OpenAI gpt-oss-20b vs PrismML Ternary Bonsai 2 9B
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- gpt-oss-20b is 2.6× cheaper at a typical mix of 3 input tokens per output token.
- Ternary Bonsai 2 9B accepts longer prompts: 262K vs 131K tokens.
- Ternary Bonsai 2 9B is the newer model (released 2026-10-16).
| gpt-oss-20b | Ternary Bonsai 2 9B | |
|---|---|---|
| Vendor | OpenAI | PrismML |
| Released | 2025-08-05 | 2026-10-16 |
| Input / 1M | $0.018 | $0.08 |
| Output / 1M | $0.09 | $0.13 |
| Cached input / 1M | $0.0090 | $0.04 |
| Blended / 1M (3:1) | $0.036 | $0.092 |
| Context | 131K | 262K |
| Max output | 33K | 66K |
| Accepts | text | text, image |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 10 | 1 |
| Cheapest provider, output | $0.09 | $0.13 |
| Best provider uptime, 24 h | 100% | 99.58% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | — |
Cost calculator
gpt-oss-20b
$2.43 per month$0.08 per day
Ternary Bonsai 2 9B
$6.75 per month$0.23 per day
gpt-oss-20b saves $4.32 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare gpt-oss-20b with
Compare Ternary Bonsai 2 9B with