@dreb/ai 2.64.5 → 2.65.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -13,11 +13,11 @@ export const MODELS = {
13
13
  cost: {
14
14
  input: 0.33,
15
15
  output: 2.75,
16
- cacheRead: 0,
17
- cacheWrite: 0,
16
+ cacheRead: 0.0825,
17
+ cacheWrite: 0.33,
18
18
  },
19
- contextWindow: 128000,
20
- maxTokens: 4096,
19
+ contextWindow: 1000000,
20
+ maxTokens: 65535,
21
21
  },
22
22
  "amazon.nova-lite-v1:0": {
23
23
  id: "amazon.nova-lite-v1:0",
@@ -31,10 +31,10 @@ export const MODELS = {
31
31
  input: 0.06,
32
32
  output: 0.24,
33
33
  cacheRead: 0.015,
34
- cacheWrite: 0,
34
+ cacheWrite: 0.06,
35
35
  },
36
36
  contextWindow: 300000,
37
- maxTokens: 8192,
37
+ maxTokens: 10000,
38
38
  },
39
39
  "amazon.nova-micro-v1:0": {
40
40
  id: "amazon.nova-micro-v1:0",
@@ -48,10 +48,10 @@ export const MODELS = {
48
48
  input: 0.035,
49
49
  output: 0.14,
50
50
  cacheRead: 0.00875,
51
- cacheWrite: 0,
51
+ cacheWrite: 0.035,
52
52
  },
53
53
  contextWindow: 128000,
54
- maxTokens: 8192,
54
+ maxTokens: 10000,
55
55
  },
56
56
  "amazon.nova-pro-v1:0": {
57
57
  id: "amazon.nova-pro-v1:0",
@@ -65,10 +65,10 @@ export const MODELS = {
65
65
  input: 0.8,
66
66
  output: 3.2,
67
67
  cacheRead: 0.2,
68
- cacheWrite: 0,
68
+ cacheWrite: 0.8,
69
69
  },
70
70
  contextWindow: 300000,
71
- maxTokens: 8192,
71
+ maxTokens: 10000,
72
72
  },
73
73
  "anthropic.claude-fable-5": {
74
74
  id: "anthropic.claude-fable-5",
@@ -274,6 +274,57 @@ export const MODELS = {
274
274
  contextWindow: 1000000,
275
275
  maxTokens: 128000,
276
276
  },
277
+ "apac.amazon.nova-lite-v1:0": {
278
+ id: "apac.amazon.nova-lite-v1:0",
279
+ name: "Nova Lite (APAC)",
280
+ api: "bedrock-converse-stream",
281
+ provider: "amazon-bedrock",
282
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
283
+ reasoning: false,
284
+ input: ["text", "image"],
285
+ cost: {
286
+ input: 0.063,
287
+ output: 0.252,
288
+ cacheRead: 0.01575,
289
+ cacheWrite: 0.063,
290
+ },
291
+ contextWindow: 300000,
292
+ maxTokens: 10000,
293
+ },
294
+ "apac.amazon.nova-micro-v1:0": {
295
+ id: "apac.amazon.nova-micro-v1:0",
296
+ name: "Nova Micro (APAC)",
297
+ api: "bedrock-converse-stream",
298
+ provider: "amazon-bedrock",
299
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
300
+ reasoning: false,
301
+ input: ["text"],
302
+ cost: {
303
+ input: 0.037,
304
+ output: 0.148,
305
+ cacheRead: 0.00925,
306
+ cacheWrite: 0.037,
307
+ },
308
+ contextWindow: 128000,
309
+ maxTokens: 10000,
310
+ },
311
+ "apac.amazon.nova-pro-v1:0": {
312
+ id: "apac.amazon.nova-pro-v1:0",
313
+ name: "Nova Pro (APAC)",
314
+ api: "bedrock-converse-stream",
315
+ provider: "amazon-bedrock",
316
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
317
+ reasoning: false,
318
+ input: ["text", "image"],
319
+ cost: {
320
+ input: 0.84,
321
+ output: 3.36,
322
+ cacheRead: 0.21,
323
+ cacheWrite: 0.84,
324
+ },
325
+ contextWindow: 300000,
326
+ maxTokens: 10000,
327
+ },
277
328
  "au.anthropic.claude-haiku-4-5-20251001-v1:0": {
278
329
  id: "au.anthropic.claude-haiku-4-5-20251001-v1:0",
279
330
  name: "Claude Haiku 4.5 (AU)",
@@ -308,6 +359,23 @@ export const MODELS = {
308
359
  contextWindow: 1000000,
309
360
  maxTokens: 128000,
310
361
  },
362
+ "au.anthropic.claude-opus-4-7": {
363
+ id: "au.anthropic.claude-opus-4-7",
364
+ name: "Claude Opus 4.7 (AU)",
365
+ api: "bedrock-converse-stream",
366
+ provider: "amazon-bedrock",
367
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
368
+ reasoning: true,
369
+ input: ["text", "image"],
370
+ cost: {
371
+ input: 5.5,
372
+ output: 27.5,
373
+ cacheRead: 0.55,
374
+ cacheWrite: 6.875,
375
+ },
376
+ contextWindow: 1000000,
377
+ maxTokens: 128000,
378
+ },
311
379
  "au.anthropic.claude-opus-4-8": {
312
380
  id: "au.anthropic.claude-opus-4-8",
313
381
  name: "Claude Opus 4.8 (AU)",
@@ -393,22 +461,22 @@ export const MODELS = {
393
461
  contextWindow: 1000000,
394
462
  maxTokens: 128000,
395
463
  },
396
- "deepseek.r1-v1:0": {
397
- id: "deepseek.r1-v1:0",
398
- name: "DeepSeek-R1",
464
+ "ca.amazon.nova-lite-v1:0": {
465
+ id: "ca.amazon.nova-lite-v1:0",
466
+ name: "Nova Lite (CA)",
399
467
  api: "bedrock-converse-stream",
400
468
  provider: "amazon-bedrock",
401
469
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
402
- reasoning: true,
403
- input: ["text"],
470
+ reasoning: false,
471
+ input: ["text", "image"],
404
472
  cost: {
405
- input: 1.35,
406
- output: 5.4,
407
- cacheRead: 0,
408
- cacheWrite: 0,
473
+ input: 0.064,
474
+ output: 0.256,
475
+ cacheRead: 0.016,
476
+ cacheWrite: 0.064,
409
477
  },
410
- contextWindow: 128000,
411
- maxTokens: 32768,
478
+ contextWindow: 300000,
479
+ maxTokens: 10000,
412
480
  },
413
481
  "deepseek.v3-v1:0": {
414
482
  id: "deepseek.v3-v1:0",
@@ -429,7 +497,7 @@ export const MODELS = {
429
497
  },
430
498
  "deepseek.v3.2": {
431
499
  id: "deepseek.v3.2",
432
- name: "DeepSeek-V3.2",
500
+ name: "DeepSeek V3.2",
433
501
  api: "bedrock-converse-stream",
434
502
  provider: "amazon-bedrock",
435
503
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -444,6 +512,74 @@ export const MODELS = {
444
512
  contextWindow: 163840,
445
513
  maxTokens: 81920,
446
514
  },
515
+ "eu.amazon.nova-2-lite-v1:0": {
516
+ id: "eu.amazon.nova-2-lite-v1:0",
517
+ name: "Nova 2 Lite (EU)",
518
+ api: "bedrock-converse-stream",
519
+ provider: "amazon-bedrock",
520
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
521
+ reasoning: true,
522
+ input: ["text", "image"],
523
+ cost: {
524
+ input: 0.374,
525
+ output: 3.157,
526
+ cacheRead: 0.0935,
527
+ cacheWrite: 0.374,
528
+ },
529
+ contextWindow: 1000000,
530
+ maxTokens: 65535,
531
+ },
532
+ "eu.amazon.nova-lite-v1:0": {
533
+ id: "eu.amazon.nova-lite-v1:0",
534
+ name: "Nova Lite (EU)",
535
+ api: "bedrock-converse-stream",
536
+ provider: "amazon-bedrock",
537
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
538
+ reasoning: false,
539
+ input: ["text", "image"],
540
+ cost: {
541
+ input: 0.069,
542
+ output: 0.276,
543
+ cacheRead: 0.01725,
544
+ cacheWrite: 0.069,
545
+ },
546
+ contextWindow: 300000,
547
+ maxTokens: 10000,
548
+ },
549
+ "eu.amazon.nova-micro-v1:0": {
550
+ id: "eu.amazon.nova-micro-v1:0",
551
+ name: "Nova Micro (EU)",
552
+ api: "bedrock-converse-stream",
553
+ provider: "amazon-bedrock",
554
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
555
+ reasoning: false,
556
+ input: ["text"],
557
+ cost: {
558
+ input: 0.04,
559
+ output: 0.16,
560
+ cacheRead: 0.01,
561
+ cacheWrite: 0.04,
562
+ },
563
+ contextWindow: 128000,
564
+ maxTokens: 10000,
565
+ },
566
+ "eu.amazon.nova-pro-v1:0": {
567
+ id: "eu.amazon.nova-pro-v1:0",
568
+ name: "Nova Pro (EU)",
569
+ api: "bedrock-converse-stream",
570
+ provider: "amazon-bedrock",
571
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
572
+ reasoning: false,
573
+ input: ["text", "image"],
574
+ cost: {
575
+ input: 0.92,
576
+ output: 3.68,
577
+ cacheRead: 0.23,
578
+ cacheWrite: 0.92,
579
+ },
580
+ contextWindow: 300000,
581
+ maxTokens: 10000,
582
+ },
447
583
  "eu.anthropic.claude-fable-5": {
448
584
  id: "eu.anthropic.claude-fable-5",
449
585
  name: "Claude Fable 5 (EU)",
@@ -614,6 +750,40 @@ export const MODELS = {
614
750
  contextWindow: 1000000,
615
751
  maxTokens: 128000,
616
752
  },
753
+ "eu.mistral.pixtral-large-2502-v1:0": {
754
+ id: "eu.mistral.pixtral-large-2502-v1:0",
755
+ name: "Pixtral Large (25.02) (EU)",
756
+ api: "bedrock-converse-stream",
757
+ provider: "amazon-bedrock",
758
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
759
+ reasoning: false,
760
+ input: ["text", "image"],
761
+ cost: {
762
+ input: 2,
763
+ output: 6,
764
+ cacheRead: 0,
765
+ cacheWrite: 0,
766
+ },
767
+ contextWindow: 128000,
768
+ maxTokens: 8192,
769
+ },
770
+ "global.amazon.nova-2-lite-v1:0": {
771
+ id: "global.amazon.nova-2-lite-v1:0",
772
+ name: "Nova 2 Lite (Global)",
773
+ api: "bedrock-converse-stream",
774
+ provider: "amazon-bedrock",
775
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
776
+ reasoning: true,
777
+ input: ["text", "image"],
778
+ cost: {
779
+ input: 0.3,
780
+ output: 2.5,
781
+ cacheRead: 0.075,
782
+ cacheWrite: 0.3,
783
+ },
784
+ contextWindow: 1000000,
785
+ maxTokens: 65535,
786
+ },
617
787
  "global.anthropic.claude-fable-5": {
618
788
  id: "global.anthropic.claude-fable-5",
619
789
  name: "Claude Fable 5 (Global)",
@@ -852,6 +1022,23 @@ export const MODELS = {
852
1022
  contextWindow: 1050000,
853
1023
  maxTokens: 128000,
854
1024
  },
1025
+ "global.openai.gpt-6-astra": {
1026
+ id: "global.openai.gpt-6-astra",
1027
+ name: "GPT-6 Astra (Global)",
1028
+ api: "bedrock-converse-stream",
1029
+ provider: "amazon-bedrock",
1030
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1031
+ reasoning: true,
1032
+ input: ["text", "image"],
1033
+ cost: {
1034
+ input: 10,
1035
+ output: 50,
1036
+ cacheRead: 1,
1037
+ cacheWrite: 12.5,
1038
+ },
1039
+ contextWindow: 1050000,
1040
+ maxTokens: 128000,
1041
+ },
855
1042
  "global.xai.grok-4.6": {
856
1043
  id: "global.xai.grok-4.6",
857
1044
  name: "Grok 4.6 (Global)",
@@ -869,30 +1056,47 @@ export const MODELS = {
869
1056
  contextWindow: 500000,
870
1057
  maxTokens: 500000,
871
1058
  },
872
- "google.gemma-3-27b-it": {
873
- id: "google.gemma-3-27b-it",
874
- name: "Google Gemma 3 27B Instruct",
1059
+ "google.gemma-4-26b-a4b": {
1060
+ id: "google.gemma-4-26b-a4b",
1061
+ name: "Gemma 4 26B A4B IT",
875
1062
  api: "bedrock-converse-stream",
876
1063
  provider: "amazon-bedrock",
877
1064
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
878
- reasoning: false,
1065
+ reasoning: true,
879
1066
  input: ["text", "image"],
880
1067
  cost: {
881
- input: 0.12,
882
- output: 0.2,
1068
+ input: 0.13,
1069
+ output: 0.4,
883
1070
  cacheRead: 0,
884
1071
  cacheWrite: 0,
885
1072
  },
886
- contextWindow: 202752,
887
- maxTokens: 8192,
1073
+ contextWindow: 262144,
1074
+ maxTokens: 32768,
888
1075
  },
889
- "google.gemma-3-4b-it": {
890
- id: "google.gemma-3-4b-it",
891
