Nova Micro vs Hy-MT2 1.8B
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Amazon
|
by Tencent
|
|---|---|---|
| Overview | ||
| Status | Current budget | Current budget Open weights |
| Released | Dec 3, 2024 | May 21, 2026 |
| Pricing per million tokens | ||
| Input | $0.035/Mtok | $0.044/Mtok |
| Output | $0.140/Mtok | $0.177/Mtok |
| Blended avg | $0.061/Mtok | $0.077/Mtok |
| Price basis | — | Tencent's own price, quoted by the FP8 endpoint Tencent operates for this model. Tencent's RMB rate card carries the matching row — Hy-MT2-Lite at ¥0.3 in / ¥1.2 out per 1M tokens, the only row on that card that converts to these figures — at 6.78 CNY/USD. Tencent publishes no cached-input rate for this family. |
| Specifications | ||
| Context window | 128K tokens | 8K tokens |
| Parameters | Proprietary | 1.8B |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
text
|
| Benchmarks sources: Vellum LLM Leaderboard / public leaderboards | ||
| Avg benchmark score | 40 | — |
| Perf / dollar | 653.1 | — |
| 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 | — |
| Providers | ||
| Available from |
Amazon — $0.035/$0.140/Mtok
|
Tencent — $0.044/$0.177/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Nova Micro | Hy-MT2 1.8B | Savings |
|---|---|---|---|
| 1M tokens | $0.06 | $0.08 | $0.02 (25.9%) |
| 10M tokens | $0.61 | $0.77 | $0.16 (20.7%) |
| 100M tokens | $6.13 | $7.73 | $1.6 (20.7%) |
| 1000M tokens | $61.25 | $77.25 | $16 (20.7%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.061/Mtok blended vs $0.077 — 20.7% less on the same 50/50 token mix
- you need the longer context: 128K tokens vs 8K (15.6×)
- you want open weights — self-host it, fine-tune it, or exit the API entirely; Nova Micro is closed
The cheaper option here — Nova Micro costs $0.061/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.
Hy-MT2 1.8B by Tencent costs $0.044/Mtok input and $0.177/Mtok output, with a 8K-token context window. It supports text input.
On a blended cost basis, Nova Micro is 20.7% cheaper than Hy-MT2 1.8B.It also has a larger context window.
The two aren't directly comparable on average benchmark score: Nova Micro has published per-benchmark results, while Hy-MT2 1.8B does not yet.
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.