Skip to main content

Console screens

The console is at proxium.tech/app. Each screen shows the project that you select in the top bar, or all your projects. The screens that show traffic have a Time window: Today, Last 7 days or Last 30 days. Select ? beside a title to read what the screen or the panel shows.

ScreenUse it toExplained in
OverviewSee the spend, and cap an appTrack spend
EndpointsGet a base URL and a key for your appsCreate endpoints and keys
RequestsSee each attempt, and why calls failedDebug a failed call
PerformanceCompare how fast, how often limited and how costly each vendor and model isMonitor your project
UsageRead the tokens, the cost and the calls over timeTrack spend
ClassifierSee how the classifier decides, how each request for auto got its tier, and write what the classifier asks Jev or ClefAutomatic routing
MemoryReview what the project learnedUse project memory
Memory settingsTurn memory on, set the retention and the goal checkUse project memory
LoopsSee each conversation that counts now, and each run that finishedLimits
RoutingSet the models of each tierRoute requests to models
KeysMake a plain virtual keyCreate endpoints and keys
ProvidersAdd vendors and their keysAdd vendors and your own keys
MCP serversGive your agents the tools of an MCP serverAdd MCP servers
Data protectionFlag, redact or block sensitive dataProtect sensitive data
Secrets foundSee the secrets that people pasted into stored conversations, and dismiss themSensitive data
Plan reuseLet an agent's planned tool calls skip the modelPlan reuse
ImproveFind what to change to spend lessLower your costs
TeamAdd and remove peopleInvite your team
SettingsSet what Proxium stores, export or erase the projectData handling
BillingSee your plan—

Settings, Team and Billing open from the top bar. The other screens are in the strip, in four groups:

GroupScreens
WatchOverview, Usage, Explore, Requests, Performance, Memory, Loops
ConfigureEndpoints, Routing, Classifier, Plan reuse, Memory settings, Providers, Keys, MCP servers
ProtectData protection, Secrets found
ImproveImprove

All projects​

If you are a member of more than one project, the project list in the top bar starts with All projects. The console opens on it. The address and your browser keep your choice.

ScreenIn All projects
OverviewThe totals of your projects, and Projects: the spend, calls, failed calls and last use of each project. A project that cannot route a call shows cannot route
Requests, Classifier › Log, ImproveThe data of all your projects. Each row shows its project
Performance, UsageThe models and vendors of all your projects together. Usage adds Project to Split by
Data protection, Settings, MCP serversThe matches, the alerts sent and the tool calls of all your projects, and the list of your projects
Endpoints, Routing, Classifier › Diagram and Setup, Plan reuse, Secrets found, Keys, Providers, Memory settings, Team, BillingThe list of your projects. Select one to open the screen for it

Select the name of a project in a row to open that project on the same screen. A change applies to one project only, so you make it in the project.

Overview​

ElementShowsYou can
Needs attentionThe list at the top, worst first, at most five lines. A line is one rule that crossed its line: the budget at 80% or more spent, a vendor that answered fewer than 95% of its calls, a model that was rate limited above 5%, a model whose p95 doubled from the first half of the window to the second, or a retired model. Each line opens the screen behind it. A rule needs 20 attempts before it speaks, so one bad call raises no line. Without a line that crossed, the list says that nothing crossed a lineOpen the screen of a line
SpentThe money of the window. Calls on a plan are left out; the line under it names what the plans used at list price
Remaining∞ during the open beta. In All projects, Projects shows the number of your projects
Saved by cacheWhat the cache saved, less what you charged for hits
Requests, TokensThe calls and the tokens of the window
Spend over timeThe cost for each time bucket
Model splitEach model by cost, with its share and its tokens
VendorsEach vendor: answered calls, input tokens, cache reads, output tokens, all tokens, cost (with the calls on a plan) and its share of the cost
Per-app burnThe spend, share, tokens and calls of each x-proxium-sourceSet Calls per hour and Dollars per day for one app
Per-key burnThe spend of each keySelect a key to see its apps
ProjectsIn All projects only: each project, busiest firstSelect a project to open it