- name: "Gemma 3 4B IT",
1076
+ "google.gemma-4-31b": {
1077
+ id: "google.gemma-4-31b",
1078
+ name: "Gemma 4 31B IT",
892
1079
  api: "bedrock-converse-stream",
893
1080
  provider: "amazon-bedrock",
894
1081
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
895
- reasoning: false,
1082
+ reasoning: true,
1083
+ input: ["text", "image"],
1084
+ cost: {
1085
+ input: 0.14,
1086
+ output: 0.4,
1087
+ cacheRead: 0,
1088
+ cacheWrite: 0,
1089
+ },
1090
+ contextWindow: 262144,
1091
+ maxTokens: 32768,
1092
+ },
1093
+ "google.gemma-4-e2b": {
1094
+ id: "google.gemma-4-e2b",
1095
+ name: "Gemma 4 E2B IT",
1096
+ api: "bedrock-converse-stream",
1097
+ provider: "amazon-bedrock",
1098
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1099
+ reasoning: true,
896
1100
  input: ["text", "image"],
897
1101
  cost: {
898
1102
  input: 0.04,
@@ -900,8 +1104,59 @@ export const MODELS = {
900
1104
  cacheRead: 0,
901
1105
  cacheWrite: 0,
902
1106
  },
903
- contextWindow: 128000,
904
- maxTokens: 4096,
1107
+ contextWindow: 131072,
1108
+ maxTokens: 8192,
1109
+ },
1110
+ "in.openai.gpt-5.6-luna": {
1111
+ id: "in.openai.gpt-5.6-luna",
1112
+ name: "GPT-5.6 Luna (India)",
1113
+ api: "bedrock-converse-stream",
1114
+ provider: "amazon-bedrock",
1115
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1116
+ reasoning: true,
1117
+ input: ["text", "image"],
1118
+ cost: {
1119
+ input: 0.22,
1120
+ output: 1.32,
1121
+ cacheRead: 0.022,
1122
+ cacheWrite: 0.275,
1123
+ },
1124
+ contextWindow: 1050000,
1125
+ maxTokens: 128000,
1126
+ },
1127
+ "in.openai.gpt-5.6-terra": {
1128
+ id: "in.openai.gpt-5.6-terra",
1129
+ name: "GPT-5.6 Terra (India)",
1130
+ api: "bedrock-converse-stream",
1131
+ provider: "amazon-bedrock",
1132
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1133
+ reasoning: true,
1134
+ input: ["text", "image"],
1135
+ cost: {
1136
+ input: 2.2,
1137
+ output: 13.2,
1138
+ cacheRead: 0.22,
1139
+ cacheWrite: 2.75,
1140
+ },
1141
+ contextWindow: 1050000,
1142
+ maxTokens: 128000,
1143
+ },
1144
+ "jp.amazon.nova-2-lite-v1:0": {
1145
+ id: "jp.amazon.nova-2-lite-v1:0",
1146
+ name: "Nova 2 Lite (JP)",
1147
+ api: "bedrock-converse-stream",
1148
+ provider: "amazon-bedrock",
1149
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1150
+ reasoning: true,
1151
+ input: ["text", "image"],
1152
+ cost: {
1153
+ input: 0.396,
1154
+ output: 3.311,
1155
+ cacheRead: 0.099,
1156
+ cacheWrite: 0.396,
1157
+ },
1158
+ contextWindow: 1000000,
1159
+ maxTokens: 65535,
905
1160
  },
906
1161
  "jp.anthropic.claude-haiku-4-5-20251001-v1:0": {
907
1162
  id: "jp.anthropic.claude-haiku-4-5-20251001-v1:0",
@@ -1088,7 +1343,7 @@ export const MODELS = {
1088
1343
  cacheWrite: 0,
1089
1344
  },
1090
1345
  contextWindow: 1000000,
1091
- maxTokens: 16384,
1346
+ maxTokens: 8192,
1092
1347
  },
1093
1348
  "meta.llama4-scout-17b-instruct-v1:0": {
1094
1349
  id: "meta.llama4-scout-17b-instruct-v1:0",
@@ -1104,12 +1359,12 @@ export const MODELS = {
1104
1359
  cacheRead: 0,
1105
1360
  cacheWrite: 0,
1106
1361
  },
1107
- contextWindow: 3500000,
1108
- maxTokens: 16384,
1362
+ contextWindow: 10000000,
1363
+ maxTokens: 8192,
1109
1364
  },
1110
1365
  "minimax.minimax-m2": {
1111
1366
  id: "minimax.minimax-m2",
1112
- name: "MiniMax M2",
1367
+ name: "MiniMax-M2",
1113
1368
  api: "bedrock-converse-stream",
1114
1369
  provider: "amazon-bedrock",
1115
1370
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1126,7 +1381,7 @@ export const MODELS = {
1126
1381
  },
1127
1382
  "minimax.minimax-m2.1": {
1128
1383
  id: "minimax.minimax-m2.1",
1129
- name: "MiniMax M2.1",
1384
+ name: "MiniMax-M2.1",
1130
1385
  api: "bedrock-converse-stream",
1131
1386
  provider: "amazon-bedrock",
1132
1387
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1143,7 +1398,7 @@ export const MODELS = {
1143
1398
  },
1144
1399
  "minimax.minimax-m2.5": {
1145
1400
  id: "minimax.minimax-m2.5",
1146
- name: "MiniMax M2.5",
1401
+ name: "MiniMax-M2.5",
1147
1402
  api: "bedrock-converse-stream",
1148
1403
  provider: "amazon-bedrock",
1149
1404
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1199,7 +1454,7 @@ export const MODELS = {
1199
1454
  provider: "amazon-bedrock",
1200
1455
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1201
1456
  reasoning: false,
1202
- input: ["text"],
1457
+ input: ["text", "image"],
1203
1458
  cost: {
1204
1459
  input: 0.2,
1205
1460
  output: 0.2,
@@ -1233,7 +1488,7 @@ export const MODELS = {
1233
1488
  provider: "amazon-bedrock",
1234
1489
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1235
1490
  reasoning: false,
1236
- input: ["text"],
1491
+ input: ["text", "image"],
1237
1492
  cost: {
1238
1493
  input: 0.15,
1239
1494
  output: 0.15,
@@ -1291,7 +1546,7 @@ export const MODELS = {
1291
1546
  cacheRead: 0,
1292
1547
  cacheWrite: 0,
1293
1548
  },
1294
- contextWindow: 128000,
1549
+ contextWindow: 32768,
1295
1550
  maxTokens: 4096,
1296
1551
  },
1297
1552
  "mistral.voxtral-small-24b-2507": {
@@ -1303,12 +1558,12 @@ export const MODELS = {
1303
1558
  reasoning: false,
1304
1559
  input: ["text"],
1305
1560
  cost: {
1306
- input: 0.15,
1307
- output: 0.35,
1561
+ input: 0.1,
1562
+ output: 0.3,
1308
1563
  cacheRead: 0,
1309
1564
  cacheWrite: 0,
1310
1565
  },
1311
- contextWindow: 32000,
1566
+ contextWindow: 32768,
1312
1567
  maxTokens: 8192,
1313
1568
  },
1314
1569
  "moonshot.kimi-k2-thinking": {
@@ -1343,7 +1598,7 @@ export const MODELS = {
1343
1598
  cacheWrite: 0,
1344
1599
  },
1345
1600
  contextWindow: 262143,
1346
- maxTokens: 16000,
1601
+ maxTokens: 16384,
1347
1602
  },
1348
1603
  "nvidia.nemotron-nano-12b-v2": {
1349
1604
  id: "nvidia.nemotron-nano-12b-v2",
@@ -1360,7 +1615,7 @@ export const MODELS = {
1360
1615
  cacheWrite: 0,
1361
1616
  },
1362
1617
  contextWindow: 128000,
1363
- maxTokens: 4096,
1618
+ maxTokens: 8192,
1364
1619
  },
1365
1620
  "nvidia.nemotron-nano-3-30b": {
1366
1621
  id: "nvidia.nemotron-nano-3-30b",
@@ -1376,8 +1631,8 @@ export const MODELS = {
1376
1631
  cacheRead: 0,
1377
1632
  cacheWrite: 0,
1378
1633
  },
1379
- contextWindow: 128000,
1380
- maxTokens: 4096,
1634
+ contextWindow: 262144,
1635
+ maxTokens: 8192,
1381
1636
  },
1382
1637
  "nvidia.nemotron-nano-9b-v2": {
1383
1638
  id: "nvidia.nemotron-nano-9b-v2",
@@ -1393,9 +1648,9 @@ export const MODELS = {
1393
1648
  cacheRead: 0,
1394
1649
  cacheWrite: 0,
1395
1650
  },
1396
- contextWindow: 128000,
1397
- maxTokens: 4096,
1398
- },
1651
+ contextWindow: 131072,
1652
+ maxTokens: 8192,
1653
+ },
1399
1654
  "nvidia.nemotron-super-3-120b": {
1400
1655
  id: "nvidia.nemotron-super-3-120b",
1401
1656
  name: "NVIDIA Nemotron 3 Super 120B A12B",
@@ -1498,6 +1753,23 @@ export const MODELS = {
1498
1753
  contextWindow: 1050000,
1499
1754
  maxTokens: 128000,
1500
1755
  },
1756
+ "openai.gpt-6-astra": {
1757
+ id: "openai.gpt-6-astra",
1758
+ name: "GPT-6 Astra",
1759
+ api: "bedrock-converse-stream",
1760
+ provider: "amazon-bedrock",
1761
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1762
+ reasoning: true,
1763
+ input: ["text", "image"],
1764
+ cost: {
1765
+ input: 11,
1766
+ output: 55,
1767
+ cacheRead: 1.1,
1768
+ cacheWrite: 13.75,
1769
+ },
1770
+ contextWindow: 1050000,
1771
+ maxTokens: 128000,
1772
+ },
1501
1773
  "openai.gpt-oss-120b": {
1502
1774
  id: "openai.gpt-oss-120b",
1503
1775
  name: "gpt-oss-120b",
@@ -1572,7 +1844,7 @@ export const MODELS = {
1572
1844
  api: "bedrock-converse-stream",
1573
1845
  provider: "amazon-bedrock",
1574
1846
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1575
- reasoning: false,
1847
+ reasoning: true,
1576
1848
  input: ["text"],
1577
1849
  cost: {
1578
1850
  input: 0.15,
@@ -1589,7 +1861,7 @@ export const MODELS = {
1589
1861
  api: "bedrock-converse-stream",
1590
1862
  provider: "amazon-bedrock",
1591
1863
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1592
- reasoning: false,
1864
+ reasoning: true,
1593
1865
  input: ["text"],
1594
1866
  cost: {
1595
1867
  input: 0.07,
@@ -1602,7 +1874,7 @@ export const MODELS = {
1602
1874
  },
1603
1875
  "qwen.qwen3-235b-a22b-2507-v1:0": {
1604
1876
  id: "qwen.qwen3-235b-a22b-2507-v1:0",
1605
- name: "Qwen3 235B A22B 2507",
1877
+ name: "Qwen3 235B-A22B Instruct 2507",
1606
1878
  api: "bedrock-converse-stream",
1607
1879
  provider: "amazon-bedrock",
1608
1880
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1619,7 +1891,7 @@ export const MODELS = {
1619
1891
  },
1620
1892
  "qwen.qwen3-32b-v1:0": {
1621
1893
  id: "qwen.qwen3-32b-v1:0",
1622
- name: "Qwen3 32B (dense)",
1894
+ name: "Qwen3 32B",
1623
1895
  api: "bedrock-converse-stream",
1624
1896
  provider: "amazon-bedrock",
1625
1897
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1631,12 +1903,12 @@ export const MODELS = {
1631
1903
  cacheRead: 0,
1632
1904
  cacheWrite: 0,
1633
1905
  },
1634
- contextWindow: 16384,
1906
+ contextWindow: 32768,
1635
1907
  maxTokens: 16384,
1636
1908
  },
1637
1909
  "qwen.qwen3-coder-30b-a3b-v1:0": {
1638
1910
  id: "qwen.qwen3-coder-30b-a3b-v1:0",
1639
- name: "Qwen3 Coder 30B A3B Instruct",
1911
+ name: "Qwen3-Coder 30B-A3B Instruct",
1640
1912
  api: "bedrock-converse-stream",
1641
1913
  provider: "amazon-bedrock",
1642
1914
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1653,14 +1925,14 @@ export const MODELS = {
1653
1925
  },
1654
1926
  "qwen.qwen3-coder-480b-a35b-v1:0": {
1655
1927
  id: "qwen.qwen3-coder-480b-a35b-v1:0",
1656
- name: "Qwen3 Coder 480B A35B Instruct",
1928
+ name: "Qwen3-Coder 480B-A35B Instruct",
1657
1929
  api: "bedrock-converse-stream",
1658
1930
  provider: "amazon-bedrock",
1659
1931
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1660
1932
  reasoning: false,
1661
1933
  input: ["text"],
1662
1934
  cost: {
1663
- input: 0.22,
1935
+ input: 0.45,
1664
1936
  output: 1.8,
1665
1937
  cacheRead: 0,
1666
1938
  cacheWrite: 0,
@@ -1674,51 +1946,170 @@ export const MODELS = {
1674
1946
  api: "bedrock-converse-stream",
1675
1947
  provider: "amazon-bedrock",
1676
1948
