@draht/ai 2026.4.26 → 2026.5.12

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.
@@ -53,23 +53,6 @@ export const MODELS = {
53
53
  contextWindow: 128000,
54
54
  maxTokens: 8192,
55
55
  },
56
- "amazon.nova-premier-v1:0": {
57
- id: "amazon.nova-premier-v1:0",
58
- name: "Nova Premier",
59
- api: "bedrock-converse-stream",
60
- provider: "amazon-bedrock",
61
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
62
- reasoning: true,
63
- input: ["text", "image"],
64
- cost: {
65
- input: 2.5,
66
- output: 12.5,
67
- cacheRead: 0,
68
- cacheWrite: 0,
69
- },
70
- contextWindow: 1000000,
71
- maxTokens: 16384,
72
- },
73
56
  "amazon.nova-pro-v1:0": {
74
57
  id: "amazon.nova-pro-v1:0",
75
58
  name: "Nova Pro",
@@ -87,91 +70,6 @@ export const MODELS = {
87
70
  contextWindow: 300000,
88
71
  maxTokens: 8192,
89
72
  },
90
- "anthropic.claude-3-5-haiku-20241022-v1:0": {
91
- id: "anthropic.claude-3-5-haiku-20241022-v1:0",
92
- name: "Claude Haiku 3.5",
93
- api: "bedrock-converse-stream",
94
- provider: "amazon-bedrock",
95
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
96
- reasoning: false,
97
- input: ["text", "image"],
98
- cost: {
99
- input: 0.8,
100
- output: 4,
101
- cacheRead: 0.08,
102
- cacheWrite: 1,
103
- },
104
- contextWindow: 200000,
105
- maxTokens: 8192,
106
- },
107
- "anthropic.claude-3-5-sonnet-20240620-v1:0": {
108
- id: "anthropic.claude-3-5-sonnet-20240620-v1:0",
109
- name: "Claude Sonnet 3.5",
110
- api: "bedrock-converse-stream",
111
- provider: "amazon-bedrock",
112
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
113
- reasoning: false,
114
- input: ["text", "image"],
115
- cost: {
116
- input: 3,
117
- output: 15,
118
- cacheRead: 0.3,
119
- cacheWrite: 3.75,
120
- },
121
- contextWindow: 200000,
122
- maxTokens: 8192,
123
- },
124
- "anthropic.claude-3-5-sonnet-20241022-v2:0": {
125
- id: "anthropic.claude-3-5-sonnet-20241022-v2:0",
126
- name: "Claude Sonnet 3.5 v2",
127
- api: "bedrock-converse-stream",
128
- provider: "amazon-bedrock",
129
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
130
- reasoning: false,
131
- input: ["text", "image"],
132
- cost: {
133
- input: 3,
134
- output: 15,
135
- cacheRead: 0.3,
136
- cacheWrite: 3.75,
137
- },
138
- contextWindow: 200000,
139
- maxTokens: 8192,
140
- },
141
- "anthropic.claude-3-7-sonnet-20250219-v1:0": {
142
- id: "anthropic.claude-3-7-sonnet-20250219-v1:0",
143
- name: "Claude Sonnet 3.7",
144
- api: "bedrock-converse-stream",
145
- provider: "amazon-bedrock",
146
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
147
- reasoning: false,
148
- input: ["text", "image"],
149
- cost: {
150
- input: 3,
151
- output: 15,
152
- cacheRead: 0.3,
153
- cacheWrite: 3.75,
154
- },
155
- contextWindow: 200000,
156
- maxTokens: 8192,
157
- },
158
- "anthropic.claude-3-haiku-20240307-v1:0": {
159
- id: "anthropic.claude-3-haiku-20240307-v1:0",
160
- name: "Claude Haiku 3",
161
- api: "bedrock-converse-stream",
162
- provider: "amazon-bedrock",
163
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
164
- reasoning: false,
165
- input: ["text", "image"],
166
- cost: {
167
- input: 0.25,
168
- output: 1.25,
169
- cacheRead: 0,
170
- cacheWrite: 0,
171
- },
172
- contextWindow: 200000,
173
- maxTokens: 4096,
174
- },
175
73
  "anthropic.claude-haiku-4-5-20251001-v1:0": {
176
74
  id: "anthropic.claude-haiku-4-5-20251001-v1:0",
177
75
  name: "Claude Haiku 4.5",
@@ -206,23 +104,6 @@ export const MODELS = {
206
104
  contextWindow: 200000,
207
105
  maxTokens: 32000,
208
106
  },
209
- "anthropic.claude-opus-4-20250514-v1:0": {
210
- id: "anthropic.claude-opus-4-20250514-v1:0",
211
- name: "Claude Opus 4",
212
- api: "bedrock-converse-stream",
213
- provider: "amazon-bedrock",
214
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
215
- reasoning: true,
216
- input: ["text", "image"],
217
- cost: {
218
- input: 15,
219
- output: 75,
220
- cacheRead: 1.5,
221
- cacheWrite: 18.75,
222
- },
223
- contextWindow: 200000,
224
- maxTokens: 32000,
225
- },
226
107
  "anthropic.claude-opus-4-5-20251101-v1:0": {
227
108
  id: "anthropic.claude-opus-4-5-20251101-v1:0",
228
109
  name: "Claude Opus 4.5",
@@ -274,9 +155,9 @@ export const MODELS = {
274
155
  contextWindow: 1000000,
275
156
  maxTokens: 128000,
276
157
  },
277
- "anthropic.claude-sonnet-4-20250514-v1:0": {
278
