Python · Proprietary · v1.1.3

Stop overpaying for the
wrong model.

agentcents sits between your agent and any LLM. Before each call it forecasts the cost as an honest p50→p90 range on every candidate model — priced live, ranked by real capability scores — tracks every cent you spend, and proves its own forecasting accuracy on a calibration page. Point your client at it. Change nothing else.

$pip install agentcents

No API keys · No accounts · No code changes required

The problem

You default every call
to your best model.

Most agents pick one frontier model and use it for everything — classifying, retrieving, the hard reasoning step, the trivial cleanup step. The easy steps don't need a frontier model. You're paying Opus-4.8 prices to decide whether a message is a question or a complaint.

agentcents shows you, per step, what you pay and what you could pay — then routes each step to the cheapest model that clears the bar. In a typical 7-step task: all-Opus-4.8 $0.114 → cost-routed $0.055, 51% cheaper — keeping the flagship only where the work demands it.

agentcents plan view: all Opus 4.8 $0.114 vs cost-routed $0.055, 51% cheaper
Every step priced across current frontier models, ranked by capability. Synthetic demo.

How it works

A proxy that sits
in the middle.

Your
Agent
agentcents
localhost:8082
LLM
Provider
01
pip install agentcents

Install once. Works with Python ≥ 3.9.

02
agentcents start

Start the local proxy. Once per session.

03
point client at proxy

One base_url — or agentcents run -- your-cmd. No code changes.

04
agentcents usage

See exactly where every cent went.

Quick start

Change one line.
Or zero.

# Wrap your run — agentcents sets the base URLs,
# groups the run into one session, and gets out of the way.
# Your agent code is untouched.
$ agentcents run -- python my_agent.py

# Or, if you'd rather set it yourself — one env var:
$ export OPENAI_BASE_URL="http://localhost:8082/openai"
$ python my_agent.py

# Or one line in code:
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8082/openai")
# everything else stays exactly the same

Already setting your own session or tag headers? agentcents recognizes the common ones (X-Session-ID, X-Request-ID, and more) automatically. The proxy adapts to your client — never the other way around.


CLI reporting

$ agentcents usage
─────────────────────────────────
Total spend (last 48h) $3.42
my-agent $2.10 61%
research-agent $1.32 39%
─────────────────────────────────
Daily budget $5.00
Remaining $1.58

$ agentcents recent
claude-opus-4-8 512 tok $0.013 my-agent
claude-sonnet-5 1.2k tok $0.012 research-agent
gpt-5.6-terra 800 tok $0.012 my-agent

New in v1.1.3

Forecast. Calibrate.
Then orchestrate.

Cost tools that auto-route on day one ask you to trust an estimator you've never seen graded. agentcents does it in the order an engineer would.

01
agentcents explain

Every candidate model priced before the call runs — measured input, output as an honest p50→p90 range learned from your own traffic. Rank-flips inside the range are flagged unstable, never hidden.

02
/explain · calibration

Every call silently logs forecast vs actual. Coverage gauges, q-error, one candle per call — the estimator graded in public, on your workload.

03
/orchestrator

Per-node routing decisions behind five gates — robustness, quality floor, tool-use, provider boundary, and trust: binding requires the calibration page to prove the forecasts first. Advisory today, by design.

04
✦ two cents

A neutral cost guide on every page. Runs on your own local model (~$0/answer, metered in your own ledger), sees aggregates never prompts — and it's allowed to say "use the free local model," because it isn't selling tokens.

New · works with Claude

Ask Claude
what it’s about to cost.

Two commands in Claude Code. Then just ask, in plain language — Claude prices every candidate model against your own ledger, before you spend.

# the cost skill — free, no install of agentcents required
/plugin marketplace add labham-llc/agentcents-skill
/plugin install agentcents@labham-skills

# optional: give Claude live tools over your own ledger
claude mcp add agentcents -- agentcents mcp
agentcents inside Claude recommending the local model over the requested cloud one

click to view full size

what would it cost to classify 500 support emails a day?

A per-model table with honest low→high ranges, the cheapest model that clears the task’s capability bar, and a Mermaid comparison — rendered right in the chat.

what did my agents spend this week?

Reads your local ledger through MCP. Spend by model and tag, zero errors, aggregates only — your prompt contents are never sent anywhere.

is my cost estimator trustworthy yet?

p90 coverage against its 90% target, q‑error against 1.00, and a straight verdict: calibrated, slightly overconfident, or not enough data to trust yet.

show me my longest session as a plan

The run reconstructed step by step with per‑node costs and cheaper alternatives — plus a link straight into your local dashboard for the rendered version.

Everything runs on your machine. The skill works with no account and no API key; the live tools read the ledger agentcents already keeps. Using claude.ai in the browser instead? Download the skill file → and add it under Settings → Capabilities → Skills. Source →

Pricing

Free forever.
Pro for serious agents.

Free
$0
Free forever, no account needed. Everything you need to start tracking and optimizing costs.
  • Proxy + cost logging
  • Exact-match cache
  • Budget alerts + hard block
  • Full CLI reporting
  • Cost forecasts (agentcents explain) + calibration page
  • Two Cents guide — local-first, ~$0/answer
  • Web dashboard (light + dark) · plan · orchestrator showcase
  • Local Ollama tracking
pip install agentcents
Pro
Pay once
One-time license key. Activate on any machine with agentcents activate <key>.
  • Everything in Free
  • Semantic similarity cache
  • Multi-agent TUI dashboard
  • Live call watch
  • Advisor + routing on your own traffic
  • Auto-routing (swap mode)
  • XGBoost cost predictor
Get Pro →

Supported providers

Any provider that speaks
OpenAI format.

Anthropic
OpenAI
Google Gemini
OpenRouter
Groq
Ollama (local)

Pricing syncs automatically on proxy startup from OpenRouter + LiteLLM. No manual updates needed.