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1677
- reasoning: true,
1949
+ reasoning: false,
1678
1950
  input: ["text"],
1679
1951
  cost: {
1680
- input: 0.22,
1681
- output: 1.8,
1952
+ input: 0.5,
1953
+ output: 1.2,
1682
1954
  cacheRead: 0,
1683
1955
  cacheWrite: 0,
1684
1956
  },
1685
- contextWindow: 131072,
1957
+ contextWindow: 262144,
1686
1958
  maxTokens: 65536,
1687
1959
  },
1688
1960
  "qwen.qwen3-next-80b-a3b": {
1689
1961
  id: "qwen.qwen3-next-80b-a3b",
1690
- name: "Qwen/Qwen3-Next-80B-A3B-Instruct",
1962
+ name: "Qwen3-Next 80B-A3B Instruct",
1691
1963
  api: "bedrock-converse-stream",
1692
1964
  provider: "amazon-bedrock",
1693
1965
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1694
1966
  reasoning: false,
1695
1967
  input: ["text"],
1696
1968
  cost: {
1697
- input: 0.14,
1698
- output: 1.4,
1969
+ input: 0.15,
1970
+ output: 1.2,
1699
1971
  cacheRead: 0,
1700
1972
  cacheWrite: 0,
1701
1973
  },
1702
- contextWindow: 262000,
1974
+ contextWindow: 262144,
1703
1975
  maxTokens: 262000,
1704
1976
  },
1705
1977
  "qwen.qwen3-vl-235b-a22b": {
1706
1978
  id: "qwen.qwen3-vl-235b-a22b",
1707
- name: "Qwen/Qwen3-VL-235B-A22B-Instruct",
1979
+ name: "Qwen3 VL 235B A22B Instruct",
1708
1980
  api: "bedrock-converse-stream",
1709
1981
  provider: "amazon-bedrock",
1710
1982
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1711
1983
  reasoning: false,
1712
1984
  input: ["text", "image"],
1713
1985
  cost: {
1714
- input: 0.3,
1715
- output: 1.5,
1986
+ input: 0.53,
1987
+ output: 2.66,
1716
1988
  cacheRead: 0,
1717
1989
  cacheWrite: 0,
1718
1990
  },
1719
- contextWindow: 262000,
1991
+ contextWindow: 262144,
1720
1992
  maxTokens: 262000,
1721
1993
  },
1994
+ "us-gov.openai.gpt-oss-120b-1:0": {
1995
+ id: "us-gov.openai.gpt-oss-120b-1:0",
1996
+ name: "gpt-oss-120b (GovCloud)",
1997
+ api: "bedrock-converse-stream",
1998
+ provider: "amazon-bedrock",
1999
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2000
+ reasoning: true,
2001
+ input: ["text"],
2002
+ cost: {
2003
+ input: 0.18,
2004
+ output: 0.72,
2005
+ cacheRead: 0,
2006
+ cacheWrite: 0,
2007
+ },
2008
+ contextWindow: 128000,
2009
+ maxTokens: 16384,
2010
+ },
2011
+ "us-gov.openai.gpt-oss-20b-1:0": {
2012
+ id: "us-gov.openai.gpt-oss-20b-1:0",
2013
+ name: "gpt-oss-20b (GovCloud)",
2014
+ api: "bedrock-converse-stream",
2015
+ provider: "amazon-bedrock",
2016
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2017
+ reasoning: true,
2018
+ input: ["text"],
2019
+ cost: {
2020
+ input: 0.084,
2021
+ output: 0.36,
2022
+ cacheRead: 0,
2023
+ cacheWrite: 0,
2024
+ },
2025
+ contextWindow: 128000,
2026
+ maxTokens: 16384,
2027
+ },
2028
+ "us.amazon.nova-2-lite-v1:0": {
2029
+ id: "us.amazon.nova-2-lite-v1:0",
2030
+ name: "Nova 2 Lite (US)",
2031
+ api: "bedrock-converse-stream",
2032
+ provider: "amazon-bedrock",
2033
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2034
+ reasoning: true,
2035
+ input: ["text", "image"],
2036
+ cost: {
2037
+ input: 0.33,
2038
+ output: 2.75,
2039
+ cacheRead: 0.0825,
2040
+ cacheWrite: 0.33,
2041
+ },
2042
+ contextWindow: 1000000,
2043
+ maxTokens: 65535,
2044
+ },
2045
+ "us.amazon.nova-lite-v1:0": {
2046
+ id: "us.amazon.nova-lite-v1:0",
2047
+ name: "Nova Lite (US)",
2048
+ api: "bedrock-converse-stream",
2049
+ provider: "amazon-bedrock",
2050
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2051
+ reasoning: false,
2052
+ input: ["text", "image"],
2053
+ cost: {
2054
+ input: 0.06,
2055
+ output: 0.24,
2056
+ cacheRead: 0.015,
2057
+ cacheWrite: 0.06,
2058
+ },
2059
+ contextWindow: 300000,
2060
+ maxTokens: 10000,
2061
+ },
2062
+ "us.amazon.nova-micro-v1:0": {
2063
+ id: "us.amazon.nova-micro-v1:0",
2064
+ name: "Nova Micro (US)",
2065
+ api: "bedrock-converse-stream",
2066
+ provider: "amazon-bedrock",
2067
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2068
+ reasoning: false,
2069
+ input: ["text"],
2070
+ cost: {
2071
+ input: 0.035,
2072
+ output: 0.14,
2073
+ cacheRead: 0.00875,
2074
+ cacheWrite: 0.035,
2075
+ },
2076
+ contextWindow: 128000,
2077
+ maxTokens: 10000,
2078
+ },
2079
+ "us.amazon.nova-premier-v1:0": {
2080
+ id: "us.amazon.nova-premier-v1:0",
2081
+ name: "Nova Premier (US)",
2082
+ api: "bedrock-converse-stream",
2083
+ provider: "amazon-bedrock",
2084
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2085
+ reasoning: false,
2086
+ input: ["text", "image"],
2087
+ cost: {
2088
+ input: 2.5,
2089
+ output: 12.5,
2090
+ cacheRead: 0.625,
2091
+ cacheWrite: 2.5,
2092
+ },
2093
+ contextWindow: 1000000,
2094
+ maxTokens: 10000,
2095
+ },
2096
+ "us.amazon.nova-pro-v1:0": {
2097
+ id: "us.amazon.nova-pro-v1:0",
2098
+ name: "Nova Pro (US)",
2099
+ api: "bedrock-converse-stream",
2100
+ provider: "amazon-bedrock",
2101
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2102
+ reasoning: false,
2103
+ input: ["text", "image"],
2104
+ cost: {
2105
+ input: 0.8,
2106
+ output: 3.2,
2107
+ cacheRead: 0.2,
2108
+ cacheWrite: 0.8,
2109
+ },
2110
+ contextWindow: 300000,
2111
+ maxTokens: 10000,
2112
+ },
1722
2113
  "us.anthropic.claude-fable-5": {
1723
2114
  id: "us.anthropic.claude-fable-5",
1724
2115
  name: "Claude Fable 5 (US)",
@@ -1838,141 +2229,294 @@ export const MODELS = {
1838
2229
  contextWindow: 1000000,
1839
2230
  maxTokens: 128000,
1840
2231
  },
1841
- "us.anthropic.claude-opus-4-8": {
1842
- id: "us.anthropic.claude-opus-4-8",
1843
- name: "Claude Opus 4.8 (US)",
2232
+ "us.anthropic.claude-opus-4-8": {
2233
+ id: "us.anthropic.claude-opus-4-8",
2234
+ name: "Claude Opus 4.8 (US)",
2235
+ api: "bedrock-converse-stream",
2236
+ provider: "amazon-bedrock",
2237
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2238
+ reasoning: true,
2239
+ input: ["text", "image"],
2240
+ cost: {
2241
+ input: 5,
2242
+ output: 25,
2243
+ cacheRead: 0.5,
2244
+ cacheWrite: 6.25,
2245
+ },
2246
+ contextWindow: 1000000,
2247
+ maxTokens: 128000,
2248
+ },
2249
+ "us.anthropic.claude-opus-5": {
2250
+ id: "us.anthropic.claude-opus-5",
2251
+ name: "Claude Opus 5 (US)",
2252
+ api: "bedrock-converse-stream",
2253
+ provider: "amazon-bedrock",
2254
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2255
+ reasoning: true,
2256
+ input: ["text", "image"],
2257
+ cost: {
2258
+ input: 5,
2259
+ output: 25,
2260
+ cacheRead: 0.5,
2261
+ cacheWrite: 6.25,
2262
+ },
2263
+ contextWindow: 1000000,
2264
+ maxTokens: 128000,
2265
+ },
2266
+ "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
2267
+ id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
2268
+ name: "Claude Sonnet 4.5 (US)",
2269
+ api: "bedrock-converse-stream",
2270
+ provider: "amazon-bedrock",
2271
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2272
+ reasoning: true,
2273
+ input: ["text", "image"],
2274
+ cost: {
2275
+ input: 3,
2276
+ output: 15,
2277
+ cacheRead: 0.3,
2278
+ cacheWrite: 3.75,
2279
+ },
2280
+ contextWindow: 200000,
2281
+ maxTokens: 64000,
2282
+ },
2283
+ "us.anthropic.claude-sonnet-4-6": {
2284
+ id: "us.anthropic.claude-sonnet-4-6",
2285
+ name: "Claude Sonnet 4.6 (US)",
2286
+ api: "bedrock-converse-stream",
2287
+ provider: "amazon-bedrock",
2288
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2289
+ reasoning: true,
2290
+ input: ["text", "image"],
2291
+ cost: {
2292
+ input: 3,
2293
+ output: 15,
2294
+ cacheRead: 0.3,
2295
+ cacheWrite: 3.75,
2296
+ },
2297
+ contextWindow: 1000000,
2298
+ maxTokens: 64000,
2299
+ },
2300
+ "us.anthropic.claude-sonnet-5": {
2301
+ id: "us.anthropic.claude-sonnet-5",
2302
+ name: "Claude Sonnet 5 (US)",
2303
+ api: "bedrock-converse-stream",
2304
+ provider: "amazon-bedrock",
2305
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2306
+ reasoning: true,
2307
+ input: ["text", "image"],
2308
+ cost: {
2309
+ input: 2,
2310
+ output: 10,
2311
+ cacheRead: 0.2,
2312
+ cacheWrite: 2.5,
2313
+ },
2314
+ contextWindow: 1000000,
2315
+ maxTokens: 128000,
2316
+ },
2317
+ "us.meta.llama3-1-70b-instruct-v1:0": {
2318
+ id: "us.meta.llama3-1-70b-instruct-v1:0",
2319
+ name: "Llama 3.1 70B Instruct (US)",
2320
+ api: "bedrock-converse-stream",
2321
+ provider: "amazon-bedrock",
2322
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2323
+ reasoning: false,
2324
+ input: ["text"],
2325
+ cost: {
2326
+ input: 0.72,
2327
+ output: 0.72,
2328
+ cacheRead: 0,
2329
+ cacheWrite: 0,
2330
+ },
2331
+ contextWindow: 128000,
2332
+ maxTokens: 4096,
2333
+ },
2334
+ "us.meta.llama3-1-8b-instruct-v1:0": {
2335
+ id: "us.meta.llama3-1-8b-instruct-v1:0",
2336
+ name: "Llama 3.1 8B Instruct (US)",
2337
+ api: "bedrock-converse-stream",
2338
+ provider: "amazon-bedrock",
2339
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2340
+ reasoning: false,
2341
+ input: ["text"],
2342
+ cost: {
2343
+ input: 0.22,
2344
+ output: 0.22,
2345
+ cacheRead: 0,
2346
+ cacheWrite: 0,
2347
+ },
2348
+ contextWindow: 128000,
2349
+ maxTokens: 4096,
2350
+ },
2351
+ "us.meta.llama3-3-70b-instruct-v1:0": {
2352
+ id: "us.meta.llama3-3-70b-instruct-v1:0",
2353
+ name: "Llama 3.3 70B Instruct (US)",
2354
+ api: "bedrock-converse-stream",
2355
+ provider: "amazon-bedrock",
2356
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2357
+ reasoning: false,
2358
+ input: ["text"],
2359
+ cost: {
2360
+ input: 0.72,
2361
+ output: 0.72,
2362
+ cacheRead: 0,
2363
+ cacheWrite: 0,
2364
+ },
2365
+ contextWindow: 128000,
2366
+ maxTokens: 4096,
2367
+ },
2368
+ "us.meta.llama4-maverick-17b-instruct-v1:0": {
2369
+ id: "us.meta.llama4-maverick-17b-instruct-v1:0",
2370
+ name: "Llama 4 Maverick 17B Instruct (US)",
2371
+ api: "bedrock-converse-stream",
2372
+ provider: "amazon-bedrock",
2373
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2374
+ reasoning: false,
2375
+ input: ["text", "image"],
2376
+ cost: {
2377
+ input: 0.24,
2378
+ output: 0.97,
2379
+ cacheRead: 0,
2380
+ cacheWrite: 0,
2381
+ },
2382
+ contextWindow: 1000000,
2383
+ maxTokens: 8192,
2384
+ },
2385
+ "us.meta.llama4-scout-17b-instruct-v1:0": {
2386
+ id: "us.meta.llama4-scout-17b-instruct-v1:0",
2387
+ name: "Llama 4 Scout 17B Instruct (US)",
2388
