I've just found out about š°ššššš¾šš-š°šø/ššššššššš (https://github.com/AgentOps-AI/tokencost). š§šµš¶š š¹š¶šÆšæš®šæš š“š¶šš²š šš¼š ššµš² š½šæš¶š°š² š¼š³ šš¼ššæ š°š®š¹š¹š šš¼ š®š»š ššš šš£š: OpenAI, Anthropic, Mistral, AWS or Databricks...
For any model, you can use as input either string prompts or messages, and get as outputs either the price or token count.
Congrats to the AgentOps-AI team: this will be very useful when trying to get a ballpark estimate of a project's price, to compare APIs, or for precise monitoring of usage!