Euro open source specialist proposes LLM gateway to ease token bills
The Finnish open-source database provider says it cut its own AI token costs by 80% by moving to open-weight models. To help other developers manage token expenses and control their AI infrastructure costs, Aiven is building a gateway allowing seamless swapping of models. This responds to a broader industry shift toward cost-conscious AI adoption using mix-and-match approaches with open-weight models like Llama, Qwen, and Gemma alongside or instead of expensive frontier models from OpenAI and Anthropic.
Key points
- Aiven reduced internal AI token costs by 80% via open-weight models
- Building LLM gateway for developers to swap models without vendor lock-in
- Growing industry interest in cheaper open-weight alternatives to frontier AI models
Summary and key points written by AI from the headline and a short excerpt, so they can be incomplete or wrong. The Register did the reporting; read the original for the full story.
Read the full story at The Register