+ api: "bedrock-converse-stream",
2389
+ provider: "amazon-bedrock",
2390
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2391
+ reasoning: false,
2392
+ input: ["text", "image"],
2393
+ cost: {
2394
+ input: 0.17,
2395
+ output: 0.66,
2396
+ cacheRead: 0,
2397
+ cacheWrite: 0,
2398
+ },
2399
+ contextWindow: 10000000,
2400
+ maxTokens: 8192,
2401
+ },
2402
+ "us.mistral.pixtral-large-2502-v1:0": {
2403
+ id: "us.mistral.pixtral-large-2502-v1:0",
2404
+ name: "Pixtral Large (25.02) (US)",
1844
2405
  api: "bedrock-converse-stream",
1845
2406
  provider: "amazon-bedrock",
1846
2407
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1847
- reasoning: true,
2408
+ reasoning: false,
1848
2409
  input: ["text", "image"],
1849
2410
  cost: {
1850
- input: 5,
1851
- output: 25,
1852
- cacheRead: 0.5,
1853
- cacheWrite: 6.25,
2411
+ input: 2,
2412
+ output: 6,
2413
+ cacheRead: 0,
2414
+ cacheWrite: 0,
1854
2415
  },
1855
- contextWindow: 1000000,
1856
- maxTokens: 128000,
2416
+ contextWindow: 128000,
2417
+ maxTokens: 8192,
1857
2418
  },
1858
- "us.anthropic.claude-opus-5": {
1859
- id: "us.anthropic.claude-opus-5",
1860
- name: "Claude Opus 5 (US)",
2419
+ "us.openai.gpt-5.6-luna": {
2420
+ id: "us.openai.gpt-5.6-luna",
2421
+ name: "GPT-5.6 Luna (US)",
1861
2422
  api: "bedrock-converse-stream",
1862
2423
  provider: "amazon-bedrock",
1863
2424
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1864
2425
  reasoning: true,
1865
2426
  input: ["text", "image"],
1866
2427
  cost: {
1867
- input: 5,
1868
- output: 25,
1869
- cacheRead: 0.5,
1870
- cacheWrite: 6.25,
2428
+ input: 0.22,
2429
+ output: 1.32,
2430
+ cacheRead: 0.022,
2431
+ cacheWrite: 0.275,
1871
2432
  },
1872
- contextWindow: 1000000,
2433
+ contextWindow: 1050000,
1873
2434
  maxTokens: 128000,
1874
2435
  },
1875
- "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
1876
- id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
1877
- name: "Claude Sonnet 4.5 (US)",
2436
+ "us.openai.gpt-5.6-sol": {
2437
+ id: "us.openai.gpt-5.6-sol",
2438
+ name: "GPT-5.6 Sol (US)",
1878
2439
  api: "bedrock-converse-stream",
1879
2440
  provider: "amazon-bedrock",
1880
2441
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1881
2442
  reasoning: true,
1882
2443
  input: ["text", "image"],
1883
2444
  cost: {
1884
- input: 3,
1885
- output: 15,
1886
- cacheRead: 0.3,
1887
- cacheWrite: 3.75,
2445
+ input: 4.4,
2446
+ output: 22,
2447
+ cacheRead: 0.44,
2448
+ cacheWrite: 5.5,
1888
2449
  },
1889
- contextWindow: 200000,
1890
- maxTokens: 64000,
2450
+ contextWindow: 1050000,
2451
+ maxTokens: 128000,
1891
2452
  },
1892
- "us.anthropic.claude-sonnet-4-6": {
1893
- id: "us.anthropic.claude-sonnet-4-6",
1894
- name: "Claude Sonnet 4.6 (US)",
2453
+ "us.openai.gpt-5.6-terra": {
2454
+ id: "us.openai.gpt-5.6-terra",
2455
+ name: "GPT-5.6 Terra (US)",
1895
2456
  api: "bedrock-converse-stream",
1896
2457
  provider: "amazon-bedrock",
1897
2458
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1898
2459
  reasoning: true,
1899
2460
  input: ["text", "image"],
1900
2461
  cost: {
1901
- input: 3,
1902
- output: 15,
1903
- cacheRead: 0.3,
1904
- cacheWrite: 3.75,
2462
+ input: 2.2,
2463
+ output: 13.2,
2464
+ cacheRead: 0.22,
2465
+ cacheWrite: 2.75,
1905
2466
  },
1906
- contextWindow: 1000000,
1907
- maxTokens: 64000,
2467
+ contextWindow: 1050000,
2468
+ maxTokens: 128000,
1908
2469
  },
1909
- "us.anthropic.claude-sonnet-5": {
1910
- id: "us.anthropic.claude-sonnet-5",
1911
- name: "Claude Sonnet 5 (US)",
2470
+ "us.openai.gpt-6-astra": {
2471
+ id: "us.openai.gpt-6-astra",
2472
+ name: "GPT-6 Astra (US)",
1912
2473
  api: "bedrock-converse-stream",
1913
2474
  provider: "amazon-bedrock",
1914
2475
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1915
2476
  reasoning: true,
1916
2477
  input: ["text", "image"],
1917
2478
  cost: {
1918
- input: 2,
1919
- output: 10,
1920
- cacheRead: 0.2,
1921
- cacheWrite: 2.5,
2479
+ input: 11,
2480
+ output: 55,
2481
+ cacheRead: 1.1,
2482
+ cacheWrite: 13.75,
1922
2483
  },
1923
- contextWindow: 1000000,
2484
+ contextWindow: 1050000,
1924
2485
  maxTokens: 128000,
1925
2486
  },
1926
- "us.deepseek.r1-v1:0": {
1927
- id: "us.deepseek.r1-v1:0",
1928
- name: "DeepSeek-R1 (US)",
2487
+ "us.writer.palmyra-x4-v1:0": {
2488
+ id: "us.writer.palmyra-x4-v1:0",
2489
+ name: "Palmyra X4 (US)",
1929
2490
  api: "bedrock-converse-stream",
1930
2491
  provider: "amazon-bedrock",
1931
2492
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1932
2493
  reasoning: true,
1933
2494
  input: ["text"],
1934
2495
  cost: {
1935
- input: 1.35,
1936
- output: 5.4,
1937
- cacheRead: 0,
1938
- cacheWrite: 0,
1939
- },
1940
- contextWindow: 128000,
1941
- maxTokens: 32768,
1942
- },
1943
- "us.meta.llama4-maverick-17b-instruct-v1:0": {
1944
- id: "us.meta.llama4-maverick-17b-instruct-v1:0",
1945
- name: "Llama 4 Maverick 17B Instruct (US)",
1946
- api: "bedrock-converse-stream",
1947
- provider: "amazon-bedrock",
1948
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1949
- reasoning: false,
1950
- input: ["text", "image"],
1951
- cost: {
1952
- input: 0.24,
1953
- output: 0.97,
2496
+ input: 2.5,
2497
+ output: 10,
1954
2498
  cacheRead: 0,
1955
2499
  cacheWrite: 0,
1956
2500
  },
1957
- contextWindow: 1000000,
1958
- maxTokens: 16384,
2501
+ contextWindow: 122880,
2502
+ maxTokens: 8192,
1959
2503
  },
1960
- "us.meta.llama4-scout-17b-instruct-v1:0": {
1961
- id: "us.meta.llama4-scout-17b-instruct-v1:0",
1962
- name: "Llama 4 Scout 17B Instruct (US)",
2504
+ "us.writer.palmyra-x5-v1:0": {
2505
+ id: "us.writer.palmyra-x5-v1:0",
2506
+ name: "Palmyra X5 (US)",
1963
2507
  api: "bedrock-converse-stream",
1964
2508
  provider: "amazon-bedrock",
1965
2509
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1966
- reasoning: false,
1967
- input: ["text", "image"],
2510
+ reasoning: true,
2511
+ input: ["text"],
1968
2512
  cost: {
1969
- input: 0.17,
1970
- output: 0.66,
2513
+ input: 0.6,
2514
+ output: 6,
1971
2515
  cacheRead: 0,
1972
2516
  cacheWrite: 0,
1973
2517
  },
1974
- contextWindow: 3500000,
1975
- maxTokens: 16384,
2518
+ contextWindow: 1040000,
2519
+ maxTokens: 8192,
1976
2520
  },
1977
2521
  "us.xai.grok-4.6": {
1978
2522
  id: "us.xai.grok-4.6",
@@ -2108,7 +2652,7 @@ export const MODELS = {
2108
2652
  cacheWrite: 0,
2109
2653
  },
2110
2654
  contextWindow: 202752,
2111
- maxTokens: 101376,
2655
+ maxTokens: 131072,
2112
2656
  },
2113
2657
  },
2114
2658
  "anthropic": {
@@ -5324,6 +5868,78 @@ export const MODELS = {
5324
5868
  contextWindow: 1000000,
5325
5869
  maxTokens: 384000,
5326
5870
  },
5871
+ "deepseek-ai/DeepSeek-V4.1-Flash": {
5872
+ id: "deepseek-ai/DeepSeek-V4.1-Flash",
5873
+ name: "DeepSeek V4.1 Flash",
5874
+ api: "openai-completions",
5875
+ provider: "huggingface",
5876
+ baseUrl: "https://router.huggingface.co/v1",
5877
+ compat: { "supportsDeveloperRole": false },
5878
+ reasoning: true,
5879
+ input: ["text", "image"],
5880
+ cost: {
5881
+ input: 0.3,
5882
+ output: 1.2,
5883
+ cacheRead: 0,
5884
+ cacheWrite: 0,
5885
+ },
5886
+ contextWindow: 1048576,
5887
+ maxTokens: 384000,
5888
+ },
5889
+ "google/gemma-3-12b-it": {
5890
+ id: "google/gemma-3-12b-it",
5891
+ name: "Gemma 3 12B IT",
5892
+ api: "openai-completions",
5893
+ provider: "huggingface",
5894
+ baseUrl: "https://router.huggingface.co/v1",
5895
+ compat: { "supportsDeveloperRole": false },
5896
+ reasoning: false,
5897
+ input: ["text", "image"],
5898
+ cost: {
5899
+ input: 0.05,
5900
+ output: 0.15,
5901
+ cacheRead: 0,
5902
+ cacheWrite: 0,
5903
+ },
5904
+ contextWindow: 131072,
5905
+ maxTokens: 131072,
5906
+ },
5907
+ "google/gemma-3-27b-it": {
5908
+ id: "google/gemma-3-27b-it",
5909
+ name: "Gemma 3 27B IT",
5910
+ api: "openai-completions",
5911
+ provider: "huggingface",
5912
+ baseUrl: "https://router.huggingface.co/v1",
5913
+ compat: { "supportsDeveloperRole": false },
5914
+ reasoning: false,
5915
+ input: ["text", "image"],
5916
+ cost: {
5917
+ input: 0.08,
5918
+ output: 0.16,
5919
+ cacheRead: 0,
5920
+ cacheWrite: 0,
5921
+ },
5922
+ contextWindow: 131072,
5923
+ maxTokens: 131072,
5924
+ },
5925
+ "google/gemma-3-4b-it": {
5926
+ id: "google/gemma-3-4b-it",
5927
+ name: "Gemma 3 4B IT",
5928
+ api: "openai-completions",
5929
+ provider: "huggingface",
5930
+ baseUrl: "https://router.huggingface.co/v1",
5931
+ compat: { "supportsDeveloperRole": false },
5932
+ reasoning: false,
5933
+ input: ["text", "image"],
5934
+ cost: {
5935
+ input: 0.05,
5936
+ output: 0.1,
5937
+ cacheRead: 0,
5938
+ cacheWrite: 0,
5939
+ },
5940
+ contextWindow: 131072,
5941
+ maxTokens: 131072,
5942
+ },
5327
5943
  "google/gemma-4-26B-A4B-it": {
5328
5944
  id: "google/gemma-4-26B-A4B-it",
5329
5945
  name: "Gemma 4 26B A4B IT",
@@ -8614,9 +9230,9 @@ export const MODELS = {
8614
9230
  reasoning: true,
8615
9231
  input: ["text"],
8616
9232
  cost: {
8617
- input: 0.22,
8618
- output: 0.66,
8619
- cacheRead: 0.007,
9233
+ input: 0.15,
9234
+ output: 0.6,
9235
+ cacheRead: 0.003,
8620
9236
  cacheWrite: 0,
8621
9237
  },
8622
9238
  contextWindow: 1000000,
@@ -8631,9 +9247,9 @@ export const MODELS = {
8631
9247
  reasoning: true,
8632
9248
  input: ["text", "image"],
8633
9249
  cost: {
8634
- input: 0.22,
8635
- output: 0.66,
8636
- cacheRead: 0.007,
9250
+ input: 0.15,
9251
+ output: 0.6,
9252
+ cacheRead: 0.003,
8637
9253
  cacheWrite: 0,
8638
9254
  },
8639
9255
  contextWindow: 1000000,
@@ -8656,6 +9272,23 @@ export const MODELS = {
8656
9272
  contextWindow: 1000000,
8657
9273
  maxTokens: 384000,
8658
9274
  },
9275
+ "deepseek-v4.1-flash": {
9276
+ id: "deepseek-v4.1-flash",
9277
+ name: "DeepSeek V4.1 Flash",
9278
+ api: "openai-completions",
9279
+ provider: "opencode-go",
9280
+ baseUrl: "https://opencode.ai/zen/go/v1",
9281
+ reasoning: true,
9282
+ input: ["text", "image"],
9283
+ cost: {
9284
+ input: 0.15,
9285
+ output: 0.6,
9286
+ cacheRead: 0.003,
9287
+ cacheWrite: 0,
9288
+ },
9289
+ contextWindow: 1000000,
9290
+ maxTokens: 384000,
9291
+ },
8659
9292
  "glm-5.1": {
8660
9293
