gpt-oss-120b-fast vs Kimi-K2.5
gpt-oss-120b-fast is cheaper on output tokens, while Kimi-K2.5 offers a larger context window. Choose gpt-oss-120b-fast or Kimi-K2.5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | gpt-oss-120b-fast | Kimi-K2.5 |
|---|---|---|
| Provider | Nebius Token Factory | Nebius Token Factory |
| Input / 1M tokens | $0.10 | $0.50 |
| Output / 1M tokens | $0.50 | $2.50 |
| Context window | 8K | 256K |
| Parameters | — | 1T |
| Open weights | Yes | Yes |
| Released | Jun 2025 | Dec 2025 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.