Free LLM API

• https://www.awanllm.com
• https://api.together.xyz/signin
• https://www.together.ai/
• https://cloud.sambanova.ai/apis
• https://www.mixedbread.ai/
• The fastest and most efficient inference engine to build production-ready, compound AI systems. https://fireworks.ai/pricing

https://llm.extractum.io/

• https://www.baseten.co/

https://github.com/wandb/openui

https://docs.cloud.ploomber.io/en/latest/apps/docker.html

https://getomni.ai/blog/benchmarking-open-source-models-for-ocr

LLM inference

• https://fireworks.ai/
  • Build for small customsied model why we need huge model that know unwanted things so finetune the smalll model for specfic task