You are sending requests to https://bedrock-runtime.us-east-1.amazonaws.com with a model ID of (something like) anthropic.claude-sonnet-5
But you need to specify the region in the model ID, matching the region of the hostname; see: charmbracelet/catwalk#223 -- so something like "us.anthropic.claude-sonnet-5"
> grep error /tmp/vixd.log
12:08:52 [vixd] [llm req=2fd067f6d8a1] SSE stream error after 0 events: POST "https://bedrock-runtime.us-east-1.amazonaws.com/model/anthropic.claude-sonnet-5/invoke-with-response-stream": 400 400 Bad Request {"message":"Invocation of model ID anthropic.claude-sonnet-5 with on-demand throughput isn’t supported. Retry your request with the ID or ARN of an inference profile that contains this model."}
You are sending requests to https://bedrock-runtime.us-east-1.amazonaws.com with a model ID of (something like) anthropic.claude-sonnet-5
But you need to specify the region in the model ID, matching the region of the hostname; see: charmbracelet/catwalk#223 -- so something like "us.anthropic.claude-sonnet-5"