Previous full o-series reasoning model. Trained with reinforcement learning for complex reasoning; the model “thinks before it answers”, producing an internal chain of thought.
トークン
トークン
最終更新
総合評価
| タイプ | 価格 | 単位 | Context Type |
|---|---|---|---|
Input | $15.000000 | per mtokens | Standard |
Output | $60.000000 | per mtokens | Standard |
Cached Input | $7.500000 | per mtokens | Standard Reduced cost for cached input |
| タイプ | 価格 | 単位 | Context Type | Savings |
|---|---|---|---|---|
| Input | $7.500000 | per mtokens | Standard | |
| Output | $30.000000 | per mtokens | Standard |
| 階層 | RPM | TPM | Additional Limits |
|---|---|---|---|
| tier_1 | 500 | 30000 | Queue:90,000 requests |
| tier_2 | 5,000 | 450000 | Queue:1,350,000 requests |
| tier_3 | 5,000 | 800000 | Queue:50,000,000 requests |
| tier_4 | 10,000 | 2000000 | Queue:200,000,000 requests |
| tier_5 | 10,000 | 30000000 | Queue:5,000,000,000 requests |