  id: "glm-5.1",
8661
9294
  name: "GLM-5.1",
@@ -8709,16 +9342,16 @@ export const MODELS = {
8709
9342
  },
8710
9343
  "glm-5.3-flash": {
8711
9344
  id: "glm-5.3-flash",
8712
- name: "GLM-5.3-Flash (2x usage)",
9345
+ name: "GLM-5.3-Flash",
8713
9346
  api: "openai-completions",
8714
9347
  provider: "opencode-go",
8715
9348
  baseUrl: "https://opencode.ai/zen/go/v1",
8716
9349
  reasoning: true,
8717
9350
  input: ["text", "image"],
8718
9351
  cost: {
8719
- input: 0.075,
8720
- output: 0.25,
8721
- cacheRead: 0.015,
9352
+ input: 0.15,
9353
+ output: 0.5,
9354
+ cacheRead: 0.03,
8722
9355
  cacheWrite: 0,
8723
9356
  },
8724
9357
  contextWindow: 1000000,
@@ -8962,23 +9595,6 @@ export const MODELS = {
8962
9595
  contextWindow: 1048576,
8963
9596
  maxTokens: 131072,
8964
9597
  },
8965
- "omen-alpha": {
8966
- id: "omen-alpha",
8967
- name: "Omen Alpha",
8968
- api: "openai-completions",
8969
- provider: "opencode-go",
8970
- baseUrl: "https://opencode.ai/zen/go/v1",
8971
- reasoning: true,
8972
- input: ["text", "image"],
8973
- cost: {
8974
- input: 0.2,
8975
- output: 0.66,
8976
- cacheRead: 0.04,
8977
- cacheWrite: 0,
8978
- },
8979
- contextWindow: 500000,
8980
- maxTokens: 128000,
8981
- },
8982
9598
  "qwen3.6-plus": {
8983
9599
  id: "qwen3.6-plus",
8984
9600
  name: "Qwen3.6 Plus",
@@ -9857,13 +10473,13 @@ export const MODELS = {
9857
10473
  reasoning: false,
9858
10474
  input: ["text"],
9859
10475
  cost: {
9860
- input: 0.32,
9861
- output: 0.8899999999999999,
10476
+ input: 0.2574,
10477
+ output: 1.0287,
9862
10478
  cacheRead: 0,
9863
10479
  cacheWrite: 0,
9864
10480
  },
9865
10481
  contextWindow: 163840,
9866
- maxTokens: 16384,
10482
+ maxTokens: 16000,
9867
10483
  },
9868
10484
  "deepseek/deepseek-chat-v3-0324": {
9869
10485
  id: "deepseek/deepseek-chat-v3-0324",
@@ -9874,9 +10490,9 @@ export const MODELS = {
9874
10490
  reasoning: false,
9875
10491
  input: ["text"],
9876
10492
  cost: {
9877
- input: 0.29,
9878
- output: 1.1400000000000001,
9879
- cacheRead: 0.11,
10493
+ input: 0.25,
10494
+ output: 1,
10495
+ cacheRead: 0,
9880
10496
  cacheWrite: 0,
9881
10497
  },
9882
10498
  contextWindow: 163840,
@@ -9993,9 +10609,9 @@ export const MODELS = {
9993
10609
  reasoning: true,
9994
10610
  input: ["text"],
9995
10611
  cost: {
9996
- input: 0.088606,
9997
- output: 0.177212,
9998
- cacheRead: 0.017721200000000003,
10612
+ input: 0.08553999999999999,
10613
+ output: 0.17107999999999998,
10614
+ cacheRead: 0.017108,
9999
10615
  cacheWrite: 0,
10000
10616
  },
10001
10617
  contextWindow: 1048576,
@@ -10010,9 +10626,9 @@ export const MODELS = {
10010
10626
  reasoning: true,
10011
10627
  input: ["text"],
10012
10628
  cost: {
10013
- input: 0.065,
10014
- output: 0.18,
10015
- cacheRead: 0.016,
10629
+ input: 0.06,
10630
+ output: 0.12,
10631
+ cacheRead: 0.012,
10016
10632
  cacheWrite: 0,
10017
10633
  },
10018
10634
  contextWindow: 1310720,
@@ -10027,9 +10643,9 @@ export const MODELS = {
10027
10643
  reasoning: true,
10028
10644
  input: ["text"],
10029
10645
  cost: {
10030
- input: 0.14,
10031
- output: 0.28,
10032
- cacheRead: 0.03,
10646
+ input: 0.11,
10647
+ output: 0.33,
10648
+ cacheRead: 0.0035,
10033
10649
  cacheWrite: 0,
10034
10650
  },
10035
10651
  contextWindow: 1048576,
@@ -10050,7 +10666,24 @@ export const MODELS = {
10050
10666
  cacheWrite: 0,
10051
10667
  },
10052
10668
  contextWindow: 1048576,
10053
- maxTokens: 384000,
10669
+ maxTokens: 943718,
10670
+ },
10671
+ "deepseek/deepseek-v4-flash-vision-exp:batch": {
10672
+ id: "deepseek/deepseek-v4-flash-vision-exp:batch",
10673
+ name: "DeepSeek: DeepSeek V4 Flash Vision Exp (batch)",
10674
+ api: "openai-completions",
10675
+ provider: "openrouter",
10676
+ baseUrl: "https://openrouter.ai/api/v1",
10677
+ reasoning: true,
10678
+ input: ["text", "image"],
10679
+ cost: {
10680
+ input: 0.11,
10681
+ output: 0.33,
10682
+ cacheRead: 0.0035,
10683
+ cacheWrite: 0,
10684
+ },
10685
+ contextWindow: 1048576,
10686
+ maxTokens: 943718,
10054
10687
  },
10055
10688
  "deepseek/deepseek-v4-pro": {
10056
10689
  id: "deepseek/deepseek-v4-pro",
@@ -10061,13 +10694,13 @@ export const MODELS = {
10061
10694
  reasoning: true,
10062
10695
  input: ["text"],
10063
10696
  cost: {
10064
- input: 0.9552599999999999,
10065
- output: 1.9105199999999998,
10066
- cacheRead: 0.07960500000000001,
10697
+ input: 1.5999999999999999,
10698
+ output: 3.1999999999999997,
10699
+ cacheRead: 0.135,
10067
10700
  cacheWrite: 0,
10068
10701
  },
10069
10702
  contextWindow: 1048576,
10070
- maxTokens: 384000,
10703
+ maxTokens: 393216,
10071
10704
  },
10072
10705
  "deepseek/deepseek-v4-pro-0813": {
10073
10706
  id: "deepseek/deepseek-v4-pro-0813",
@@ -10078,9 +10711,9 @@ export const MODELS = {
10078
10711
  reasoning: true,
10079
10712
  input: ["text"],
10080
10713
  cost: {
10081
- input: 1.0494,
10082
- output: 3.1482,
10083
- cacheRead: 0.03498,
10714
+ input: 0.9833999999999999,
10715
+ output: 2.9502,
10716
+ cacheRead: 0.03278,
10084
10717
  cacheWrite: 0,
10085
10718
  },
10086
10719
  contextWindow: 1048576,
@@ -10095,14 +10728,31 @@ export const MODELS = {
10095
10728
  reasoning: true,
10096
10729
  input: ["text"],
10097
10730
  cost: {
10098
- input: 1.32,
10099
- output: 3.9600000000000004,
10100
- cacheRead: 0.13,
10731
+ input: 0.66,
10732
+ output: 1.9800000000000002,
10733
+ cacheRead: 0.022,
10101
10734
  cacheWrite: 0,
10102
10735
  },
10103
10736
  contextWindow: 1048576,
10104
10737
  maxTokens: 943718,
10105
10738
  },
10739
+ "deepseek/deepseek-v4.1-flash": {
10740
+ id: "deepseek/deepseek-v4.1-flash",
10741
+ name: "DeepSeek: DeepSeek V4.1 Flash",
10742
+ api: "openai-completions",
10743
+ provider: "openrouter",
10744
+ baseUrl: "https://openrouter.ai/api/v1",
10745
+ reasoning: true,
10746
+ input: ["text", "image"],
10747
+ cost: {
10748
+ input: 0.15,
10749
+ output: 0.6,
10750
+ cacheRead: 0.003,
10751
+ cacheWrite: 0,
10752
+ },
10753
+ contextWindow: 1048576,
10754
+ maxTokens: 384000,
10755
+ },
10106
10756
  "dots-studio/dots-3-note-preview:free": {
10107
10757
  id: "dots-studio/dots-3-note-preview:free",
10108
10758
  name: "Dots Studio: Dots3-Note Preview (free)",
@@ -10622,13 +11272,13 @@ export const MODELS = {
10622
11272
  reasoning: true,
10623
11273
  input: ["text", "image"],
10624
11274
  cost: {
10625
- input: 0.07,
10626
- output: 0.33999999999999997,
10627
- cacheRead: 0,
11275
+ input: 0.09,
11276
+ output: 0.3,
11277
+ cacheRead: 0.049999999999999996,
10628
11278
  cacheWrite: 0,
10629
11279
  },
10630
11280
  contextWindow: 262144,
10631
- maxTokens: 16384,
11281
+ maxTokens: 235929,
10632
11282
  },
10633
11283
  "google/gemma-4-26b-a4b-it:free": {
10634
11284
  id: "google/gemma-4-26b-a4b-it:free",
@@ -10707,9 +11357,9 @@ export const MODELS = {
10707
11357
  reasoning: true,
10708
11358
  input: ["text"],
10709
11359
  cost: {
10710
- input: 0.09999999999999999,
10711
- output: 0.15,
10712
- cacheRead: 0.049999999999999996,
11360
+ input: 0.06,
11361
+ output: 0.25,
11362
+ cacheRead: 0.015,
10713
11363
  cacheWrite: 0,
10714
11364
  },
10715
11365
  contextWindow: 131072,
@@ -10732,9 +11382,9 @@ export const MODELS = {
10732
11382
  contextWindow: 128000,
10733
11383
  maxTokens: 50000,
10734
11384
  },
10735
- "inception/mercury-2.5-preview": {
10736
- id: "inception/mercury-2.5-preview",
10737
- name: "Inception: Mercury 2.5 Preview",
11385
+ "inception/mercury-2.5": {
11386
+ id: "inception/mercury-2.5",
11387
+ name: "Inception: Mercury 2.5",
10738
11388
  api: "openai-completions",
10739
11389
  provider: "openrouter",
10740
11390
  baseUrl: "https://openrouter.ai/api/v1",
@@ -10817,6 +11467,40 @@ export const MODELS = {
10817
11467
  contextWindow: 262144,
10818
11468
  maxTokens: 32768,
10819
11469
  },
11470
+ "inclusionai/ling-3.0-flash-vl": {
11471
+ id: "inclusionai/ling-3.0-flash-vl",
11472
+ name: "inclusionAI: Ling 3.0 Flash VL",
11473
+ api: "openai-completions",
11474
+ provider: "openrouter",
11475
+ baseUrl: "https://openrouter.ai/api/v1",
11476
+ reasoning: true,
11477
+ input: ["text", "image"],
11478
+ cost: {
11479
+ input: 0.06,
11480
+ output: 0.18,
11481
+ cacheRead: 0.012,
11482
+ cacheWrite: 0,
11483
+ },
11484
+ contextWindow: 131072,
11485
+ maxTokens: 32768,
11486
+ },
11487
+ "inclusionai/ling-3.0-flash-vl:free": {
11488
+ id: "inclusionai/ling-3.0-flash-vl:free",
11489
+ name: "inclusionAI: Ling 3.0 Flash VL (free)",
11490
+ api: "openai-completions",
11491
+ provider: "openrouter",
11492
+ baseUrl: "https://openrouter.ai/api/v1",
11493
+ reasoning: true,
11494
+ input: ["text", "image"],
11495
+ cost: {
11496
+ input: 0,
11497
+ output: 0,
11498
+ cacheRead: 0,
11499
+ cacheWrite: 0,
11500
+ },
11501
+ contextWindow: 262144,
11502
+ maxTokens: 32768,
11503
+ },
10820
11504
  "kwaipilot/kat-coder-pro-v2": {
10821
11505
  id: "kwaipilot/kat-coder-pro-v2",
10822
11506
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -10979,8 +11663,8 @@ export const MODELS = {
10979
11663
  reasoning: true,
10980
11664
  input: ["text", "image"],
10981
11665
  cost: {
10982
- input: 0.3,
10983
- output: 1.1,
11666
+ input: 0.35,
11667
+ output: 1.5,
10984
11668
  cacheRead: 0.04,
10985
11669
  cacheWrite: 0,
10986
11670
  },
@@ -10996,9 +11680,9 @@ export const MODELS = {
10996
11680
  reasoning: true,
10997
11681
  input: ["text", "image"],
10998
11682
  cost: {
10999
- input: 0.35,
11000
- output: 1.5,
11001
- cacheRead: 0.04,
11683
+ input: 0.175,
11684
+ output: 0.75,
11685
+ cacheRead: 0.02,
11002
11686
  cacheWrite: 0,
11003
11687
  },
11004
11688
  contextWindow: 131072,
@@ -11098,7 +11782,7 @@ export const MODELS = {
11098
11782
  reasoning: true,
11099
11783
  input: ["text"],
11100
11784
  cost: {
11101
- input: 0.39999999999999997,
11785
+ input: 0.55,
11102
11786
  output: 2.2,
11103
11787
  cacheRead: 0,
11104
11788
  cacheWrite: 0,
@@ -11225,6 +11909,23 @@ export const MODELS = {
11225
11909
  contextWindow: 256000,
11226
11910
  maxTokens: 204800,
11227
11911
  },
11912
+ "mistralai/codestral-2508:batch": {
11913
