiku: Available in both 4k for lightweight tasks and 128k for handling complex, data-intensive workflows.
- Claude 3.7 Sonnet: Delivers enhanced reasoning and deep contextual insights for dynamic problem-solving.
- Claude 3 Opus & Claude 3 Haiku: Trusted models offering robust performance across a wide range of AI applications.
Google Gemini Series:
- Gemini 1.5 Flash: Engineered for rapid, high-speed processing with a full 128k token capacity.
- Gemini 1.5 Pro: A scalable solution built for deep, context-rich operations.
- Gemini 2.0 Flash: The latest addition, pushing the boundaries of speed and efficiency for real-time, multi-agent interactions.
DeepSeek Models:
- DeepSeek-R1: Crafted for intricate, data-intensive workflows and enterprise-grade automation.
- DeepSeek-V3: Balances rapid processing with profound contextual insights, ideal for dynamic, real-time interactions.
Looking Ahead:
We’re committed to continuous innovation, with plans to integrate even more advanced models—such as Meta LlaMA and other open-source alternatives—as they mature, ensuring you always have access to the best AI solutions available. 🌟
See the next FAQ about all LLMs integrated with Chatsistant or view our pricing page for more details.
What LLMs is Chatsistant integrated with? (GPT, Claude, Gemini, DeepSeek?)
At Chatsistant, our back-end is engineered for unmatched versatility. Imagine an elite lineup of LLMs—each supercharged with up to 128k tokens—ready to tackle any challenge. Our platform comes with natively integrated large language models, giving you the flexibility to bring your own key (BYOK) or purchase message credits and token limits directly from us. See our pricing page for full details and breakdowns.
OpenAI ChatGPT
- GPT-3.5-turbo: The reliable workhorse for both general and detailed responses.
- GPT-4: Our advanced model delivering versatile and sophisticated interactions.
- GPT-4o & GPT-4o-mini: Optimized for speed and efficiency—all powered by 128k tokens.
- GPT-o3-mini & GPT-o1: Our newest cost-efficient variants, available in various token sizes to meet your needs.
Anthropic Claude
- Claude 3.5 Haiku: Now available in a lightweight 4k version for quick tasks and a powerhouse 128k variant for complex, data-rich workflows.
- Claude 3.7 Sonnet: Brings enhanced reasoning and deeper contextual insights for dynamic problem-solving.
- Claude 3 Opus & Claude 3 Haiku: Robust models for high-performance, versatile operations.
Google Gemini
- Gemini 1.5 Flash: Engineered for rapid, high-speed processing with a full 128k token capacity.
- Gemini 1.5 Pro: Scalable for deep, context-rich operations.
- Gemini 2.0 Flash: The latest addition, delivering blazing-fast responses and advanced context management—all with 128k tokens.
DeepSeek
- DeepSeek-R1: Designed for advanced multi-agent coordination and deep contextual analysis in enterprise-grade workflows.
- DeepSeek-V3: Strikes the perfect balance between rapid processing and profound contextual insights.
And that’s not all—our journey continues as we plan to integrate even more cutting-edge models like Meta LLaMA and other open-source alternatives as they mature.
📌 For full details and pricing, visit Pricing.
Can I share a chatbot I created?
Input-wise, you as the administrator, and your collaborators are the only ones to the design, customization, and data of your chatbot. Output-wise, you can share your chatbot for anyone to use.
Can I give my chatbots instructions?
Yes. You can customize your chatbot to have different personas via our template-guided prompt engineering.
How can I add my chatbot to my website?
You can embed an iframe or add a chat bubble to the bottom right of your website. To do that, create a chatbot and click “Embed on website”.
Need More Help?
Feel free to email us at su*****@*********nt.com or reference our terms & conditions.
– Chatsistant Team