OpenAI: gpt-oss-120b vs ScaleDown: Summarize
On input price, ScaleDown: Summarize is ~3.8× cheaper. Verified 2026-10-21.
OpenAI: gpt-oss-120b $0.150/$0.600vsScaleDown: Summarize $0.040/Free
Verdict
On blended price (3:1 input:output), ScaleDown: Summarize is ~8.7× cheaper ($0.040/Free vs $0.150/$0.600 per 1M tokens).
Pricing
Per-million-token list prices, verified 2026-10-21. Green marks the better value.
| Metric | OpenAI: gpt-oss-120b | ScaleDown: Summarize |
|---|---|---|
| Input / 1M | $0.150 | $0.040 |
| Output / 1M | $0.600 | Free |
| Cache read / 1M | $0.075 | — |
| Blended (3:1) | $0.262/1M | $0.030/1M |
| Estimated monthly cost | OpenAI: gpt-oss-120b | ScaleDown: Summarize |
|---|---|---|
| Chatbot10,000 reqs · 800/400 tok | $3.60 | $0.32 |
| Coding agent5,000 reqs · 8000/2000 tok | $12.00 | $1.60 |
| RAG pipeline30,000 reqs · 4000/500 tok | $27.00 | $4.80 |
Plug in your own numbers in the calculator, or paste a real bill into the Bill Shredder.
Specifications & capabilities
| Metric | OpenAI: gpt-oss-120b | ScaleDown: Summarize |
|---|---|---|
| Context window | 131K | 1M |
| Max output | 66K | 4K |
| Vision input | – | ✓ |
| Tool calling | ✓ | – |
| Reasoning | ✓ | – |
Quality
Intelligence Index by Artificial Analysis (independent evaluations, 0–100).
Verified intelligence scores aren't available for both models yet. See the full leaderboard.
Provider
Infrastructure metrics for the organizations behind these models.
| Metric | OpenAI | scaledown |
|---|---|---|
| Listed endpoints | 12 | — |
| Reliability | 99.9% | — |
| Avg latency | 450 ms | — |
| Pricing tiers | standard, batch, provisioned | — |
Full details: OpenAI: gpt-oss-120b pricing · ScaleDown: Summarize pricing