Can I get Perplexity spend per day from the API?

Not as a series. Each response reports its own cost, so sum it per day yourself, or let Argus do it.

What happens when Perplexity credits run out?

Zero balance → 401 (looks like a bad key!); auto-reload optional, off by default. Auto-recharge is available.

LLMs

How to get your Perplexity API usage, balance and spend programmatically

Perplexity's API credit balance is only in the console; there's no verified endpoint for it. Every response reports its own cost in usage.cost.total_cost, so per-call spend is exact.

What the Perplexity API exposes

Signal	Perplexity
Balance	No
Spend history	No
Cost breakdown	No
Plan and quota	No
Cost on each response	Yes, the exact USD
Rate-limit headers	None
Credential	API key

Call it yourself

Credential. A Perplexity API key. Argus validates it with a 1-token sonar completion.

What each response carries

{
  "id": "6f0e…",
  "model": "sonar",
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 240,
    "cost": { "total_cost": 0.0061 }
  }
}

Trimmed to the fields Argus reads. Values are examples.

No billing API, so measure from your side

Argus can't poll a Perplexity balance, so spend is the sum of usage.cost.total_cost the SDK reads off each response.

Gotchas

A zero balance returns 401. It looks exactly like a bad key.
Auto-reload is optional and off by default.
Cost is per-token plus a per-request fee that scales with search context size, so token counts alone undercount.
No rate-limit headers. Limits rise through tiers 0–5 by cumulative purchases.

How Perplexity charges

Prepaid credits: per-token cost plus a per-request fee that scales with search context size. Tiers 0–5 by cumulative purchases raise rate limits.

Tier 0: 50 RPM (sonar)
Tier 5: 4,000 RPM

At zero. Zero balance → 401 (looks like a bad key!); auto-reload optional, off by default.

requests per minute, per key. Per model per tier; no rate-limit headers.

Or let Argus track it

Paste the key once. Argus keeps the ledger, and your coding agent reads it through the MCP server.

With the SDK, records the cost Perplexity reports on each response, so every call is itemized at its exact price.
Emails you on low balance, days to zero, a spend spike, or projected overage.
Hands all of it to your coding agent over MCP, so it can ask what a run cost or how much runway is left without leaving the editor.

> what has perplexity cost today, and how long until it runs out?

get_overview       → perplexity: mtd spend, burn per day, days to zero
get_request_costs  { "provider": "perplexity", "limit": 25 }
get_advisories     → credits_low, spend_spike, rate_limit_low …

Questions

Does Perplexity have an API for its balance?: Perplexity's API credit balance is only in the console; there's no verified endpoint for it. Every response reports its own cost in usage.cost.total_cost, so per-call spend is exact.
Can I get Perplexity spend per day from the API?: Not as a series. Each response reports its own cost, so sum it per day yourself, or let Argus do it.
What happens when Perplexity credits run out?: Zero balance → 401 (looks like a bad key!); auto-reload optional, off by default. Auto-recharge is available.
What key does Argus need for Perplexity?: A Perplexity API key. Argus validates it with a 1-token sonar completion.

Why provider dashboards disagree with your bill

Daily buckets, async settlement, cache pricing, per-request fees and charges that only bill on a match. Where the numbers drift, and how to reconcile them.

What happens when API credits run out

The status code and error each provider returns at zero balance. Several look like rate limits or bad keys, so they get retried instead of fixed.

Every balance endpoint

The balance call for each provider, side by side.