A fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.
Different token groups have different prices. Unit: Million tokens (M)
| Token Group | Group Ratio | Input Price | Output Price | Cache Read | Cache write |
|---|---|---|---|---|---|
| default 通用渠道（全站大部分模型可用） | 1x | $1/M | $5/M | $0.05/M | $1.25/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 | $2/M | $7.5/M | $0.1/M | $2.5/M |
Requests with a service_tier are billed at the matching price, per million tokens (M)
| service_tier | Input Price | Output Price | Cache Read | Cache write |
|---|---|---|---|---|
| fast | $2/M | $10/M | $0.1/M | $2.5/M |