Model choice is the biggest single factor in what a chatbot costs to run. To compare fairly, here is one workload priced across several current models.
The workload
1,000 active users, 10 conversations each per month, 6 messages per conversation, an 800-token system prompt, 60-token user messages and 300-token replies, with full chat history. That is 10,560 input and 1,800 output tokens per conversation.
Input tokens
6 × 800 + 6 × 60 + 360 × 6 × 5 ÷ 2equals10,560
Output tokens
6 × 300equals1,800
Per conversation
10,560 ÷ 1M × $2.00 + 1,800 ÷ 1M × $10.00equals$0.0391
Per month
$0.0391 × 10,000 conversationsequals$391.20
Monthly cost by model
- GPT-5.6 Luna: $42.72
- Gemini 3.5 Flash-Lite: $76.68
- Claude Haiku 4.5: $195.60
- Claude Sonnet 5: $391.20
- GPT-5.6 Terra: $427.20
- Gemini 3.1 Pro: $427.20
The cheapest and most expensive options here are ten times apart for the same traffic. Mid-tier models cluster around $2 per million input tokens, so the difference between them comes mostly from output prices.
Choosing
Price is only half the decision. Test each model on your own conversations and compare quality, then pick the cheapest one that meets your bar. Prices here were verified in September 2026 and change often.