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 |
|---|---|---|---|---|---|
| codex | 包含gpt5+和codex（来自codex） | 0.5x | $0.5/M | $3/M | $0.05/M |
| default | 通用渠道（全站大部分模型可用） | 1x | $1/M | $6/M | $0.1/M |
When a token condition is met, the request uses that tier's prices
| Condition | Input Price | Output Price | Cache Read |
|---|---|---|---|
| Input tokens > 272K | $1/M | $4.5/M | $0.1/M |