How to setup the Proxy

[axetroy]

I'm glad I found this project, but I'm encountering some problems when trying to set up the proxy.

I can't find any useful information in the documentation; it's too rudimentary.

Could someone please help me? I would be very grateful.

---

I run the following command to run the Proxy

headroom proxy --openai-api-url http://localhost:20128/api/v1

Then I test the APIs and got an error

curl http://localhost:8787/api/v1/chat/completions \
	-H "Content-Type: application/json" \
	-H "Authorization: Bearer <MY_TOKEN>" \
	-d '{
		"model": "opencode/deepseek-v4-flash-free",
		"messages": [
		{
			"role": "user",
			"content": "How many r`s are in the word `strawberry?`"
		}
		],
		"reasoning": {
		"enabled": true
	}
}'

{"error":{"code":"AUTH_001","message":"Invalid management token","correlation_id":"6dad2654-26d4-481f-b40d-0b7796e19fb6"}}

However, I can test the orignal APIs and it works like expect

curl http://localhost:20128/api/v1/chat/completions \
	-H "Content-Type: application/json" \
	-H "Authorization: Bearer <MY_TOKEN>" \
	-d '{
		"model": "opencode/deepseek-v4-flash-free",
		"messages": [
		{
			"role": "user",
			"content": "How many r`s are in the word `strawberry?`"
		}
		],
		"reasoning": {
		"enabled": true
	}
}'

data: {"id":"c6b1ce5c-647d-4857-b253-9f8ea2768453","object":"chat.completion.chunk","created":1783058257,"model":"deepseek-v4-flash-free","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"c6b1ce5c-647d-4857-b253-9f8ea2768453","object":"chat.completion.chunk","created":1783058257,"model":"deepseek-v4-flash-free","choices":[{"index":0,"delta":{"reasoning_content":"We need to count the number of 'r's in the word \"strawberry\". Let's spell it: s-t-r-a-w-b-e-r-r-y. So we have r at positions 3, 8, 9? Wait: s(1), t(2), r(3), a(4), w(5), b(6), e(7), r(8), r(9), y(10). So three r's? But let's double-check: strawberry has two r's? Actually common spelling: strawberry is often spelled with two r's? Wait, \"strawberry\" has two 'r's? Let's think: straw-berry. Straw has one r, berry has two r's? Actually berry is b-e-r-r-y, so two r's. Straw is s-t-r-a-w, one r. So total three r's. But sometimes people think it's two? Let's confirm: The word \"strawberry\" has three r's. Yes, it's a common trick question. So answer: 3.\n\nBut the question says: \"How many r`s are in the word `strawberry?`\" So we need to output the number.\n\nThus final answer: 3."},"finish_reason":null}]}

data: {"id":"c6b1ce5c-647d-4857-b253-9f8ea2768453","object":"chat.completion.chunk","created":1783058257,"model":"deepseek-v4-flash-free","choices":[{"index":0,"delta":{"content":"The word \"strawberry\" contains three 'r's: one in \"straw\" and two in \"berry\".\n\nAnswer: 3"},"finish_reason":null}]}

data: {"id":"c6b1ce5c-647d-4857-b253-9f8ea2768453","object":"chat.completion.chunk","created":1783058257,"model":"deepseek-v4-flash-free","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":2097,"completion_tokens":289,"total_tokens":2386,"cached_tokens":0,"reasoning_tokens":259}}

: x-omniroute-cache-hit=false
: x-omniroute-latency-ms=6
: x-omniroute-response-cost=0.0000000000
: x-omniroute-tokens-in=97
: x-omniroute-tokens-out=289
: x-omniroute-version=3.8.43
: x-omniroute-model=deepseek-v4-flash-free
: x-omniroute-provider=opencode-zen
data: [DONE]