Not every task needs the most powerful AI. Some need speed. Others need volume. That’s why we offer a range of models — so you choose the right brain for the job and get the most from every credit.
Credits Breakdown
| Model | Chats per | Best For |
|---|---|---|
| Claude 3.7 Sonnet | 1 | Deep reasoning, long documents, strategic content, accuracy-critical tasks. |
| Claude 3.5 Sonnet | 1 | General-purpose work with solid reasoning. |
| DeepSeek-R1 | 2.5 | Everyday use, balance of speed and intelligence, technical tasks. |
| Claude 3.5 Haiku | 3.75 | Fast drafts, summaries, low-latency use cases. |
| Amazon Nova Pro | 4 | Middle ground between performance and value. |
| Meta Llama 3.3 70B | 5.5 | Creative writing, coding, open-source transparency, budget-conscious power. |
| Amazon Nova Light | 50 | Bulk Q&A, lookups, internal tools, high-volume needs, simple reasoning. |
Note: Chat counts are approximate and may vary slightly based on usage patterns and prompt complexity.
What’s the Best Option for Me?
Here’s a quick guide:
- Need the best thinking available? Go with Claude 3.7 Sonnet.
- Want something fast and efficient? Claude 3.5 Haiku or DeepSeek-R1 are great picks.
- Building tools or experimenting? Use Llama 3.3 70B – amazing value and open-source.
- Running high-volume chat or Q&A? Nova Light is unbeatable for scale.
Still Not Sure?
We’ve built this so you’re in control. No mystery pricing. Just clear value per credit.
Tip: For most users, mixing models gives the best balance of quality and cost.
Need help choosing? Contact Us →
Let's Build Your Agency's Brain
See how ChatterKB can automate your workflows, elevate your team, and impress your clients.
No credit card required. 14-day free trial.