Custom model costs
Yes, it is possible to provide the costs per tokens for Langfuse to calculate the costs for generation with a custom model. However, the documentation provided does not contain any information about how to do that. [...] If you have any further questions or need assistance with integrating cost calculation into Langfuse, I recommend reaching out to the founders directly for guidance. They will be able to provide the most accurate and up-to-date information.The chat bot says I should reach out to you 👀 I'm using for one generation the Mixtral-8x7B-Instruct-v0.1 model (https://deepinfra.com/mistralai/Mixtral-8x7B-Instruct-v0.1). Is there an option in Langfuse to specify what the costs for the model are?
1 Reply
Hi @Nils Reichardt , it is not possible yet to add custom cost per model. This is high on our prio list though so there will be an uopdate on this soon.
Right now, this means you would have to ingest your tokens manually, but cost would not be calculated.