@@ -475,7 +475,33 @@ public enum ChatModel implements ChatModelDescription {
475
475
* Context window: 4,096 tokens. Max output tokens: 4,096 tokens. Knowledge
476
476
* cutoff: September, 2021.
477
477
*/
478
- GPT_3_5_TURBO_INSTRUCT ("gpt-3.5-turbo-instruct" );
478
+ GPT_3_5_TURBO_INSTRUCT ("gpt-3.5-turbo-instruct" ),
479
+
480
+ /**
481
+ * <b>GPT-4.1</b> is the flagship model for complex tasks. It is well suited for
482
+ * problem solving across domains.
483
+ * <p>
484
+ * Context window: 1,047,576 tokens. Max output tokens: 32,768 tokens. Knowledge
485
+ * cutoff: June 1, 2024.
486
+ */
487
+ GPT_4_1 ("gpt-4.1" ),
488
+
489
+ /**
490
+ * <b>GPT-4.1-mini</b> provides a balance between intelligence, speed, and cost
491
+ * that makes it an attractive model for many use cases.
492
+ * <p>
493
+ * Context window: 1,047,576 tokens. Max output tokens: 32,768 tokens. Knowledge
494
+ * cutoff: June 1, 2024.
495
+ */
496
+ GPT_4_1_MINI ("gpt-4.1-mini" ),
497
+
498
+ /**
499
+ * <b>GPT-4.1-nano</b> is the fastest, most cost-effective GPT-4.1 model.
500
+ * <p>
501
+ * Context window: 1,047,576 tokens. Max output tokens: 32,768 tokens. Knowledge
502
+ * cutoff: June 1, 2024.
503
+ */
504
+ GPT_4_1_NANO ("gpt-4.1-nano" );
479
505
480
506
public final String value ;
481
507
0 commit comments