Nova Micro vs GLM-4-32B-0414
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Amazon
|
by Z.AI
|
|---|---|---|
| Overview | ||
| Status | Current budget | Current budget Open weights |
| Released | Dec 3, 2024 | Apr 1, 2025 |
| Pricing per million tokens | ||
| Input | $0.035/Mtok | $0.100/Mtok |
| Output | $0.140/Mtok | $0.100/Mtok |
| Blended avg | $0.088/Mtok | $0.100/Mtok |
| Specifications | ||
| Context window | 128K tokens | 128K tokens |
| Parameters | Proprietary | 32B |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
text
|
| Benchmarks sources: Vellum LLM Leaderboard / LMSYS Chatbot Arena (UC Berkeley) | ||
| Avg benchmark score | 40 | — |
| Perf / dollar | 457.1 | — |
| GPQA Diamond | 40 | — |
| SWE-Bench Verified | 10 vendor | — |
| Humanity's Last Exam | 5 vendor | — |
| ARC-AGI 2 | 4 vendor | — |
| AIME 2025 | 20 vendor | — |
| MMMLU | 62 vendor | — |
| BFCL | 42 vendor | — |
| HumanEval | 68 vendor | — |
| MATH 500 | 42 vendor | — |
| Independent composite scores each on its own scale — not part of the average above | ||
| LMSYS Chatbot Arena | — | 1342.9 ELO |
| Providers | ||
| Available from |
Amazon — $0.035/$0.140/Mtok
|
Z.AI — $0.100/$0.100/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Nova Micro | GLM-4-32B-0414 | Savings |
|---|---|---|---|
| 1M tokens | $0.09 | $0.1 | $0.01 (10%) |
| 10M tokens | $0.88 | $1 | $0.12 (12%) |
| 100M tokens | $8.75 | $10 | $1.25 (12.5%) |
| 1000M tokens | $87.5 | $100 | $12.5 (12.5%) |
The cheaper option here — Nova Micro costs $0.088/Mtok blended on Amazon.
Summary
Nova Micro by Amazon costs $0.035/Mtok input and $0.140/Mtok output, with a 128K-token context window. It supports text input.
GLM-4-32B-0414 by Z.AI costs $0.100/Mtok input and $0.100/Mtok output, with a 128K-token context window. It supports text input.
On a blended cost basis, Nova Micro is 12.5% cheaper than GLM-4-32B-0414.
The two aren't directly comparable on average benchmark score: Nova Micro has published per-benchmark results, while GLM-4-32B-0414 does not yet — it is measured today on independent composites (see the table above).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.