gpt-oss-20b (batch) vs Llama-3.2-1B
Llama-3.2-1B is cheaper on output tokens. Choose gpt-oss-20b (batch) or Llama-3.2-1B based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | gpt-oss-20b (batch) | Llama-3.2-1B |
|---|---|---|
| Provider | OpenAI | Pioneer |
| Input / 1M tokens | $0.02 | $0.10 |
| Output / 1M tokens | $0.11 | $0.10 |
| Context window | 131K | 131K |
| Parameters | 21B | — |
| Open weights | Yes | Yes |
| Released | Aug 2025 | Sep 2024 |
| LMArena (Chatbot Arena) Elo score | 1287 | — |
| GPQA Diamond score | 60.8 | — |
| Epoch Capabilities Index score | 138 | 102 |
FAQ
Is gpt-oss-20b (batch) or Llama-3.2-1B cheaper?
Llama-3.2-1B is cheaper on output tokens ($0.10 vs $0.11 per 1M).
Which has the larger context window, gpt-oss-20b (batch) or Llama-3.2-1B?
Both models offer a similar context window.
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.