add deepseek

README.md

@@ -45,6 +45,8 @@ curl -H "X-Proxy-Token: YOUR_SECRET" http://localhost:8080/elevenlabs/v1/voices
 | /elevenlabs/ | https://api.elevenlabs.io   |
 | /openai/     | https://api.openai.com      |
 | /telegram/   | https://api.telegram.org    |
+| /openrouter/ | https://openrouter.ai/api/v1|
+| /deepseek/   | https://api.deepseek.com    |
 | /health      | local health check (no auth)|
 
 ---
@@ -203,6 +205,6 @@ docker inspect --format='{{.State.Health.Status}}' api-proxy
 
 1. A k8s pod sends an HTTP request to `http://<proxy-vm>:8080/elevenlabs/v1/text-to-speech/...` with the `X-Proxy-Token` header and the original API key.
 2. Nginx checks the source IP against `ALLOWED_CIDR` and validates `X-Proxy-Token` — rejecting with 403 if either fails.
-3. The prefix (`/elevenlabs/`, `/openai/`, `/telegram/`) is stripped via rewrite, and the request is forwarded over HTTPS to the upstream with SNI enabled.
+3. The prefix (`/elevenlabs/`, `/openai/`, `/telegram/`, `/openrouter/`, `/deepseek/`) is stripped via rewrite, and the request is forwarded over HTTPS to the upstream with SNI enabled.
 4. `X-Proxy-Token` and all IP-leaking headers are removed before forwarding; API keys pass through unchanged.
 5. The response streams back unbuffered to the pod — critical for binary audio data and long-polling (Telegram).