GPT-5.6 Luna is designed for high concurrency and low-cost scenarios, making it the ultimate choice for cost-effectiveness. Its performance is comparable to the nano model tier in the early GPT-5 series, making it suitable for large-scale, lightweight task processing.
Different token groups have different prices. Unit: Million tokens (M)
| Token Group | Description | Group Ratio | Input Price | Output Price | Cache Read | Cache write |
|---|---|---|---|---|---|---|
| codex | 包含gpt5+和codex（来自codex） | 0.35x | $0.07/M | $0.42/M | $0.007/M | $0.087/M |
| default | 通用渠道（全站大部分模型可用） | 1x | $0.2/M | $1.2/M | $0.02/M | $0.25/M |
When a token condition is met, the request uses that tier's prices
| Condition | Input Price | Output Price | Cache Read | Cache write |
|---|---|---|---|---|
| Input tokens > 272K | $0.14/M | $0.63/M | $0.014/M | $0.175/M |