Capacity from model allowance / month 24.0M tokens
- CP value
- 0.5
- Equivalent cost / 1M
- $1.25
- Model allowance (theoretical)
- $30
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
Capacity from model allowance / month 26.4M tokens
- CP value
- 0.5
- Equivalent cost / 1M
- $1.25
- Model allowance (theoretical)
- $33
Cost per 1M token-equivalent $1.25
- CP value
- 0.5
- Equivalent cost / 1M
- $1.25
- Model allowance (theoretical)
- Pay as you go
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 | OpenCode Go Qwen3.7 Max | Command Code GOAT Qwen 3.7 Max | OpenCode Zen Qwen3.7 Max |
|---|---|---|---|
| Input / 1M | $2.50 | $2.50 | $2.50 |
| Cache read / 1M | $0.50 | $0.50 | $0.50 |
| Output / 1M | $7.50 | $7.50 | $7.50 |
| Cache write / 1M | $3.13 | $3.13 | $3.13 |
| Cost / request Recalculated | $0.01500012,000 tokens/request | $0.01500012,000 tokens/request | $0.01500012,000 tokens/request |
| Model allowance Published | $30Based on this model’s plan allowance | $33Based on this model’s plan allowance | Pay as you goNo plan allowance; billed per request |
| Requests / month Recalculated | 2,000Estimated with the 12,000-token workload above | 2,200Estimated with the 12,000-token workload above | Pay as you goNo plan allowance; compare its rates instead |
| 5-hour limit Published | $12Plan window | $14Plan window | —Pay as you go |
| Weekly limit Published | $30Plan window | $35Plan window | —Pay as you go |
| Monthly limit Published | $60Plan window | $70Plan window | —Pay as you go |
03Official reference rows
The official reference behind each plan
Compare each provider’s reference token mix and published estimates below.
OpenCode Go View the provider’s reference workload
| Reference input / request | 420 |
|---|---|
| Reference cache read / request | 66,000 |
| Reference output / request | 200 |
| Reference cache write / request | 0 |
| Reference volume / request | 66,620 |
| Cost per request | $0.035550 |
| Model monthly allowance | $30 |
| Published requests / month | 840 |
| Published capacity / month | 56.0M |
| Capacity basis | Based on the published request estimate |
Calculation
Cost per request = add the four token classes after multiplying each by its price per 1,000,000 tokens.
floor($30 ÷ $0.035550) = 843
Official source: OpenCode Go · Snapshot captured: 2026-09-06
Command Code GOAT View the provider’s reference workload
| 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 | $0.028500 |
| Model monthly allowance | $33 |
| Published requests / month | 1,160 |
| Published capacity / month | 59.2M |
| Capacity basis | Based on the published request estimate |
Calculation
Cost per request = add the four token classes after multiplying each by its price per 1,000,000 tokens.
floor($33 ÷ $0.028500) = 1,157
Official source: Command Code GOAT · Snapshot captured: 2026-09-06
OpenCode Zen View the provider’s reference workload
| Reference input / request | 1,000 |
|---|---|
| Reference cache read / request | 10,000 |
| Reference output / request | 1,000 |
| Reference cache write / request | 0 |
| Reference volume / request | 12,000 |
| Cost per request | $0.015000 |
| Model monthly allowance | Pay as you go |
| Capacity basis | No published reference profile; the site common workload is used instead |
Official source: OpenCode Zen · Snapshot captured: 2026-09-06
04Artificial Analysis external scores
External benchmarks with their source version
Benchmarks are from Artificial Analysis. See the source version and matched model below.
intelligence46.7Intelligence rank: 71
coding66.0Coding rank: 65
agentic30.9Agentic rank: 92
Scores describe the model’s performance on the named benchmarks. Results on your own tasks also depend on tools, prompts and execution environment.