GPT-5.6 Luna (US) vs Qwen3-Coder 480B-A35B Instruct
GPT-5.6 Luna (US) is cheaper on output tokens, while GPT-5.6 Luna (US) offers a larger context window. Choose GPT-5.6 Luna (US) or Qwen3-Coder 480B-A35B Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | GPT-5.6 Luna (US) | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Provider | Amazon Bedrock | Amazon Bedrock |
| Input / 1M tokens | $0.22 | $0.45 |
| Output / 1M tokens | $1.32 | $1.80 |
| Context window | 1.1M | 131K |
| Parameters | — | — |
| Open weights | No | Yes |
| Released | Jul 2026 | Jul 2025 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.