Endpoints​

ElementShowsYou can
Endpoints, With own routing, ExpiredThe counts of your endpoints
Base URLhttps://proxium.tech/v1Copy it
Your endpointsEach endpoint: name, routing, last useRouting, Revoke
New endpointCreate an endpoint, with its own routing

Requests​

ElementShowsYou can
The app barThe calls of each appShow one app only
RequestsOne row for each request: When (with a short id under it), Route (the classifier hops and each model tried, with the reason of a failure in words), Cost and Result (answered, failed over, failed). Select a row for the app, the kind, Tokens (input · read from the cache · output), Took, the whole request id, the road of the request, and the prompt and the answer. A cost with + is a lower bound: a model of the request has no priceShow All calls, Your apps, Proxium memory, Failed or failed over or Lost the cache, and sort them by Newest or Slowest. Select a row for the road of the request and the prompt and the answer

Performance​

The same traffic seen from the side of the vendors: which model is fast, which one limits the rate, and what a call costs. The window is Today, Last 7 days or Last 30 days. The screen opens with one sentence: the fastest model, the cheapest call and the most reliable model, of those with at least 20 streamed calls.

ElementShowsYou can
Latency bandThe busiest models over time, as a band from p50 to p95Show Answer time or First token, and pick the models
Rate limits over timeThe share of the attempts of each model that were answered 429, for each time bucket
Speed against costEach model as a bubble: p95 against the cost of one answered call, sized by its calls
FailuresHow the attempts of each model ended over time, and the causes of the failed attempts in words, biggest first. One cause across several vendors is one lineDraw Attempts or Failures over time
Failures by provider, Failures by reasonThe failed attempts of each provider with its share of them, and the failed attempts by provider, outcome and reason with their models
Models and vendorsBy vendor and By model: answered calls, the share of the calls sent that were answered, input tokens, cache reads, output tokens and cost, as each vendor billed them, and the failures. A vendor row adds the mean time; the calls on a plan sit under the cost. A model row adds p50 and p90 and its state. Allowances: each vendor request or token allowance with what it used and when it resets. Retired now: each retired model and vendor, why, and until whenOpen a row for Retire, Retire vendor, Bring back and Bring back vendor
Answer healthHow the attempts of each model ended: answered, empty, cut at max_tokens, or failed. It counts what the gateway saw and does not say whether an answer was rightShow it as bars or as a series over time
Failover flowThe name the caller used and the model that answered, with the requests and the share of each pair. A model name on the left that differs from the answering model is a failover
Vendor scorecardOne row for each of the ten models with the most calls, then every model of the window: Answered (the share of the attempts sent that the vendor answered), Time to answer p50, p95 and p99, First token p50 and p95, Speed in output tokens per second, 429 (the rate-limited attempts and their share), Calls with the output tokens, and Cost of one call with the total under it. The best value of each column is marked. The heading row holds at the top of the panel and the model column at its left while the body scrollsSort by p95, First token p95, Speed, Answered or Cost per call, and press Show all 30 models to draw every model of the window (the same control returns to Show the 10 busiest)

Usage​

The tokens, the cost and the calls of the project over time, split by what you choose. The MCP tool proxium_read_usage_series answers the same numbers.

ElementShowsYou can
Time rangeOne hour, 24 hours, 7, 30 or 90 days. A range up to 3 hours is drawn by the minute, up to 8 days by the hour, up to 120 days by the day, and a longer one by the weekPick the range
Split byModel, Vendor, App, Key or Tier, and Project in All projectsPick the split
Tokens, Cost, CallsThe totals of the range, with the Busiest minute and the share of the input that the vendors read from cache
The chartThe metric you chose over time, with one series for each groupDraw Tokens, Cost or Calls
Tokens by kindNew input, cache reads and output, for each time bucket
By model, By vendor, …The twelve groups with the most tokens, and the rest as (other): tokens, new input, cache reads, output, cost and calls
CacheThe hits and what they saved, for each time bucket, by layer and by model, and the last hits with the caller that sent them
Who callsThe attempts and failed attempts of each app. Your apps are the tools and services that call with your keys or your login. Proxium, for this project is the memory worker, which finds facts in your conversations and searches them for each call

Classifier​

One screen with three tabs. The tab is in the address (#/classifier?section=diagram, log or setup), so a link opens the tab that it names. The old addresses #/classification and #/routing?section=classifier open the same tabs.

