API response for "Auto (best for prompt)"? | OpenRouter | Page 1

quiet crater Jun 22, 2024, 10:18 PM

#

I want to see which model was used by OpenRouter in the API response. This article (https://openrouter.ai/models/openrouter/auto) indicates the data exists in the users Activity tab, but how do we have this exposed via the API?

Auto (best for prompt) by openrouter

Depending on their size, subject, and complexity, your prompts will be sent to Mistral Large, Claude 3.5 Sonnet (self-moderated) or GPT-4o. To see which model was used, visit Activity.

A major redesign of this router is coming s...

crystal kayak Jun 22, 2024, 10:20 PM

#

What do you mean by the API btw? Like in the model listing API, or in the chat completion API?

quiet crater Jun 23, 2024, 6:21 PM

#

@crystal kayak The chat completion API, so that you can see which LLM was used to provide each response

frozen jungle Jun 23, 2024, 7:54 PM

#

Requests to the auto router should send down the model used in the model of the response

#API response for "Auto (best for prompt)"?