Nova Premier 1.0 vs GLM 5.2: pricing comparison
GLM 5.2 is the cheaper option at $0.01/$6.80 per 1M input/output tokens — Nova Premier 1.0 ($2.50/$12.50) costs about 357x more per input token. Full spec-by-spec breakdown below.
| Nova Premier 1.0 | GLM 5.2 | |
|---|---|---|
| Input /1M tokens | $2.50 | $0.01 |
| Output /1M tokens | $12.50 | $6.80 |
| Cache read /1M | $0.63 | $0.01 |
| Context window | 1M | 1.0M |
| Provider | Amazon | Z-ai |
| Vision input | Yes | No |
| Released | Oct 2025 | Jun 2026 |
Real workload costs: Nova Premier 1.0 vs GLM 5.2
Cost per single request at common token profiles — the cheapest model for each workload is highlighted.
| Workload | Tokens (in / out) | Nova Premier 1.0 | GLM 5.2 |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0050 | $0.0020 |
| RAG query with context | 4,000 / 500 | $0.02 | $0.0034 |
| Document summarization | 20,000 / 1,000 | $0.06 | $0.0069 |
| Agent coding session | 100,000 / 5,000 | $0.31 | $0.03 |
Frequently asked questions
Which is cheaper: Nova Premier 1.0 vs GLM 5.2?
GLM 5.2 is the cheapest on input tokens at $0.01 per 1M, and GLM 5.2 is cheapest on output at $6.80 per 1M. Nova Premier 1.0 costs about 357x more per input token than GLM 5.2.
How much does Nova Premier 1.0 cost per 1M tokens?
Nova Premier 1.0 costs $2.50 per 1M input tokens and $12.50 per 1M output tokens on the Amazon API, with a 1M-token context window.
How much does GLM 5.2 cost per 1M tokens?
GLM 5.2 costs $0.01 per 1M input tokens and $6.80 per 1M output tokens on the Z-ai API, with a 1.0M-token context window.
What does a typical request cost on Nova Premier 1.0 vs GLM 5.2?
For a typical request with 2,000 input and 500 output tokens: Nova Premier 1.0 costs $0.01, GLM 5.2 costs $0.0034. At 1,000 requests/day for a month that is $338 for Nova Premier 1.0 vs $102 for GLM 5.2.
Estimate your own workload with the per-model calculators (Nova Premier 1.0, GLM 5.2), browse all current prices on the live model pricing dashboard, or run these models head-to-head on a real prompt (free account required). Prices may differ from provider list prices for batch or tiered usage.
Pricing data via the OpenRouter models API.