← Compare models
Open all in the calculator — adjust volume and token counts →
GPT-5.4 Mini vs Skyfall 36B V2
List-price comparison ·GPT-5.4 Mini details ·Skyfall 36B V2 details
For a typical workload (100,000 requests / mo), Skyfall 36B V2 is the cheapest — 64% less than the priciest here ($98.00/mo vs $270.00/mo).
| GPT-5.4 Mini | Skyfall 36B V2 | |
|---|---|---|
| Input / 1M tokens | $0.750 | $0.550 |
| Output / 1M tokens | $4.50 | $0.800 |
| Typical request (1,200 in + 400 out) | $0.0027 | $0.001 |
| Context window | 400k tokens | 32,768 tokens |
| Max output | 128k tokens | 32,768 tokens |
| Quality score | 80/100 | 68/100 |
| Tier | Balanced | Balanced |
| Provider | OpenAI | TheDrummer |
Projected monthly cost
| Requests / mo | GPT-5.4 Mini | Skyfall 36B V2 |
|---|---|---|
| 1,000 | $2.70 | $0.98 |
| 10,000 | $27.00 | $9.80 |
| 100,000 | $270.00 | $98.00 |
GPT-5.4 Mini
Good default for everyday chat, summarization, and lightweight agent steps where GPT-5.4-level reasoning isn't required.
Quality gap widens on long, multi-hop reasoning tasks — needs careful prompt design to avoid silent failures on edge cases.
Skyfall 36B V2
Auto-synced from OpenRouter — no editorial write-up yet.
More comparisons
Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.