Which AI model for a customer service chatbot?
A chatbot that answers customers: order tracking, FAQs, returns, with a human handover.
GLM-5.3 Flash
€0.13 / €0.45 per million tokens (input / output)
The cheapest model on the Pareto line: each message rereads the history, so the price per message matters.
Cost for 1 million messages of about 2,500 tokens read (instructions and history) and 300 written: €469.
See in the ranking →Qwen3.8 27B
Free to use: only your hardware cost (a 24 GB GPU is enough with Q4 quantization).
Open weights under the Apache 2.0 license: conversations and customer data stay on your server.
See in the ranking →Claude Sonnet 5.5
€1.78 / €8.91 per million tokens (input / output)
On the Pareto line, with one of the best capability scores: more accurate answers and better tone with unhappy customers.
Cost for 1 million messages of about 2,500 tokens read (instructions and history) and 300 written: €7,128.
See in the ranking →Why these choices
For a chatbot, the model matters less than its guardrails: staying in scope, resisting injection attempts, promising nothing and handing over to a human. Test it with attacks before going live, and disclose that it is an AI (EU AI Act, Article 50).
Take action
Data: Epoch AI index (CC BY 4.0), developers' official prices converted at the ECB rate, updated 2026-10-03 · AI model ranking: intelligence, benchmarks and price