Capacity from model allowance / month Free option
- CP value
- No data
- Equivalent cost / 1M
- No data
- Model allowance (theoretical)
- Free / not metered
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
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 Zen Nemotron 3.5 Lightning Free |
|---|---|
| Input / 1M | No data |
| Cache read / 1M | No data |
| Output / 1M | No data |
| Cache write / 1M | No data |
| Cost / request Recalculated | No data12,000 tokens/request |
| Model allowance Published | Free / not meteredBased on this model’s plan allowance |
| Requests / month Recalculated | Free / not meteredFree option; see usage conditions |
| 5-hour limit Published | —Plan window |
| Weekly limit Published | —Plan window |
| Monthly limit Published | —Plan window |
03Official reference rows
The official reference behind each plan
Compare each provider’s reference token mix and published estimates below.
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 | No data |
| Model monthly allowance | Free / not metered |
| 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.
intelligence23.6Intelligence rank: 246
coding26.8Coding rank: 170
agentic13.8Agentic rank: 144
Score inherited from Nemotron 3.5 Lightning
Scores describe the model’s performance on the named benchmarks. Results on your own tasks also depend on tools, prompts and execution environment.
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.
OpenCode Zen: An NVIDIA free endpoint for trial use only; do not submit personal or confidential data, and your use is logged and used to improve NVIDIA products.