Same workload comparison

Start with what this workload buys you

The same token mix is applied to each plan’s prices and model allowance. Check shared pools and time windows on the plan page.

Comparison example: 12,000 tokens/request · 83% cache read

Command Code GOAT ↗

Base price variant · Speed variant, Peak pricing

Plan rules ↗
Capacity from model allowance / month 800.0M tokens
CP value
No data
Equivalent cost / 1M
$0.0750
Model allowance (theoretical)
$60
Does it work well?

Loading…

Anonymous user reports. They never change CP value; after 10 votes they count toward Today’s Pick. Press again to undo.

Example workload (12,000 tokens/request)

Input
1,000
Cache read
10,000
Output
1,000
Cache write
0

02Prices and allowances

Keep prices, requests and plan windows in one evidence ledger

Expand the ledger to verify four token prices, cost per request, model allowance and theoretical requests for this workload.

Open prices, capacity and plan windows
Metric Command Code GOAT DeepSeek V4.1 Flash Fast (latest)
Input / 1M$0.16
Cache read / 1M$0.0160
Output / 1M$0.58
Cache write / 1M$0.000000
Cost / request Recalculated $0.00090012,000 tokens/request
Model allowance Published $60Based on this model’s plan allowance
Requests / month Recalculated 66,666Estimated with the 12,000-token workload above
5-hour limit Published $14Plan window
Weekly limit Published $35Plan window
Monthly limit Published $70Plan window

03Official reference rows

The official reference behind each plan

Compare each provider’s reference token mix and published estimates below.

Command Code GOAT View the provider’s reference workload Based on the published request estimate
DeepSeek V4.1 Flash Fast (latest) · Speed variant, Peak pricing
Reference input / request800
Reference cache read / request50,000
Reference output / request200
Reference cache write / request0
Reference volume / request51,000
Cost per request$0.001044
Model monthly allowance$60
Published requests / month57,500
Published capacity / month2.9B
Capacity basisBased on the published request estimate

Peak price variant

DeepSeek peak windows are weekdays 01:00–04:00 and 06:00–10:00 UTC.

MetricOff-peakPeak
Input / 1M$0.16$0.32
Cache read / 1M$0.0160$0.0320
Output / 1M$0.58$1.16
Cost per request$0.001044$0.002088
Estimated requests / month57,47128,735
Calculation

Cost per request = add the four token classes after multiplying each by its price per 1,000,000 tokens.

floor($60 ÷ $0.001044) = 57,471

Official source: Command Code GOAT · Snapshot captured: 2026-10-23

05Usage and billing note

Pricing conditions to keep in view

These model-level conditions change the estimate; the official plan document remains the source for plan rules.

Command Code GOAT: The default view uses off-peak pricing; peak windows are weekdays 01:00–04:00 and 06:00–10:00 UTC.