Qwen: Qwen3.6 35B A3B vs ScaleDown: Summarize
On input price, ScaleDown: Summarize is ~2.5× cheaper. Verified 2026-10-21.
Qwen: Qwen3.6 35B A3B $0.100/$0.950vsScaleDown: Summarize $0.040/Free
Verdict
On blended price (3:1 input:output), ScaleDown: Summarize is ~10.4× cheaper ($0.040/Free vs $0.100/$0.950 per 1M tokens).
Pricing
Per-million-token list prices, verified 2026-10-21. Green marks the better value.
| Metric | Qwen: Qwen3.6 35B A3B | ScaleDown: Summarize |
|---|---|---|
| Input / 1M | $0.100 | $0.040 |
| Output / 1M | $0.950 | Free |
| Cache read / 1M | $0.050 | — |
| Blended (3:1) | $0.313/1M | $0.030/1M |
| Estimated monthly cost | Qwen: Qwen3.6 35B A3B | ScaleDown: Summarize |
|---|---|---|
| Chatbot10,000 reqs · 800/400 tok | $4.60 | $0.32 |
| Coding agent5,000 reqs · 8000/2000 tok | $13.50 | $1.60 |
| RAG pipeline30,000 reqs · 4000/500 tok | $26.25 | $4.80 |
Plug in your own numbers in the calculator, or paste a real bill into the Bill Shredder.
Specifications & capabilities
| Metric | Qwen: Qwen3.6 35B A3B | ScaleDown: Summarize |
|---|---|---|
| Context window | 262K | 1M |
| Max output | 236K | 4K |
| Vision input | ✓ | ✓ |
| Tool calling | ✓ | – |
| Reasoning | ✓ | – |
Provider
Infrastructure metrics for the organizations behind these models.
| Metric | Qwen (Alibaba) | scaledown |
|---|---|---|
| Listed endpoints | 18 | — |
| Reliability | 99.3% | — |
| Avg latency | 450 ms | — |
| Pricing tiers | standard, free | — |
Full details: Qwen: Qwen3.6 35B A3B pricing · ScaleDown: Summarize pricing