GPT-5.6 Luna (Azure) vs Qwen3.8 27B (reka-ai)
GPT-5.6 Luna (Azure) is cheaper on output tokens, while GPT-5.6 Luna (Azure) offers a larger context window. Choose GPT-5.6 Luna (Azure) or Qwen3.8 27B (reka-ai) based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | GPT-5.6 Luna (Azure) | Qwen3.8 27B (reka-ai) |
|---|---|---|
| Provider | LLM Gateway | LLM Gateway |
| Input / 1M tokens | $0.20 | $0.41 |
| Output / 1M tokens | $1.20 | $3.00 |
| Context window | 1.1M | 262K |
| Parameters | — | — |
| Open weights | No | Yes |
| Released | Jul 2026 | Aug 2026 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.