+ id: "mistralai/codestral-2508:batch",
11914
+ name: "Mistral: Codestral 2508 (batch)",
11915
+ api: "openai-completions",
11916
+ provider: "openrouter",
11917
+ baseUrl: "https://openrouter.ai/api/v1",
11918
+ reasoning: false,
11919
+ input: ["text"],
11920
+ cost: {
11921
+ input: 0.15,
11922
+ output: 0.44999999999999996,
11923
+ cacheRead: 0.015,
11924
+ cacheWrite: 0,
11925
+ },
11926
+ contextWindow: 256000,
11927
+ maxTokens: 204800,
11928
+ },
11228
11929
  "mistralai/devstral-2512": {
11229
11930
  id: "mistralai/devstral-2512",
11230
11931
  name: "Mistral: Devstral 2 2512",
@@ -11293,6 +11994,23 @@ export const MODELS = {
11293
11994
  contextWindow: 262144,
11294
11995
  maxTokens: 209715,
11295
11996
  },
11997
+ "mistralai/ministral-8b-2512:batch": {
11998
+ id: "mistralai/ministral-8b-2512:batch",
11999
+ name: "Mistral: Ministral 3 8B 2512 (batch)",
12000
+ api: "openai-completions",
12001
+ provider: "openrouter",
12002
+ baseUrl: "https://openrouter.ai/api/v1",
12003
+ reasoning: false,
12004
+ input: ["text", "image"],
12005
+ cost: {
12006
+ input: 0.075,
12007
+ output: 0.075,
12008
+ cacheRead: 0.0075,
12009
+ cacheWrite: 0,
12010
+ },
12011
+ contextWindow: 262144,
12012
+ maxTokens: 209715,
12013
+ },
11296
12014
  "mistralai/mistral-large": {
11297
12015
  id: "mistralai/mistral-large",
11298
12016
  name: "Mistral Large",
@@ -11344,6 +12062,23 @@ export const MODELS = {
11344
12062
  contextWindow: 262144,
11345
12063
  maxTokens: 209715,
11346
12064
  },
12065
+ "mistralai/mistral-large-2512:batch": {
12066
+ id: "mistralai/mistral-large-2512:batch",
12067
+ name: "Mistral: Mistral Large 3 2512 (batch)",
12068
+ api: "openai-completions",
12069
+ provider: "openrouter",
12070
+ baseUrl: "https://openrouter.ai/api/v1",
12071
+ reasoning: false,
12072
+ input: ["text", "image"],
12073
+ cost: {
12074
+ input: 0.25,
12075
+ output: 0.75,
12076
+ cacheRead: 0.024999999999999998,
12077
+ cacheWrite: 0,
12078
+ },
12079
+ contextWindow: 262144,
12080
+ maxTokens: 209715,
12081
+ },
11347
12082
  "mistralai/mistral-medium-3": {
11348
12083
  id: "mistralai/mistral-medium-3",
11349
12084
  name: "Mistral: Mistral Medium 3",
@@ -11412,6 +12147,23 @@ export const MODELS = {
11412
12147
  contextWindow: 131072,
11413
12148
  maxTokens: 104857,
11414
12149
  },
12150
+ "mistralai/mistral-medium-3.1:batch": {
12151
+ id: "mistralai/mistral-medium-3.1:batch",
12152
+ name: "Mistral: Mistral Medium 3.1 (batch)",
12153
+ api: "openai-completions",
12154
+ provider: "openrouter",
12155
+ baseUrl: "https://openrouter.ai/api/v1",
12156
+ reasoning: false,
12157
+ input: ["text", "image"],
12158
+ cost: {
12159
+ input: 0.19999999999999998,
12160
+ output: 1,
12161
+ cacheRead: 0.02,
12162
+ cacheWrite: 0,
12163
+ },
12164
+ contextWindow: 131072,
12165
+ maxTokens: 104857,
12166
+ },
11415
12167
  "mistralai/mistral-nemo": {
11416
12168
  id: "mistralai/mistral-nemo",
11417
12169
  name: "Mistral: Mistral Nemo",
@@ -11463,6 +12215,23 @@ export const MODELS = {
11463
12215
  contextWindow: 262144,
11464
12216
  maxTokens: 209715,
11465
12217
  },
12218
+ "mistralai/mistral-small-2603:batch": {
12219
+ id: "mistralai/mistral-small-2603:batch",
12220
+ name: "Mistral: Mistral Small 4 (batch)",
12221
+ api: "openai-completions",
12222
+ provider: "openrouter",
12223
+ baseUrl: "https://openrouter.ai/api/v1",
12224
+ reasoning: true,
12225
+ input: ["text", "image"],
12226
+ cost: {
12227
+ input: 0.075,
12228
+ output: 0.3,
12229
+ cacheRead: 0.0075,
12230
+ cacheWrite: 0,
12231
+ },
12232
+ contextWindow: 262144,
12233
+ maxTokens: 209715,
12234
+ },
11466
12235
  "mistralai/mistral-small-3.2-24b-instruct": {
11467
12236
  id: "mistralai/mistral-small-3.2-24b-instruct",
11468
12237
  name: "Mistral: Mistral Small 3.2 24B",
@@ -11477,7 +12246,7 @@ export const MODELS = {
11477
12246
  cacheRead: 0,
11478
12247
  cacheWrite: 0,
11479
12248
  },
11480
- contextWindow: 131072,
12249
+ contextWindow: 256000,
11481
12250
  maxTokens: 16384,
11482
12251
  },
11483
12252
  "mistralai/mixtral-8x22b-instruct": {
@@ -11529,7 +12298,7 @@ export const MODELS = {
11529
12298
  cacheWrite: 0,
11530
12299
  },
11531
12300
  contextWindow: 131072,
11532
- maxTokens: 100352,
12301
+ maxTokens: 98304,
11533
12302
  },
11534
12303
  "moonshotai/kimi-k2-0905": {
11535
12304
  id: "moonshotai/kimi-k2-0905",
@@ -11546,7 +12315,7 @@ export const MODELS = {
11546
12315
  cacheWrite: 0,
11547
12316
  },
11548
12317
  contextWindow: 262144,
11549
- maxTokens: 100352,
12318
+ maxTokens: 98304,
11550
12319
  },
11551
12320
  "moonshotai/kimi-k2-thinking": {
11552
12321
  id: "moonshotai/kimi-k2-thinking",
@@ -11559,11 +12328,11 @@ export const MODELS = {
11559
12328
  cost: {
11560
12329
  input: 0.6,
11561
12330
  output: 2.5,
11562
- cacheRead: 0,
12331
+ cacheRead: 0.15,
11563
12332
  cacheWrite: 0,
11564
12333
  },
11565
12334
  contextWindow: 262144,
11566
- maxTokens: 235929,
12335
+ maxTokens: 98304,
11567
12336
  },
11568
12337
  "moonshotai/kimi-k2.5": {
11569
12338
  id: "moonshotai/kimi-k2.5",
@@ -11625,9 +12394,9 @@ export const MODELS = {
11625
12394
  reasoning: true,
11626
12395
  input: ["text", "image"],
11627
12396
  cost: {
11628
- input: 3,
11629
- output: 15,
11630
- cacheRead: 0.3,
12397
+ input: 2.6481380629999998,
12398
+ output: 13.282724250000001,
12399
+ cacheRead: 0.30264435,
11631
12400
  cacheWrite: 0,
11632
12401
  },
11633
12402
  contextWindow: 1048576,
@@ -11650,6 +12419,40 @@ export const MODELS = {
11650
12419
  contextWindow: 1048576,
11651
12420
  maxTokens: 943718,
11652
12421
  },
12422
+ "nex-agi/nex-n2.5-mini:free": {
12423
+ id: "nex-agi/nex-n2.5-mini:free",
12424
+ name: "Nex AGI: Nex-N2.5-Mini (free)",
12425
+ api: "openai-completions",
12426
+ provider: "openrouter",
12427
+ baseUrl: "https://openrouter.ai/api/v1",
12428
+ reasoning: true,
12429
+ input: ["text", "image"],
12430
+ cost: {
12431
+ input: 0,
12432
+ output: 0,
12433
+ cacheRead: 0,
12434
+ cacheWrite: 0,
12435
+ },
12436
+ contextWindow: 262144,
12437
+ maxTokens: 235929,
12438
+ },
12439
+ "nex-agi/nex-n2.5-pro:free": {
12440
+ id: "nex-agi/nex-n2.5-pro:free",
12441
+ name: "Nex AGI: Nex-N2.5-Pro (free)",
12442
+ api: "openai-completions",
12443
+ provider: "openrouter",
12444
+ baseUrl: "https://openrouter.ai/api/v1",
12445
+ reasoning: true,
12446
+ input: ["text", "image"],
12447
+ cost: {
12448
+ input: 0,
12449
+ output: 0,
12450
+ cacheRead: 0,
12451
+ cacheWrite: 0,
12452
+ },
12453
+ contextWindow: 262144,
12454
+ maxTokens: 235929,
12455
+ },
11653
12456
  "nvidia/nemotron-3-nano-30b-a3b": {
11654
12457
  id: "nvidia/nemotron-3-nano-30b-a3b",
11655
12458
  name: "NVIDIA: Nemotron 3 Nano 30B A3B",
@@ -11693,13 +12496,13 @@ export const MODELS = {
11693
12496
  reasoning: true,
11694
12497
  input: ["text"],
11695
12498
  cost: {
11696
- input: 0.08499999999999999,
11697
- output: 0.39999999999999997,
12499
+ input: 0.08,
12500
+ output: 0.44999999999999996,
11698
12501
  cacheRead: 0,
11699
12502
  cacheWrite: 0,
11700
12503
  },
11701
- contextWindow: 1000000,
11702
- maxTokens: 16384,
12504
+ contextWindow: 262144,
12505
+ maxTokens: 235929,
11703
12506
  },
11704
12507
  "nvidia/nemotron-3-super-120b-a12b:free": {
11705
12508
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -11727,13 +12530,13 @@ export const MODELS = {
11727
12530
  reasoning: true,
11728
12531
  input: ["text"],
11729
12532
  cost: {
11730
- input: 0.625,
11731
- output: 3.125,
11732
- cacheRead: 0.1875,
12533
+ input: 0.6,
12534
+ output: 2.4,
12535
+ cacheRead: 0.12,
11733
12536
  cacheWrite: 0,
11734
12537
  },
11735
12538
  contextWindow: 262144,
11736
- maxTokens: 32768,
12539
+ maxTokens: 182520,
11737
12540
  },
11738
12541
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
11739
12542
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -13461,13 +14264,13 @@ export const MODELS = {
13461
14264
  reasoning: true,
13462
14265
  input: ["text"],
13463
14266
  cost: {
13464
- input: 0.22749999999999998,
13465
- output: 0.9099999999999999,
14267
+ input: 0.12,
14268
+ output: 0.24,
13466
14269
  cacheRead: 0,
13467
14270
  cacheWrite: 0,
13468
14271
  },
13469
14272
  contextWindow: 131072,
13470
- maxTokens: 8192,
14273
+ maxTokens: 16384,
13471
14274
  },
13472
14275
  "qwen/qwen3-235b-a22b": {
13473
14276
  id: "qwen/qwen3-235b-a22b",
@@ -13495,13 +14298,13 @@ export const MODELS = {
13495
14298
  reasoning: false,
13496
14299
  input: ["text"],
13497
14300
  cost: {
13498
- input: 0.09,
13499
- output: 0.55,
13500
- cacheRead: 0,
14301
+ input: 0.0875,
14302
+ output: 0.35,
14303
+ cacheRead: 0.0175,
13501
14304
  cacheWrite: 0,
13502
14305
  },
13503
14306
  contextWindow: 262144,
13504
- maxTokens: 16384,
14307
+ maxTokens: 235929,
13505
14308
  },
13506
14309
  "qwen/qwen3-235b-a22b-thinking-2507": {
13507
14310
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -13733,13 +14536,13 @@ export const MODELS = {
13733
14536
  reasoning: false,
13734
14537
  input: ["text"],
13735
14538
  cost: {
13736
- input: 0.09999999999999999,
14539
+ input: 0.09,
13737
14540
  output: 1.1,
13738
- cacheRead: 0.07,
14541
+ cacheRead: 0,
13739
14542
  cacheWrite: 0,
13740
14543
  },
13741
14544
  contextWindow: 262144,
13742
- maxTokens: 235929,
14545
+ maxTokens: 16384,
13743
14546
  },
13744
14547
  "qwen/qwen3-next-80b-a3b-thinking": {
13745
14548
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -13886,13 +14689,13 @@ export const MODELS = {
13886
14689
  reasoning: true,
13887
14690
  input: ["text", "image"],
13888
14691
  cost: {
13889
- input: 0.29,
13890
- output: 2.4,
14692
+ input: 0.26,
14693
+ output: 2.08,
13891
14694
  cacheRead: 0,
13892
14695
  cacheWrite: 0,
13893
14696
  },
13894
14697
  contextWindow: 262144,
13895
- maxTokens: 81920,
14698
+ maxTokens: 65536,
13896
14699
  },
13897
14700
  "qwen/qwen3.5-27b": {
13898
14701
  id: "qwen/qwen3.5-27b",
@@ -14181,7 +14984,7 @@ export const MODELS = {
14181
14984
  cacheWrite: 0,
14182
14985
  },
14183
14986
  contextWindow: 1048576,
14184