TabShowsYou can
DiagramFive boxes from left to right: Reuse (the share of the requests that reused the decision of their conversation), Facts (what the document reads from the request), Questions (each question, its kind, what it reads, and whether it is asked once for each item of a list), Rules (each rule in words, what it sets, and in how many of the classified decisions it held; the counts start on 16 Nov 2026), and Decision (what a call gets, and the tiers it can pick)Select the time window, and open Change the document
LogHow each request for auto got its tier. The figures: Requests for auto, Reused the decision (the share that read the decision of its conversation), Classified now (System One or a language model decided it), Timed out → standard (no hop answered in time), Classifier calls failed (of all classifier calls), and the typical time of the hop that answers most. Each hop reads as vendor/modelSelect the time window, and read the decision of one request
SetupWhat the classifier asks Jev or Clef, and what the answers doWrite the document of a scope, and test it

Log​

ElementShowsYou can
Requests, Decided by Jev, Response time, Failed calls, FallbacksThe figures of the windowSelect the time window
RoutingThe requests for auto, who decided them, and the share of each tier
Response timeThe typical time, the time 95% of decisions stay under, and the slowest answer of each classifier model
ConfidenceHow sure Jev was, and the average confidence of each tier
ModelsEach classifier model, its calls and how many it answered, and each call that failed
Top projectsIn All projects only: the projects that call the classifier mostSelect a project to open it
Decision logThe newest decisions: app, decider, confidence, tier and timeSelect a decision to read its route, or Details for the request

Setup​

One page for the whole call of the classifier. The bar at the top stays in view while you scroll. The page has four parts, in the order of the work.

ElementShowsYou can
Applies to (bar)The project, or one app or key, with the version of its documentSelect a scope, or add an app (its x-proxium-source) or a key (its prefix). An app wins over a key, and a key wins over the project
Classifier (bar)Jev or Clef. The page opens on the first model that your project's classifier chain asksSwitch the model. The page then offers only what that model takes: Clef has no box question, no long context, and needs two or more options or levels
Unsaved changes, Save, Versions, Remove this document (bar)The state of the draftSave, open an earlier version as a draft, or remove the document of the scope. Save stays off while the page lists a problem
What should the classifier decide? (a scope with no document)Checks to tick, in three groups: Routing, Context and Safety. Beside them, the document that applies now, in wordsTick the checks and create one document. All questions go to the classifier in one call. Or copy the document that applies, or write your own
1. What the model readsThe parts of the request that go into the callSwitch on any of these parts: the last message, the messages before it, the system message, the whole conversation, the output limit, the app, the project memory, a header
2. QuestionsThe questions that the model answers in one callAdd a question: Yes / no, Pick one, Rate on a scale or Find in an image. Add a ready-made check. Open a question with Edit to write what the model judges and to list its options or levels
3. RulesOne sentence for each rule: "If … , …"Open a rule with Edit. Add tests that fit the type of the question. Add actions: use a tier, try a model first, set the reasoning level, add the project memory, keep the cached model, flag the request or block it
AdvancedWhen the next classifier answers, a chat model as the last step, the call options of the model and the document as JSONEdit any of them
4. Test (right)The decision, which rule did what, what the model answered, and the call that was sentRun the draft on a request. A test is one paid call to the classifier. A test of an earlier draft shows that you changed the document

A scope with no document uses the document of the next scope, and at the end the template Tier and reasoning. Start from a template, from a copy of the document in force, or from nothing.

