GPT OSS 20B is cheaper than Gemini 2.5 Pro Preview 06-05 at $0.02/M vs $1.25/M input tokens.
| Spec | Gemini 2.5 Pro Preview 06-05 | GPT OSS 20B |
|---|---|---|
| Input price | $1.25/M tokens | $0.02/M tokens |
| Output price | $10/M tokens | $0.1/M tokens |
| Context window | 1.0M tokens | 131K tokens |
| Parameters | Not disclosed | 21B (3.6B active) |
| Weights | Closed | Open |
| Free API (OpenRouter) | No | No |
| Released | Jun 2025 | Aug 2025 |
Not enough votes to call it. On the specs, Gemini 2.5 Pro Preview 06-05 has the edge: bigger model tier, bigger context window.
GPT OSS 20B costs 100x less per token.
Reviewing agent-written code?See a Brief PR report
GPT OSS 20B is cheaper on both: 63× input, 100× output.
Per million tokens. Prices and uptime via OpenRouter, checked 13 Sep 2026.
GPT OSS 20B uses 10.2x more emoji