Hy-MT2-30B-A3B is $4.93 cheaper per 1M input tokens (98.5% lower; 67.6x difference).
API cost decision in 10 seconds
NewHy-MT2-30B-A3B vs Fugu Ultra
Pick Hy-MT2-30B-A3B for lower cost; pick Fugu Ultra only if the larger context window matters more.
Page updated:
Data confirmed:
Prices normalized to USD per 1M tokens
Sample workload: 1M input + 500K output
Budget verdict
Pick Hy-MT2-30B-A3B for lower cost; pick Fugu Ultra only if the larger context window matters more.
On the standard 1M input plus 500K output workload, Hy-MT2-30B-A3B is estimated at $0.22 vs $20 for Fugu Ultra, saving $19.78 (98.9% lower).
Cost-first pickHy-MT2-30B-A3B
Context-first pickFugu Ultra
Sample savings$19.7898.9%
10x traffic gap$197.79
Fugu Ultra has more context, but Hy-MT2-30B-A3B saves $19.78 on the standard workload. At 10x that traffic, the same price gap is about $197.79. Use the calculator below to replace the sample workload with your own token volume.
Cost sensitivity
Workload Sensitivity
Hy-MT2-30B-A3B stays cheaper across input-heavy, balanced, and output-heavy sample workloads.
| Workload shape | Token mix | Better pick | Hy-MT2-30B-A3B | Fugu Ultra |
|---|---|---|---|---|
| Input-heavy / RAG | 5M input + 500K output | Hy-MT2-30B-A3B | $0.52 | $40 |
| Balanced workload | 1M input + 1M output | Hy-MT2-30B-A3B | $0.37 | $35 |
| Output-heavy chatbot | 1M input + 5M output | Hy-MT2-30B-A3B | $1.55 | $155 |
Hy-MT2-30B-A3B is $29.7 cheaper per 1M output tokens (99% lower; 101.7x difference).
Fugu Ultra has 991.81K more context (122.1x larger).
Hy-MT2-30B-A3B is $19.78 cheaper on the standard workload (98.9% lower).
Estimate your workload cost
Your Workload Cost
This estimate uses normalized public API pricing per 1M tokens. It is a planning aid, not a billing quote. Verify provider pricing, limits, and terms before production use.
Quick Decision
Hy-MT2-30B-A3B has the lower input price; Hy-MT2-30B-A3B has the lower output price; Fugu Ultra offers the larger context window. For the 1M input plus 500K output sample, Hy-MT2-30B-A3B is cheaper for the standard workload.
For a 1M input token plus 500K output token workload, the estimated API cost is $0.22 for Hy-MT2-30B-A3B and $20 for Fugu Ultra.
Choose Hy-MT2-30B-A3B when you care most about lower input-token price, and lower output-token price.
Choose Fugu Ultra when you care most about larger context window.
- On the standard 1M input plus 500K output workload, Hy-MT2-30B-A3B is estimated at $0.22 vs $20 for Fugu Ultra, saving $19.78 (98.9% lower).
- Hy-MT2-30B-A3B is $19.78 cheaper on the standard workload (98.9% lower).
- Hy-MT2-30B-A3B is $4.93 cheaper per 1M input tokens (98.5% lower; 67.6x difference).
- Hy-MT2-30B-A3B is $29.7 cheaper per 1M output tokens (99% lower; 101.7x difference).
- Fugu Ultra has 991.81K more context (122.1x larger).
| Feature | NewHy-MT2-30B-A3B (Tencent) | Fugu Ultra (Sakana) |
|---|---|---|
| Input Price prompt tokens per 1M | $0.074 | $5 |
| Completion Price per 1M tokens | $0.295 | $30 |
| Sample Workload Cost 1M input + 500K output | $0.22 | $20 |
| Context Window | 8.19K | 1M |
| Release Date |
Use-Case Decision Matrix
| Use case | Better pick | Why |
|---|---|---|
| Budget-constrained production | Hy-MT2-30B-A3B | On the standard 1M input plus 500K output workload, Hy-MT2-30B-A3B is estimated at $0.22 vs $20 for Fugu Ultra, saving $19.78 (98.9% lower). |
| High-volume input processing | Hy-MT2-30B-A3B | Lower prompt-token price matters most when prompts, retrieved passages, or documents dominate the bill. |
| Long responses and chatbots | Hy-MT2-30B-A3B | Lower output-token price matters most when assistants generate many completion tokens. |
| RAG or long-document work | Fugu Ultra | A larger context window leaves more room for retrieved passages, conversation history, or source files. |
Related Alternatives
- Hy3 (free) can replace Hy-MT2-30B-A3B when lower sample workload cost matters most: $0.
- Hy-MT2-1.8B can replace Hy-MT2-30B-A3B when lower sample workload cost matters most: $0.13.
- Sakana Namazu can replace Fugu Ultra when lower sample workload cost matters most: $2.95.
- Grok 4.20 Multi-Agent offers 2M context with $2.5 sample workload cost.
- Grok 4.20 offers 2M context with $2.5 sample workload cost.
- DeepSeek V4 Flash 0731 offers 1.31M context with $0.17 sample workload cost.
- DeepSeek V4 Flash Latest offers 1.31M context with $0.11 sample workload cost.
- DeepSeek V4 Flash 0731 · DeepSeek · #1
- MiMo-V2.5 · Xiaomi · #2
- Hy3 · Tencent · #3
- Ox Alpha · stealth · #4
Cheaper alternatives
Review low-cost models sorted by a standard 1M input plus 500K output workload.
Open cheapest modelsLarger context alternatives
Find models with larger context windows for RAG, long documents, and codebase review.
Open largest context modelsProvider catalogs
Compare models within provider hubs before choosing a final API vendor.
Open provider hubsTencent catalog
Review all tracked Tencent models before deciding whether this matchup is the right shortlist.
Open Tencent modelsSakana catalog
Check other Sakana models with comparable pricing, context, or release timing.
Open Sakana modelsHy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...
Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...