Memory​

ElementShowsYou can
Knowledge pageWhat the project knows, written from its memories
MemoriesThe memories, to review firstConfirm, Pin, Edit, Remove, add a New memory
Recent conversationsThe kept conversations, with title and summarySearch

With memory off, the screen says so and links to Memory in Configure.

Memory settings​

A setting of one project, so it is in the Configure run of the strip.

ElementShowsYou can
Setup (top)Memory on or off, the memory cost of this month, and the goal check with its share, daily cap, credit and judgeTurn memory on, set Only these senders, Delete conversations after and the Goal check
Erase one user (bottom)Erase one end user. Owners only

Loops​

A loop is an agent that turns more than once. The loop is on for a project that set nothing. The gateway counts every conversation and refuses no call, because every ceiling of that project is 0. A project stops counting with Stop counting on this screen or in Settings › Loop, and a call turns it off with the header x-proxium-loop: off.

A conversation is one task. The gateway takes the session anchor of the call. A call that carries the x-proxium-conversation header joins the conversation that the header names. The header names a conversation, or groups the calls of several sessions. It does not decide whether the project counts.

ElementShowsYou can
Agent runsRunning now, Cost so far, Finished and Goal reached, and who approves a new goal of a running agentStop counting or Start counting, choose who approves a new goal, open Ceilings
Goals that wait for youEach new goal that waits for a personApprove, Reject
Running nowEach conversation that made a call in the last ten minutes: its short id (a link to Memory), app, calls, cost, repeats and last callOpen the conversation
FinishedEach run that ended: calls, cost, how it ended, goal and end timeOpen the conversation
  • Calls is the number of calls of the conversation, and Cost is what they cost in total.
  • Repeats is the number of repeated tool calls. It counts a call with the same arguments, or the same error, when the work did not change between the two.
  • When a conversation is over its ceiling, the gateway refuses the next call with 429 loop_capped. Raise the ceiling in Settings › Loop, or set Over a ceiling to alert to let the calls pass.
  • The screen shows one project. Over All projects it asks you to select a project first, because a conversation belongs to one project.
  • See The loop for the settings and the routes.

Routing​

ElementShowsYou can
Which routing to showThe default chains, or the chains of the projectSwitch the view
Ready-made routingThe preset of the project, its version, and the models of each tierUse this preset, Copy and edit, Reset to the preset
Text routing, and one section for each other typeEach tier, and Resolves to: its chainChange, Use default
Where a call to this scope goesThe drawing of the routing as it runs: the scope that sets each chain, the model that a call reaches first, and every hop after it
Add a hop under a chain, and the arrow and close buttons of a hopThe chain as you edit itAdd, move or remove a hop, then Save as version N, or Undo my edits
VersionsEach version of the document of the scopeGo back to it
Scoped rulesThe rules for one app or one keyAdd a rule
When a call failsThe failover policy: extra calls to one model, first wait, what a 429 does, longest Retry-After wait, how long a rate-limited vendor and a vendor out of quota are skipped, the retries of a cut answer, the small output budget, models in a plan, the catalog fill, the rules that retire a model or a vendor, and the alertSave, Reset to default
Model catalogEach model, with Cost, per MtokFilter the catalog

The drawing is also where a person edits a chain, and each edit shows where a call would go before a save. See Edit the routing in the drawing.

Keys​

ElementShowsYou can
Your keysEach key: name, prefix, limits, status, last useLimits, Revoke
Limits of a keyCalls per hour, Requests per minute, Tokens per minute, Dollars per daySave limits. An empty field is no limit
Name this keyCreate a key. Your new key shows it one time

Providers​

ElementShowsYou can
VendorsEach vendor: name, URL, type, models, keyAdd a vendor, Models, Remove
Your own keysYour keys for the platform providers and for your own vendorsAdd a key, Remove. Without pooled keys, the form lists only your own vendors

MCP servers​

ElementShowsYou can
ServersEach MCP server of the project: name, URL, toolsAdd a server, set its credential, turn tools on or off. Owners only
Connect an agentThe MCP URL of the projectCopy it
Tool callsEach call: when, tool, caller, outcome, timeOlder calls

Improve​

The page opens with one sentence. It gives the dollars a month that the findings with a saving add up to. It also gives the count of the other findings, which fix a failure or show where the cost sits.

