Cheap AI models: low cost per token
When budget wins, these models deliver usable quality at aggressive prices. Great for high-volume pipelines, classification, extraction, and drafts where you do not need a flagship. All run through Geek Hub’s OpenAI-compatible API.
Models in this collection
| Model | Type | Context | Price |
|---|---|---|---|
 DeepSeek V4 FlashDeepSeek | Chat | 1M tokens | $0.1526/M in · $0.3052/M out |
 Gemini 2.5 Flash-LiteGoogle | Chat | 1M tokens | $0.109/M in · $0.436/M out |
| Gemini 3.5 Flash-LiteGoogle | Chat | 1M tokens | $0.327/M in · $2.7251/M out |
 Ministral 8BMistral | Chat | 128k tokens | $0.109/M in · $0.109/M out |
 GPT-4.1 mini (legacy)OpenAI | Chat | 1M tokens | $0.436/M in · $1.7441/M out |
| Gemini 2.5 FlashGoogle | Chat | 1M tokens | $0.327/M in · $2.7251/M out |
 Claude Haiku 4.5Anthropic | Chat | 200k tokens | $1.0901/M in · $5.4503/M out |
| DeepSeek V4 ProDeepSeek | Chat | 1M tokens | $0.4742/M in · $0.9484/M out |
Why these models
We prioritized cheap input/output and decent latency: Flash/lite, mini, and aggressive open-weight options. DeepSeek Flash and Gemini Flash Lite set the floor; Haiku and GPT-4.1-mini step up when you want more reliability.
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
- What is the cheapest model on Geek Hub?
- It depends on timing and modality. For chat, start with DeepSeek Flash and Gemini Flash Lite; this page’s table shows price per 1M tokens for each.
- Are cheap models OK for production?
- Yes for bounded tasks: classification, short summaries, routing, tests. For long reasoning or critical code, step up (Sonnet, Pro, DeepSeek Pro).
- Can I switch from a cheap model to a premium one without rewriting?
- Yes. Same base URL and API key — only the model id in the request changes.