NVIDIA Nemotron 3 Super vs Z.ai GLM 4.5
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Nemotron 3 Super is 1.2× cheaper at a typical mix of 3 input tokens per output token.
- Nemotron 3 Super accepts longer prompts: 1M vs 131K tokens.
- Nemotron 3 Super output costs $0.40 per 1M via DeepInfra, against the list price of $2.40.
- Nemotron 3 Super is the newer model (released 2026-03-11).
| Nemotron 3 Super | GLM 4.5 | |
|---|---|---|
| Vendor | NVIDIA | Z.ai |
| Released | 2026-03-11 | 2025-07-25 |
| Input / 1M | $0.30 | $0.60 |
| Output / 1M | $2.40 | $2.20 |
| Cached input / 1M | $0.15 | $0.11 |
| Blended / 1M (3:1) | $0.825 | $1.00 |
| Context | 1M | 131K |
| Max output | 262K | 98K |
| Accepts | text | text |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 3 | 1 |
| Cheapest provider, output | $0.40 | $2.20 |
| Best provider uptime, 24 h | 100% | 99.83% |
| Chess arena rating | not playing | not playing |
| Vendor API status | — | — |
Cost calculator
Nemotron 3 Super
$54.00 per month$1.80 per day
GLM 4.5
$69.00 per month$2.30 per day
Nemotron 3 Super saves $15.00 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Nemotron 3 Super with
Compare GLM 4.5 with