Same workload comparison
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
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)
02Prices and allowances
Expand the ledger to verify four token prices, cost per request, model allowance and theoretical requests for this workload.
| Metric | Command Code GOAT Tencent Hy3 |
|---|---|
| Input / 1M | $0.14 |
| Cache read / 1M | $0.0350 |
| Output / 1M | $0.58 |
| Cache write / 1M | $0.000000 |
| Cost / request Recalculated | $0.00107012,000 tokens/request |
| Model allowance Published | $70Based on this model’s plan allowance |
| Requests / month Recalculated | 65,420Estimated 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
Compare each provider’s reference token mix and published estimates below.
| Reference input / request | 800 |
|---|---|
| Reference cache read / request | 50,000 |
| Reference output / request | 200 |
| Reference cache write / request | 0 |
| Reference volume / request | 51,000 |
| Cost per request | $0.001978 |
| Model monthly allowance | $70 |
| Published requests / month | 35,400 |
| Published capacity / month | 1.8B |
| Capacity basis | Based on the published request estimate |
Cost per request = add the four token classes after multiplying each by its price per 1,000,000 tokens.
floor($70 ÷ $0.001978) = 35,389
Official source: Command Code GOAT · Snapshot captured: 2026-10-23
04Artificial Analysis external scores
Benchmarks are from Artificial Analysis. See the source version and matched model below.
Scores describe the model’s performance on the named benchmarks. Results on your own tasks also depend on tools, prompts and execution environment.