- maxTokens: 262144,
14987
+ maxTokens: 131072,
14185
14988
  },
14186
14989
  "qwen/qwen3.8-2.4t-a95b:batch": {
14187
14990
  id: "qwen/qwen3.8-2.4t-a95b:batch",
@@ -14209,9 +15012,9 @@ export const MODELS = {
14209
15012
  reasoning: true,
14210
15013
  input: ["text", "image"],
14211
15014
  cost: {
14212
- input: 0.42,
14213
- output: 3,
14214
- cacheRead: 0.08499999999999999,
15015
+ input: 0.21400000000000002,
15016
+ output: 2.5500000000000003,
15017
+ cacheRead: 0.15,
14215
15018
  cacheWrite: 0,
14216
15019
  },
14217
15020
  contextWindow: 1000000,
@@ -14285,6 +15088,23 @@ export const MODELS = {
14285
15088
  contextWindow: 256000,
14286
15089
  maxTokens: 128000,
14287
15090
  },
15091
+ "sakana/fugu-max": {
15092
+ id: "sakana/fugu-max",
15093
+ name: "Sakana: Fugu Max",
15094
+ api: "openai-completions",
15095
+ provider: "openrouter",
15096
+ baseUrl: "https://openrouter.ai/api/v1",
15097
+ reasoning: true,
15098
+ input: ["text", "image"],
15099
+ cost: {
15100
+ input: 2,
15101
+ output: 6,
15102
+ cacheRead: 0.25,
15103
+ cacheWrite: 0,
15104
+ },
15105
+ contextWindow: 1000000,
15106
+ maxTokens: 128000,
15107
+ },
14288
15108
  "sakana/fugu-ultra": {
14289
15109
  id: "sakana/fugu-ultra",
14290
15110
  name: "Sakana: Fugu Ultra",
@@ -14302,6 +15122,23 @@ export const MODELS = {
14302
15122
  contextWindow: 1000000,
14303
15123
  maxTokens: 128000,
14304
15124
  },
15125
+ "sakana/fugu-ultra-v2": {
15126
+ id: "sakana/fugu-ultra-v2",
15127
+ name: "Sakana: Fugu Ultra v2",
15128
+ api: "openai-completions",
15129
+ provider: "openrouter",
15130
+ baseUrl: "https://openrouter.ai/api/v1",
15131
+ reasoning: true,
15132
+ input: ["text", "image"],
15133
+ cost: {
15134
+ input: 5,
15135
+ output: 30,
15136
+ cacheRead: 0.5,
15137
+ cacheWrite: 0,
15138
+ },
15139
+ contextWindow: 1000000,
15140
+ maxTokens: 128000,
15141
+ },
14305
15142
  "sakana/sakana-namazu": {
14306
15143
  id: "sakana/sakana-namazu",
14307
15144
  name: "Sakana: Sakana Namazu",
@@ -14566,9 +15403,9 @@ export const MODELS = {
14566
15403
  reasoning: true,
14567
15404
  input: ["text"],
14568
15405
  cost: {
14569
- input: 0.03,
14570
- output: 0.12,
14571
- cacheRead: 0.006,
15406
+ input: 0.09,
15407
+ output: 0.36,
15408
+ cacheRead: 0.018,
14572
15409
  cacheWrite: 0,
14573
15410
  },
14574
15411
  contextWindow: 524288,
@@ -14770,13 +15607,13 @@ export const MODELS = {
14770
15607
  reasoning: true,
14771
15608
  input: ["text"],
14772
15609
  cost: {
14773
- input: 0.55,
14774
- output: 2.2,
14775
- cacheRead: 0.11,
15610
+ input: 0.43,
15611
+ output: 1.75,
15612
+ cacheRead: 0.08,
14776
15613
  cacheWrite: 0,
14777
15614
  },
14778
15615
  contextWindow: 204800,
14779
- maxTokens: 131072,
15616
+ maxTokens: 16384,
14780
15617
  },
14781
15618
  "z-ai/glm-4.6v": {
14782
15619
  id: "z-ai/glm-4.6v",
@@ -14826,7 +15663,7 @@ export const MODELS = {
14826
15663
  cacheRead: 0,
14827
15664
  cacheWrite: 0,
14828
15665
  },
14829
- contextWindow: 202752,
15666
+ contextWindow: 200000,
14830
15667
  maxTokens: 117964,
14831
15668
  },
14832
15669
  "z-ai/glm-5": {
@@ -14889,14 +15726,31 @@ export const MODELS = {
14889
15726
  reasoning: true,
14890
15727
  input: ["text"],
14891
15728
  cost: {
14892
- input: 0.966,
14893
- output: 3.036,
14894
- cacheRead: 0.1932,
15729
+ input: 0.6832,
15730
+ output: 2.1471999999999998,
15731
+ cacheRead: 0.12688000000000002,
14895
15732
  cacheWrite: 0,
14896
15733
  },
14897
15734
  contextWindow: 1048576,
14898
15735
  maxTokens: 131072,
14899
15736
  },
15737
+ "z-ai/glm-5.2:batch": {
15738
+ id: "z-ai/glm-5.2:batch",
15739
+ name: "Z.ai: GLM 5.2 (batch)",
15740
+ api: "openai-completions",
15741
+ provider: "openrouter",
15742
+ baseUrl: "https://openrouter.ai/api/v1",
15743
+ reasoning: true,
15744
+ input: ["text"],
15745
+ cost: {
15746
+ input: 0.7,
15747
+ output: 2.2,
15748
+ cacheRead: 0.07,
15749
+ cacheWrite: 0,
15750
+ },
15751
+ contextWindow: 1048576,
15752
+ maxTokens: 943718,
15753
+ },
14900
15754
  "z-ai/glm-5.3": {
14901
15755
  id: "z-ai/glm-5.3",
14902
15756
  name: "Z.ai: GLM 5.3",
@@ -14912,7 +15766,7 @@ export const MODELS = {
14912
15766
  cacheWrite: 0,
14913
15767
  },
14914
15768
  contextWindow: 1310720,
14915
- maxTokens: 943718,
15769
+ maxTokens: 943717,
14916
15770
  },
14917
15771
  "z-ai/glm-5.3-flash": {
14918
15772
  id: "z-ai/glm-5.3-flash",
@@ -14923,9 +15777,9 @@ export const MODELS = {
14923
15777
  reasoning: true,
14924
15778
  input: ["text", "image"],
14925
15779
  cost: {
14926
- input: 0.075,
14927
- output: 0.25,
14928
- cacheRead: 0.015,
15780
+ input: 0.15,
15781
+ output: 0.5,
15782
+ cacheRead: 0.03,
14929
15783
  cacheWrite: 0,
14930
15784
  },
14931
15785
  contextWindow: 1310720,
@@ -14940,13 +15794,30 @@ export const MODELS = {
14940
15794
  reasoning: true,
14941
15795
  input: ["text", "image"],
14942
15796
  cost: {
14943
- input: 0.15,
14944
- output: 0.5,
14945
- cacheRead: 0.03,
15797
+ input: 0.075,
15798
+ output: 0.25,
15799
+ cacheRead: 0.015,
14946
15800
  cacheWrite: 0,
14947
15801
  },
14948
- contextWindow: 1048575,
14949
- maxTokens: 943717,
15802
+ contextWindow: 1048576,
15803
+ maxTokens: 943718,
15804
+ },
15805
+ "z-ai/glm-5.3:batch": {
15806
+ id: "z-ai/glm-5.3:batch",
15807
+ name: "Z.ai: GLM 5.3 (batch)",
15808
+ api: "openai-completions",
15809
+ provider: "openrouter",
15810
+ baseUrl: "https://openrouter.ai/api/v1",
15811
+ reasoning: true,
15812
+ input: ["text"],
15813
+ cost: {
15814
+ input: 0.7,
15815
+ output: 2.2,
15816
+ cacheRead: 0.13,
15817
+ cacheWrite: 0,
15818
+ },
15819
+ contextWindow: 1048576,
15820
+ maxTokens: 943718,
14950
15821
  },
14951
15822
  "z-ai/glm-5v-turbo": {
14952
15823
  id: "z-ai/glm-5v-turbo",
@@ -14984,7 +15855,7 @@ export const MODELS = {
14984
15855
  },
14985
15856
  "~anthropic/claude-haiku-latest": {
14986
15857
  id: "~anthropic/claude-haiku-latest",
14987
- name: "Anthropic Claude Haiku Latest",
15858
+ name: "Anthropic: Claude Haiku Latest",
14988
15859
  api: "openai-completions",
14989
15860
  provider: "openrouter",
14990
15861
  baseUrl: "https://openrouter.ai/api/v1",
@@ -15018,7 +15889,7 @@ export const MODELS = {
15018
15889
  },
15019
15890
  "~anthropic/claude-sonnet-latest": {
15020
15891
  id: "~anthropic/claude-sonnet-latest",
15021
- name: "Anthropic Claude Sonnet Latest",
15892
+ name: "Anthropic: Claude Sonnet Latest",
15022
15893
  api: "openai-completions",
15023
15894
  provider: "openrouter",
15024
15895
  baseUrl: "https://openrouter.ai/api/v1",
@@ -15035,16 +15906,16 @@ export const MODELS = {
15035
15906
  },
15036
15907
  "~deepseek/deepseek-v4-flash-latest": {
15037
15908
  id: "~deepseek/deepseek-v4-flash-latest",
15038
- name: "DeepSeek V4 Flash Latest",
15909
+ name: "DeepSeek: DeepSeek V4 Flash Latest",
15039
15910
  api: "openai-completions",
15040
15911
  provider: "openrouter",
15041
15912
  baseUrl: "https://openrouter.ai/api/v1",
15042
15913
  reasoning: true,
15043
15914
  input: ["text"],
15044
15915
  cost: {
15045
- input: 0.049999999999999996,
15046
- output: 0.16,
15047
- cacheRead: 0.013000000000000001,
15916
+ input: 0.04,
15917
+ output: 0.09999999999999999,
15918
+ cacheRead: 0.01,
15048
15919
  cacheWrite: 0,
15049
15920
  },
15050
15921
  contextWindow: 1310720,
@@ -15052,7 +15923,7 @@ export const MODELS = {
15052
15923
  },
15053
15924
  "~google/gemini-flash-latest": {
15054
15925
  id: "~google/gemini-flash-latest",
15055
- name: "Google Gemini Flash Latest",
15926
+ name: "Google: Gemini Flash Latest",
15056
15927
  api: "openai-completions",
15057
15928
  provider: "openrouter",
15058
15929
  baseUrl: "https://openrouter.ai/api/v1",
@@ -15069,7 +15940,7 @@ export const MODELS = {
15069
15940
  },
15070
15941
  "~google/gemini-pro-latest": {
15071
15942
  id: "~google/gemini-pro-latest",
15072
- name: "Google Gemini Pro Latest",
15943
+ name: "Google: Gemini Pro Latest",
15073
15944
  api: "openai-completions",
15074
15945
  provider: "openrouter",
15075
15946
  baseUrl: "https://openrouter.ai/api/v1",
@@ -15086,41 +15957,58 @@ export const MODELS = {
15086
15957
  },
15087
15958
  "~moonshotai/kimi-latest": {
15088
15959
  id: "~moonshotai/kimi-latest",
15089
- name: "MoonshotAI Kimi Latest",
15960
+ name: "MoonshotAI: Kimi Latest",
15090
15961
  api: "openai-completions",
15091
15962
  provider: "openrouter",
15092
15963
  baseUrl: "https://openrouter.ai/api/v1",
15093
15964
  reasoning: true,
15094
15965
  input: ["text", "image"],
15095
15966
  cost: {
15096
- input: 2.5,
15097
- output: 14,
15098
- cacheRead: 0.29,
15967
+ input: 2.0999999999999996,
15968
+ output: 10.950000000000001,
15969
+ cacheRead: 0.22999999999999998,
15099
15970
  cacheWrite: 0,
15100
15971
  },
15101
15972
  contextWindow: 1048576,
15102
15973
  maxTokens: 943718,
15103
15974
  },
15104
- "~openai/gpt-latest": {
15105
- id: "~openai/gpt-latest",
15106
- name: "OpenAI GPT Latest",
15975
+ "~openai/gpt-astra-latest": {
15976
+ id: "~openai/gpt-astra-latest",
15977
+ name: "OpenAI: GPT Astra Latest",
15107
15978
  api: "openai-completions",
15108
15979
  provider: "openrouter",
15109
15980
  baseUrl: "https://openrouter.ai/api/v1",
15110
15981
  reasoning: true,
15111
15982
  input: ["text", "image"],
15112
15983
  cost: {
15113
- input: 2,
15114
- output: 10,
15115
- cacheRead: 0.19999999999999998,
15116
- cacheWrite: 2.5,
15984
+ input: 10,
15985
+ output: 50,
15986
+ cacheRead: 1,
15987
+ cacheWrite: 12.5,
15988
+ },
15989
+ contextWindow: 1050000,
15990
+ maxTokens: 128000,
15991
+ },
15992
+ "~openai/gpt-luna-latest": {
15993
+ id: "~openai/gpt-luna-latest",
15994
+ name: "OpenAI: GPT Luna Latest",
15995
+ api: "openai-completions",
15996
+ provider: "openrouter",
15997
+ baseUrl: "https://openrouter.ai/api/v1",
15998
+ reasoning: true,
15999
+ input: ["text", "image"],
16000
+ cost: {
16001
+ input: 0.19999999999999998,
16002
+ output: 1.2,
16003
+ cacheRead: 0.02,
16004
+ cacheWrite: 0.25,
15117
16005
  },
15118
16006
  contextWindow: 1050000,
15119
16007
  maxTokens: 128000,
15120
16008
  },
15121
16009
