BOI·PROXY
checking…
Requests served
–
0 errors
Upstream
–
–
Uptime
–
seconds online
Last minute
–
– in 5 min
Models
–
– allowed
WARP pool
–
–

Recent requestslive feed

TimeModelResultLatencyCount
no requests yet - go make some noise.

Allowed models

These are served on /v1/models and accepted by the proxy. Hit TEST to send a tiny completion and see live status. The default model is used when a request asks for an unknown one. Auto-sync probes every upstream free model and prunes the dead ones automatically.

auto-sync: …
ModelDefaultLast test

WARP pool…

Managed Cloudflare WARP instances used as SOCKS5 egress. Healthy instances join the outbound proxy pool next to proxy.txt entries. Requests stick to the entry that answers 200 until it hits 429, then rotate. Reset cycles the tunnel for a fresh egress IP.

Start or stop the WARP pool. Needs the warp-svc/warp-cli binaries (see guide.txt section 10c).
#StateAddressEgress IPUptimeRestartsLast error
Loading…

Quota guard…

Anonymous free quota rides on the egress IP. On a 429 the guard marks that IP spent and rotates to the next one. When all IPs are spent it resets all WARP instances for fresh IPs and starts over from IP 1.

–
Loading…

Outbound proxies…

Every egress entry in the pool: proxy.txt, config and environment entries. Sticky: the entry that answers 200 keeps serving until it 429s, then rotation moves on. WARP instances are listed above. Addresses show scheme + host:port only - credentials are never shown. Egress IPs refresh automatically every 30 seconds. Test probes one entry on demand and reports its egress IP and latency.

Last request: none yet.

Pinned: none yet.

Free pool: open.

Use proxy.txt entries in the pool.
#AddressSourceLast testEgress IPLatency
Loading…

Usage statistics…

Requests
–
–
Total tokens
–
Prompt + output tokens
Cache tokens
–
–
Output tokens
–
Generated completions

Categories

NameRequestsOKOutputAvg latency

Traffic

Server settingsport / host need restart

Loaded ApiKEY Free = … Loaded ApiKEY GO = …
Trust x-forwarded-for from a reverse proxy
Auto-sync models (probe upstream free models, prune dead ones)
Auto-track opencode releases & update the User-Agent
Inject x-opencode-session header per client (free tier needs it)
Rate-limit chat requests per client (0 = off)

Server logs

Loading…