subsdaddy
The three LLM subscriptions I pay for: what each one actually runs, what it costs per billion tokens, and how fast it is.
quota read 2026-11-04 21:26Z · traffic 7 days (2026-10-28 21:28Z to 2026-11-04 21:26Z) · fees owner-confirmed
| Lane | Fee/mo | Quota window | $/B | Tokens 7d | tok/s | TTFT p50 |
|---|---|---|---|---|---|---|
| CommandCode - GOAT | $10.00/mo | monthly 44.5% | $1.60measured | 2.22B | 176measured | 2,507 msmeasured |
| OpenCode Go | $10.00/mo | monthly 99.0% | $2.74measured | 1.30B | 197measured | 1,509 msmeasured |
| Z.ai Coding Plan - Max (Legacy v2) | $56.00/mo | weekly 12.0% | $26.09*derived | 672M | 78measured | 4,213 msmeasured |
$/B is the plan fee over the tokens its binding quota window delivered, priced from my gateway's own logs. A lane with no readable window keeps its row and says why.
* derived: the plan publishes no monthly dollar allowance, so its $/B is derived from its quota window percentages.
CommandCode - GOAT
$10.00/mo5h 1.2% · weekly 19.1% · monthly 44.5% · resets 2026-11-21 15:49Z
- Capacity
- 6.25B per 30d · monthly window
- $/B
- $1.60
- Traffic, last 7 days
- 2.22B tokens · 10,603 requests · cache 96.4% · 7 days
- Speed
- 176 tok/s p50 · 2,507 ms TTFT p50 · 3,849 ms p90
| Model | Share | Tokens 7d | Requests | Cache | TTFT p50 | tok/s | Monthly limit |
|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 99.9% | 2.22B | 10,529 | 96.4% | 2,509 ms | 176 | $100.00/mo |
| Other models (13) | <0.1% | 1.5M | 74 | 50.7% | N/Apooled | N/Apooled | N/Apooled, under 1% each |
OpenCode Go
$10.00/mosingle_account_reading
5h 1.0% · weekly 11.0% · monthly 99.0% · resets 2026-11-19 00:27Z
- Capacity
- 3.65B per 30d · monthly window
- $/B
- $2.74
- Traffic, last 7 days
- 1.30B tokens · 8,342 requests · cache 98.1% · 7 days
- Speed
- 197 tok/s p50 · 1,509 ms TTFT p50 · 3,082 ms p90
| Model | Share | Tokens 7d | Requests | Cache | TTFT p50 | tok/s | Monthly limit |
|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 99.7% | 1.30B | 7,886 | 98.2% | 1,507 ms | 197 | $100.00/mo |
| Other models (5) | 0.3% | 3.7M | 456 | 52.7% | N/Apooled | N/Apooled | N/Apooled, under 1% each |
Z.ai Coding Plan - Max (Legacy v2)
$56.00/moweekly 12.0% · resets 2026-11-09 04:43Z
- Capacity
- 501M per 7d · weekly window
- $/B
- $26.09*
- Traffic, last 7 days
- 672M tokens · 4,813 requests · cache 95.2% · 7 days
- Speed
- 78 tok/s p50 · 4,213 ms TTFT p50 · 7,928 ms p90
| Model | Share | Tokens 7d | Requests | Cache | TTFT p50 | tok/s | Monthly limit |
|---|---|---|---|---|---|---|---|
| GLM-5.3 (no list price) | 92.4% | 621M | 3,847 | 97.6% | 4,140 ms | 80 | N/Ano per-model limit |
| GLM-5.3-Flash | 7.6% | 50.9M | 966 | 58.6% | 4,748 ms | 46 | N/Ano per-model limit |
Formulas, sources and limits: /methodology