Models for chatbots and customer support
A support chatbot lives on latency, cost per ticket, and clean human handoff. This list mixes Flash/mini/Haiku for day-to-day and Sonnet when the case is sensitive or legal.
Models in this collection
| Model | Type | Context | Price |
|---|---|---|---|
 Gemini 2.5 FlashGoogle | Chat | 1M tokens | $0.327/M in · $2.7251/M out |
 GPT-4.1 mini (legacy)OpenAI | Chat | 1M tokens | $0.436/M in · $1.7441/M out |
 Claude Haiku 4.5Anthropic | Chat | 200k tokens | $1.0901/M in · $5.4503/M out |
| Gemini 2.5 Flash-LiteGoogle | Chat | 1M tokens | $0.109/M in · $0.436/M out |
| GPT-5.4 miniOpenAI | Chat | 272k tokens | $0.8175/M in · $4.9053/M out |
 DeepSeek V4 FlashDeepSeek | Chat | 1M tokens | $0.1526/M in · $0.3052/M out |
 Mistral SmallMistral | Chat | 128k tokens | $0.109/M in · $0.327/M out |
| Claude Sonnet 5Anthropic | Chat | 1M tokens | $3.2702/M in · $16.3509/M out |
Why these models
Flash and mini hold high QPS cheaply; Haiku brings Claude tone; DeepSeek/Mistral Small for aggressive budgets; Sonnet for hard escalations.
Use them with Geek Hub
One OpenAI-compatible base URL and API key. Swap any model id from this list without rewriting your client.
Get an API keyFAQ
- How do I limit support hallucinations?
- RAG over your help center + “if it’s not in context, escalate” prompt. Do not let the model invent policies.
- Multilingual ES/EN?
- Yes. These models handle Spanish and English; set language in the system prompt per user.
- WhatsApp / Intercom integration?
- Geek Hub is the LLM. Your bot owns the channel; just swap base URL and model id.