  "~openai/gpt-mini-latest": {
15122
16010
  id: "~openai/gpt-mini-latest",
15123
- name: "OpenAI GPT Mini Latest",
16011
+ name: "OpenAI: GPT Mini Latest",
15124
16012
  api: "openai-completions",
15125
16013
  provider: "openrouter",
15126
16014
  baseUrl: "https://openrouter.ai/api/v1",
@@ -15135,6 +16023,40 @@ export const MODELS = {
15135
16023
  contextWindow: 400000,
15136
16024
  maxTokens: 128000,
15137
16025
  },
16026
+ "~openai/gpt-sol-latest": {
16027
+ id: "~openai/gpt-sol-latest",
16028
+ name: "OpenAI: GPT Sol Latest",
16029
+ api: "openai-completions",
16030
+ provider: "openrouter",
16031
+ baseUrl: "https://openrouter.ai/api/v1",
16032
+ reasoning: true,
16033
+ input: ["text", "image"],
16034
+ cost: {
16035
+ input: 2,
16036
+ output: 10,
16037
+ cacheRead: 0.19999999999999998,
16038
+ cacheWrite: 2.5,
16039
+ },
16040
+ contextWindow: 1050000,
16041
+ maxTokens: 128000,
16042
+ },
16043
+ "~openai/gpt-terra-latest": {
16044
+ id: "~openai/gpt-terra-latest",
16045
+ name: "OpenAI: GPT Terra Latest",
16046
+ api: "openai-completions",
16047
+ provider: "openrouter",
16048
+ baseUrl: "https://openrouter.ai/api/v1",
16049
+ reasoning: true,
16050
+ input: ["text", "image"],
16051
+ cost: {
16052
+ input: 2,
16053
+ output: 12,
16054
+ cacheRead: 0.19999999999999998,
16055
+ cacheWrite: 2.5,
16056
+ },
16057
+ contextWindow: 1050000,
16058
+ maxTokens: 128000,
16059
+ },
15138
16060
  "~x-ai/grok-latest": {
15139
16061
  id: "~x-ai/grok-latest",
15140
16062
  name: "xAI: Grok Latest",
@@ -15161,9 +16083,9 @@ export const MODELS = {
15161
16083
  reasoning: true,
15162
16084
  input: ["text", "image"],
15163
16085
  cost: {
15164
- input: 0.07125000000000001,
15165
- output: 0.2375,
15166
- cacheRead: 0.01425,
16086
+ input: 0.075,
16087
+ output: 0.25,
16088
+ cacheRead: 0.015,
15167
16089
  cacheWrite: 0,
15168
16090
  },
15169
16091
  contextWindow: 1310720,
@@ -15178,9 +16100,9 @@ export const MODELS = {
15178
16100
  reasoning: true,
15179
16101
  input: ["text"],
15180
16102
  cost: {
15181
- input: 1.12,
15182
- output: 3.52,
15183
- cacheRead: 0.20800000000000002,
16103
+ input: 0.9199999999999999,
16104
+ output: 3.1372,
16105
+ cacheRead: 0.184,
15184
16106
  cacheWrite: 0,
15185
16107
  },
15186
16108
  contextWindow: 1310720,
@@ -15664,23 +16586,6 @@ export const MODELS = {
15664
16586
  contextWindow: 991000,
15665
16587
  maxTokens: 128000,
15666
16588
  },
15667
- "alibaba/qwen3.8-flash-next": {
15668
- id: "alibaba/qwen3.8-flash-next",
15669
- name: "Qwen 3.8 Flash Next",
15670
- api: "anthropic-messages",
15671
- provider: "vercel-ai-gateway",
15672
- baseUrl: "https://ai-gateway.vercel.sh",
15673
- reasoning: true,
15674
- input: ["text", "image"],
15675
- cost: {
15676
- input: 0.12,
15677
- output: 0.39999999999999997,
15678
- cacheRead: 0.01,
15679
- cacheWrite: 0,
15680
- },
15681
- contextWindow: 1048576,
15682
- maxTokens: 1048576,
15683
- },
15684
16589
  "alibaba/qwen3.8-max": {
15685
16590
  id: "alibaba/qwen3.8-max",
15686
16591
  name: "Qwen 3.8 Max",
@@ -16106,6 +17011,23 @@ export const MODELS = {
16106
17011
  contextWindow: 256000,
16107
17012
  maxTokens: 64000,
16108
17013
  },
17014
+ "bytedance/seed-2.1-turbo": {
17015
+ id: "bytedance/seed-2.1-turbo",
17016
+ name: "Seed 2.1 Turbo",
17017
+ api: "anthropic-messages",
17018
+ provider: "vercel-ai-gateway",
17019
+ baseUrl: "https://ai-gateway.vercel.sh",
17020
+ reasoning: true,
17021
+ input: ["text", "image"],
17022
+ cost: {
17023
+ input: 0.5,
17024
+ output: 2.5,
17025
+ cacheRead: 0.09999999999999999,
17026
+ cacheWrite: 0,
17027
+ },
17028
+ contextWindow: 262144,
17029
+ maxTokens: 262144,
17030
+ },
16109
17031
  "cohere/command-a": {
16110
17032
  id: "cohere/command-a",
16111
17033
  name: "Command A",
@@ -16183,9 +17105,9 @@ export const MODELS = {
16183
17105
  reasoning: false,
16184
17106
  input: ["text"],
16185
17107
  cost: {
16186
- input: 0.28,
16187
- output: 0.42,
16188
- cacheRead: 0.028,
17108
+ input: 0.62,
17109
+ output: 1.85,
17110
+ cacheRead: 0,
16189
17111
  cacheWrite: 0,
16190
17112
  },
16191
17113
  contextWindow: 128000,
@@ -16293,6 +17215,23 @@ export const MODELS = {
16293
17215
  contextWindow: 1000000,
16294
17216
  maxTokens: 384000,
16295
17217
  },
17218
+ "deepseek/deepseek-v4.1-flash": {
17219
+ id: "deepseek/deepseek-v4.1-flash",
17220
+ name: "DeepSeek V4.1 Flash",
17221
+ api: "anthropic-messages",
17222
+ provider: "vercel-ai-gateway",
17223
+ baseUrl: "https://ai-gateway.vercel.sh",
17224
+ reasoning: true,
17225
+ input: ["text", "image"],
17226
+ cost: {
17227
+ input: 0.15,
17228
+ output: 0.6,
17229
+ cacheRead: 0.015,
17230
+ cacheWrite: 0,
17231
+ },
17232
+ contextWindow: 1000000,
17233
+ maxTokens: 384000,
17234
+ },
16296
17235
  "google/gemini-2.5-flash": {
16297
17236
  id: "google/gemini-2.5-flash",
16298
17237
  name: "Gemini 2.5 Flash",
@@ -16531,6 +17470,23 @@ export const MODELS = {
16531
17470
  contextWindow: 128000,
16532
17471
  maxTokens: 128000,
16533
17472
  },
17473
+ "inception/mercury-2.5": {
17474
+ id: "inception/mercury-2.5",
17475
+ name: "Mercury 2.5",
17476
+ api: "anthropic-messages",
17477
+ provider: "vercel-ai-gateway",
17478
+ baseUrl: "https://ai-gateway.vercel.sh",
17479
+ reasoning: true,
17480
+ input: ["text"],
17481
+ cost: {
17482
+ input: 0.04,
17483
+ output: 0.15,
17484
+ cacheRead: 0.004,
17485
+ cacheWrite: 0,
17486
+ },
17487
+ contextWindow: 260000,
17488
+ maxTokens: 65536,
17489
+ },
16534
17490
  "inception/mercury-coder-small": {
16535
17491
  id: "inception/mercury-coder-small",
16536
17492
  name: "Mercury Coder Small Beta",
@@ -16633,6 +17589,40 @@ export const MODELS = {
16633
17589
  contextWindow: 256000,
16634
17590
  maxTokens: 32000,
16635
17591
  },
17592
+ "inclusionai/ling-3.0-flash-vl": {
17593
+ id: "inclusionai/ling-3.0-flash-vl",
17594
+ name: "Ling 3.0 Flash VL",
17595
+ api: "anthropic-messages",
17596
+ provider: "vercel-ai-gateway",
17597
+ baseUrl: "https://ai-gateway.vercel.sh",
17598
+ reasoning: true,
17599
+ input: ["text", "image"],
17600
+ cost: {
17601
+ input: 0,
17602
+ output: 0,
17603
+ cacheRead: 0,
17604
+ cacheWrite: 0,
17605
+ },
17606
+ contextWindow: 256000,
17607
+ maxTokens: 32000,
17608
+ },
17609
+ "inclusionai/ling-3.0-flash-vl-free": {
17610
+ id: "inclusionai/ling-3.0-flash-vl-free",
17611
+ name: "Ling 3.0 Flash VL (Free)",
17612
+ api: "anthropic-messages",
17613
+ provider: "vercel-ai-gateway",
17614
+ baseUrl: "https://ai-gateway.vercel.sh",
17615
+ reasoning: true,
17616
+ input: ["text", "image"],
17617
+ cost: {
17618
+ input: 0,
17619
+ output: 0,
17620
+ cacheRead: 0,
17621
+ cacheWrite: 0,
17622
+ },
17623
+ contextWindow: 256000,
17624
+ maxTokens: 32000,
17625
+ },
16636
17626
  "interfaze/interfaze-beta": {
16637
17627
  id: "interfaze/interfaze-beta",
16638
17628
  name: "Interfaze Beta",
@@ -18503,6 +19493,23 @@ export const MODELS = {
18503
19493
  contextWindow: 256000,
18504
19494
  maxTokens: 32768,
18505
19495
  },
19496
+ "sakana/fugu-max": {
19497
+ id: "sakana/fugu-max",
19498
+ name: "Fugu Max",
19499
+ api: "anthropic-messages",
19500
+ provider: "vercel-ai-gateway",
19501
+ baseUrl: "https://ai-gateway.vercel.sh",
19502
+ reasoning: true,
19503
+ input: ["text", "image"],
19504
+ cost: {
19505
+ input: 2,
19506
+ output: 6,
19507
+ cacheRead: 0.25,
19508
+ cacheWrite: 0,
19509
+ },
19510
+ contextWindow: 1000000,
19511
+ maxTokens: 1000000,
19512
+ },
18506
19513
  "sakana/fugu-ultra": {
18507
19514
  id: "sakana/fugu-ultra",
18508
19515
  name: "Fugu Ultra",
@@ -18520,6 +19527,23 @@ export const MODELS = {
18520
19527
  contextWindow: 1000000,
18521
19528
  maxTokens: 1000000,
18522
19529
  },
19530
+ "sakana/fugu-ultra-v2": {
19531
+ id: "sakana/fugu-ultra-v2",
19532
+ name: "Fugu Ultra v2",
19533
+ api: "anthropic-messages",
19534
+ provider: "vercel-ai-gateway",
19535
+ baseUrl: "https://ai-gateway.vercel.sh",
19536
+ reasoning: true,
19537
+ input: ["text", "image"],
19538
+ cost: {
19539
+ input: 5,
19540
+ output: 30,
19541
+ cacheRead: 0.5,
19542
+ cacheWrite: 0,
19543
+ },
19544
+ contextWindow: 1000000,
19545
+ maxTokens: 1000000,
19546
+ },
18523
19547
  "sakana/namazu": {
18524
19548
  id: "sakana/namazu",
18525
19549
  name: "Sakana Namazu",
@@ -18877,23 +19901,6 @@ export const MODELS = {
18877
19901
  contextWindow: 1050000,
18878
19902
  maxTokens: 131000,
18879
19903
  },
18880
- "xiaomi/mimo-v2.5-pro-ultraspeed": {
18881
- id: "xiaomi/mimo-v2.5-pro-ultraspeed",
18882
- name: "MiMo V2.5 Pro UltraSpeed",
18883
- api: "anthropic-messages",
18884
- provider: "vercel-ai-gateway",
18885
- baseUrl: "https://ai-gateway.vercel.sh",
18886
- reasoning: true,
18887
- input: ["text"],
18888
- cost: {
18889
- input: 1.305,
18890
- output: 2.61,
18891
- cacheRead: 0.0108,
18892
- cacheWrite: 0,
18893
- },
18894
- contextWindow: 1048576,
18895
- maxTokens: 131072,
18896
- },
18897
19904
  "zai/glm-4.5": {
18898
19905
  id: "zai/glm-4.5",
18899
19906
  name: "GLM 4.5",
@@ -19107,9 +20114,9 @@ export const MODELS = {
19107
20114
  reasoning: true,
19108
20115
  input: ["text"],
19109
20116
  cost: {
19110
- input: 0.7,
19111
- output: 2.2,
19112
- cacheRead: 0.13,
20117
+ input: 1.4,
20118
+ output: 4.4,
20119
+ cacheRead: 0.14,
19113
20120
  cacheWrite: 0,
19114
20121
  },
19115
20122
  contextWindow: 1000000,
@@ -19149,23 +20156,6 @@ export const MODELS = {
19149
20156
  contextWindow: 1000000,
19150
20157
  maxTokens: 131000,
19151
20158
  },
19152
- "zai/glm-5.3-promo-50": {
19153
- id: "zai/glm-5.3-promo-50",
19154
- name: "GLM 5.3 (50% off)",
19155
- api: "anthropic-messages",
19156
- provider: "vercel-ai-gateway",
19157
- baseUrl: "https://ai-gateway.vercel.sh",
19158
- reasoning: true,
19159
- input: ["text"],
19160
- cost: {
19161
- input: 0.7,
19162
- output: 2.2,
19163
- cacheRead: 0.13,
19164
- cacheWrite: 0,
19165
- },
19166
- contextWindow: 1048576,
19167
- maxTokens: 1048576,
19168
- },
19169
20159
  "zai/glm-5v-turbo": {
19170
20160
  id: "zai/glm-5v-turbo",
19171
20161
  name: "GLM 5V Turbo",