OpenRouter

GPT-3.5 Turbo
Model:
Description (system prompt):
Temperature
Controls the randomness of the model's output. A higher value makes the output more creative.
Top P
Controls how top outputs are considered based on Nucleus Sampling. 0.8 means pick the top tokens with weighted probability totaling 80%.
Max Tokens
Specifies the maximum number of tokens used in the response, controlling its length. The model will stop generating tokens once this limit is reached, even if the completion is not finished.
Chat Memory
Specifies the maximum number of chat message to be included in each request.
MythoMax L2 13B (beta)
Model:
Description (system prompt):
Temperature
Controls the randomness of the model's output. A higher value makes the output more creative.
Top P
Controls how top outputs are considered based on Nucleus Sampling. 0.8 means pick the top tokens with weighted probability totaling 80%.
Max Tokens
Specifies the maximum number of tokens used in the response, controlling its length. The model will stop generating tokens once this limit is reached, even if the completion is not finished.
Chat Memory
Specifies the maximum number of chat message to be included in each request.
Llama v2 70B Chat (beta)
Model:
Description (system prompt):
Temperature
Controls the randomness of the model's output. A higher value makes the output more creative.
Top P
Controls how top outputs are considered based on Nucleus Sampling. 0.8 means pick the top tokens with weighted probability totaling 80%.
Max Tokens
Specifies the maximum number of tokens used in the response, controlling its length. The model will stop generating tokens once this limit is reached, even if the completion is not finished.
Chat Memory
Specifies the maximum number of chat message to be included in each request.

Save Chat

OpenRouter never saves your chats in the cloud.Your chats will disappear if you close the tab.Click to enable chat storage.

Focus Mode