ai-proxy

Enter your API key to access the dashboard

Use the ap-... key printed on first server start, or ask an admin to mint one.

ai-proxy

ai-proxy
Overview Token Pool Activity Users Usage patterns Settings API Keys Logs
Live
Connecting…
?
All systems operational
Tokens Online
—
—
Headroom 5h / 7d
—
—
Requests
—
Tokens Processed
—
Total processed
Avg Latency
—
Average response time

Wall of Sh(f)ame

via proxy direct
Amber is direct use of your account; the neutral ring is use via the proxy

Token Pool

Tokens over time

Last 24 hours

Token Distribution

In-flight requests

Live

Recent requests

TimeUserTokenModelStatusInput / OutputDuration
No requests yet

Quick Actions

Token Pool

All Anthropic accounts currently feeding this proxy.

Activity

Requests, token usage, and latency over time.

Tokens over time

Users

People who can use this proxy. Each gets their own API key.

#NameRoleStatus Cache (24h) Reqs (24h) Fresh tokens (24h) Last activeContributed Actions

API Keys

Your personal key, and how to point Claude Code or Codex at this proxy.

Your API key

Endpoint
Works with
Claude Code and Codex. Requests are logged under your name.

Set up a client

  1. Add to your shell rc file (~/.bashrc, ~/.zshrc)
  2. Run claude as normal
    Nothing to install, no Anthropic login needed on your machine.
  1. Paste into ~/.codex/config.toml
    Paste it at the very top of the file.
  2. Run codex as normal
    No ChatGPT login needed on your machine. The key lives in the config file, not your shell: Codex's background daemon makes the requests and never sees variables exported after it started.

Add a token

Contribute a subscription to the shared pool. Each provider has its own pool.

Anthropic

Claude Pro / Max · serves Claude Code
1
Connect with Anthropic
2
Paste the code

We'll open Anthropic's authorization page in a new tab. Log in with the account you want to share, and you'll be shown a code to paste back here.

Authorization tab opened. Log in, copy the displayed code (it looks like xxxxx#yyyyy), and paste the whole thing below.

Token added

Advanced: paste credentials JSON instead
Only if the Connect flow doesn't work for you.
Linux / WSL: cat ~/.claude/.credentials.json
macOS: security find-generic-password -s "Claude Code-credentials" -w

OpenAI

ChatGPT Plus / Pro · serves Codex
1
Sign in with ChatGPT
2
Paste the page address

Sign-in happens in a small window. The last step looks broken, but it isn't. Here's what to expect:

  1. Sign in with the ChatGPT account you want to share, and approve Codex.
  2. The window then shows an error page. That's expected: the address is what we need, not the page.
    localhost:1455/auth/callback?code=ac_…
    This site can't be reached
  3. Copy that window's whole address (click the address bar, then Ctrl/⌘+C), close it, and paste it here.

Sign-in window opened. When it shows "This site can't be reached", copy its address (starts with localhost:1455/auth/callback) and paste it below. Finishing is automatic.

Token added

This is a separate login from your own Codex: the pool keeps its own session, so your local codex stays signed in.

Fallback pool

When every token in this pool is at its limit, requests from borrow capacity from the fallback pool instead of getting a 429. Borrowed requests run on other people's subscriptions.

Logs

Recent proxied requests, most recent first. Rows marked retried are pool tokens that failed and were retried on another token -- the client never saw those statuses.

TimeUserTokenModelStatusInput / OutputDuration
—

Usage patterns

Turn session evidence into better guidance.

Loading

Pattern totals · all sessions

Checks collected—
Awaiting review—
Review coverage—
Detection threshold—

Checks

All sessions · grouped on this page

Your review workspace

Choose a check to review the assessment and label what happened.

Check

Claude’s assessment
—Jev probability

What actually happened?

Full grading criteria

Labels save immediately. Judge what happened independently of Jev’s score.

Conversation evidence


                  
Formatted from the saved tail. Raw text preserves the exact evidence.

Tool activity

For grading only
MCP available
Tools called

Calls reflect the retained tail. These facts never decide the verdict.

Audit details Grading facts & definition
Grading facts
Pattern definition at check time
Exact request sent to Jev

Find a threshold you can trust.

Explore the trade-off between useful detections and missed opportunities across all sessions for this pattern. Check-list filters do not change these metrics.

Precision & recall

0.80

Exploring doesn’t change the pattern. Saving a threshold applies to future checks.

At this threshold

Early evidence

Precision measures how often detections are real. Recall measures how many real opportunities are detected. Review negative checks too.

All threshold measurements
ThresholdPrecisionRecallTrue positivesFalse positivesFalse negativesTrue negatives

Define what matters.

Keep the pattern clear and choose whose sessions contribute evidence.

Check frequency

Applies to this instance

Choose how much conversation growth triggers a check. Token counts are estimated; changing the frequency takes effect without a restart.

Pattern definition

User hints off

Write a reminder about recent session evidence. A new detection resets the reply count instead of adding to it; a later check that finds no pattern stops the reminders. Reminders expire 15 minutes after the check. Answers never wait for a check, so the message may appear on a later reply.

Preview · hints off
ai-proxy usage hint

Your message will appear here.

Changes apply to future checks. Past checks retain their saved definition, threshold and verdict.

Participants

Use a person’s switch to enable collection. If setup is needed, choose patterns and Save & enable. Edit each person’s selection under Patterns; Pattern definition changes the rule for everyone.

Loading collection configuration…

Welcome to ai-proxy 👋

This is a shared Claude pool. Pick a path to get started.

You can always do the other one later from the sidebar.

User stats

—
Requests
—
Fresh tokens
—
Observed direct use (lower bound)
—
Avg latency
—
Errors

Top models

    Pool tokens used

      Prompt cache by prefix

      PrefixVerdictModelReqs Read Written Hit Blocks
      No requests in the selected range.

      Create user

      API key for :

      Shown once. Hand this to the user now — you can't retrieve it later. Use "Rotate key" in the users table if lost.