o3-mini is our newest small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. It supports Structured Outputs, Function Calling, and the Batch API.
个token
个token
最后更新
综合评级
| 类型 | 价格 | 单位 | Context Type |
|---|---|---|---|
Input | $1.100000 | per mtokens | Standard |
Output | $4.400000 | per mtokens | Standard |
Cached Input | $0.550000 | per mtokens | Standard Reduced cost for cached input |
| 类型 | 价格 | 单位 | Context Type | Savings |
|---|---|---|---|---|
| Input | $0.550000 | per mtokens | Standard | |
| Output | $2.200000 | per mtokens | Standard |
| 等级 | RPM | TPM | Additional Limits |
|---|---|---|---|
| tier_1 | 1,000 | 100000 | Queue:1,000,000 requests |
| tier_2 | 2,000 | 200000 | Queue:2,000,000 requests |
| tier_3 | 5,000 | 4000000 | Queue:40,000,000 requests |
| tier_4 | 10,000 | 10000000 | Queue:1,000,000,000 requests |
| tier_5 | 30,000 | 150000000 | Queue:15,000,000,000 requests |