ElementShows
Findings, Worth doing first, Worth a look, Worth fixingThe counts, and the estimated saving a month from the findings that name one
Reliability, Empty answers, Wrong model names, Classifier chain, Cost, Cache, Other findingsEach group of findings with its count, what the group costs you, and the screen where you fix it
Paused vendors and modelsOne folded table of the vendors and models that the failover policy paused: the vendor, the model, why, how many times in 7 days, and until when

Each finding shows its severity, its sentence, and one sentence of the evidence that it comes from. A vendor keeps its short name, without the prefix of the project. Classifier chain holds the hops of the classifier that answer almost nothing. Other findings holds a kind of finding that this page has no group for yet. When a vendor refuses the model name, the title of the failure names the cause. The cause gives the model that a chain asks and that the vendor does not list, and the screen to fix it.

Team​

ElementShowsYou can
Add a colleagueAdd a person as Member or Owner. Owners only
PeopleEach person, role and statusRemove. Owners only

Data protection​

ElementShowsYou can
What it looks forEach class: what it finds, its action, its alert, the action in forceSet off, flag, redact or block, and Alert. Save
Your termsYour words and phrases, one a lineEdit, then Save
Try a textEach match of a pasted text, and the text as the vendor would get itCheck
MatchesEach match: when, class, action, where, times, app, key. Never the valueSelect a time window

Secrets found​

Memory scans each message that it stores for keys, tokens and passwords (proxium_security_summary answers the same findings). A finding never holds the secret: only its kind, its place and a preview with the middle cut out.

Change a secret at its provider first (rotate). Then dismiss the finding here. A dismissal only hides the finding, and the text of the conversation still holds the secret.

The page counts the findings that need a person first. The scan closes a value that is a URL path or a documented example at once, with its reason.

ElementShowsYou can
Likely realThe open findings of the window, then Examples and URLs (closed, with the reason) and Kinds of secret foundSelect 7, 30 or 90 days
A kind of secretThe kind, its open findings, three examples, and a button that closes every open finding of the kind as not a secretPress the button, then confirm
By conversationEach conversation with a finding: its first line, its app, its kinds, its start and its open findingsOpen the conversation in Memory; Show and dismiss
A findingThe message, the kind, the preview, the time, and the state with the reason of a closed findingRotated or Not a secret

A dismissal covers every finding of the same secret.

Plan reuse​

ElementShowsYou can
What plan reuse doesWhat plan reuse is, and the mode of the apps with no setting of their ownChoose Off, Measure only or Use
AppsEach app with its calls of the last 7 days, its mode, its state and why it has no planChoose the mode of one app, Start measuring

Settings​

SectionYou can
Stored prompts and answersSet What to store: off, errors or all
CacheOne line: the cache on or off, and what it saved in the last 30 days. The lifetime opens Keep an answer for, and Match a question in other words where the project has it
Platform access (operators only)Allow or stop the use of the pooled keys, the platform classifier, and the platform Jev of the cache, the security checks, moderation, rerank, classify and the goal check of memory. The MCP tools proxium_read_platform_access and proxium_set_platform_access do the same
Spend alertsAdd Spend levels, set Warn at for the limits of keys, set the Webhook, Slack, Discord and Telegram channels, Send a test alert
Alerts that went outRead each alert: when, what about, the channel, sent, failed or blocked
Send call recordsAdd a webhook or an OTLP/HTTP destination, Test, Pause, Remove. Each row shows the records sent, failed and dropped
Export everythingDownload the data of the project
Erase this projectDelete the project and all its data. Owners only

Billing​

Plan shows open beta · free. Proxium is free during the open beta.