- id: "anthropic.claude-sonnet-4-20250514-v1:0",
279
- name: "Claude Sonnet 4",
158
+ "anthropic.claude-sonnet-4-5-20250929-v1:0": {
159
+ id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
160
+ name: "Claude Sonnet 4.5",
280
161
  api: "bedrock-converse-stream",
281
162
  provider: "amazon-bedrock",
282
163
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -291,9 +172,9 @@ export const MODELS = {
291
172
  contextWindow: 200000,
292
173
  maxTokens: 64000,
293
174
  },
294
- "anthropic.claude-sonnet-4-5-20250929-v1:0": {
295
- id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
296
- name: "Claude Sonnet 4.5",
175
+ "anthropic.claude-sonnet-4-6": {
176
+ id: "anthropic.claude-sonnet-4-6",
177
+ name: "Claude Sonnet 4.6",
297
178
  api: "bedrock-converse-stream",
298
179
  provider: "amazon-bedrock",
299
180
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -305,24 +186,24 @@ export const MODELS = {
305
186
  cacheRead: 0.3,
306
187
  cacheWrite: 3.75,
307
188
  },
308
- contextWindow: 200000,
189
+ contextWindow: 1000000,
309
190
  maxTokens: 64000,
310
191
  },
311
- "anthropic.claude-sonnet-4-6": {
312
- id: "anthropic.claude-sonnet-4-6",
313
- name: "Claude Sonnet 4.6",
192
+ "au.anthropic.claude-haiku-4-5-20251001-v1:0": {
193
+ id: "au.anthropic.claude-haiku-4-5-20251001-v1:0",
194
+ name: "Claude Haiku 4.5 (AU)",
314
195
  api: "bedrock-converse-stream",
315
196
  provider: "amazon-bedrock",
316
197
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
317
198
  reasoning: true,
318
199
  input: ["text", "image"],
319
200
  cost: {
320
- input: 3,
321
- output: 15,
322
- cacheRead: 0.3,
323
- cacheWrite: 3.75,
201
+ input: 1,
202
+ output: 5,
203
+ cacheRead: 0.1,
204
+ cacheWrite: 1.25,
324
205
  },
325
- contextWindow: 1000000,
206
+ contextWindow: 200000,
326
207
  maxTokens: 64000,
327
208
  },
328
209
  "au.anthropic.claude-opus-4-6-v1": {
@@ -342,6 +223,23 @@ export const MODELS = {
342
223
  contextWindow: 1000000,
343
224
  maxTokens: 128000,
344
225
  },
226
+ "au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
227
+ id: "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
228
+ name: "Claude Sonnet 4.5 (AU)",
229
+ api: "bedrock-converse-stream",
230
+ provider: "amazon-bedrock",
231
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
232
+ reasoning: true,
233
+ input: ["text", "image"],
234
+ cost: {
235
+ input: 3,
236
+ output: 15,
237
+ cacheRead: 0.3,
238
+ cacheWrite: 3.75,
239
+ },
240
+ contextWindow: 200000,
241
+ maxTokens: 64000,
242
+ },
345
243
  "au.anthropic.claude-sonnet-4-6": {
346
244
  id: "au.anthropic.claude-sonnet-4-6",
347
245
  name: "AU Anthropic Claude Sonnet 4.6",
@@ -478,23 +376,6 @@ export const MODELS = {
478
376
  contextWindow: 1000000,
479
377
  maxTokens: 128000,
480
378
  },
481
- "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
482
- id: "eu.anthropic.claude-sonnet-4-20250514-v1:0",
483
- name: "Claude Sonnet 4 (EU)",
484
- api: "bedrock-converse-stream",
485
- provider: "amazon-bedrock",
486
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
487
- reasoning: true,
488
- input: ["text", "image"],
489
- cost: {
490
- input: 3,
491
- output: 15,
492
- cacheRead: 0.3,
493
- cacheWrite: 3.75,
494
- },
495
- contextWindow: 200000,
496
- maxTokens: 64000,
497
- },
498
379
  "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
499
380
  id: "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
500
381
  name: "Claude Sonnet 4.5 (EU)",
@@ -597,23 +478,6 @@ export const MODELS = {
597
478
  contextWindow: 1000000,
598
479
  maxTokens: 128000,
599
480
  },
600
- "global.anthropic.claude-sonnet-4-20250514-v1:0": {
601
- id: "global.anthropic.claude-sonnet-4-20250514-v1:0",
602
- name: "Claude Sonnet 4 (Global)",
603
- api: "bedrock-converse-stream",
604
- provider: "amazon-bedrock",
605
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
606
- reasoning: true,
607
- input: ["text", "image"],
608
- cost: {
609
- input: 3,
610
- output: 15,
611
- cacheRead: 0.3,
612
- cacheWrite: 3.75,
613
- },
614
- contextWindow: 200000,
615
- maxTokens: 64000,
616
- },
617
481
  "global.anthropic.claude-sonnet-4-5-20250929-v1:0": {
618
482
  id: "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
619
483
  name: "Claude Sonnet 4.5 (Global)",
@@ -682,119 +546,85 @@ export const MODELS = {
682
546
  contextWindow: 128000,
683
547
  maxTokens: 4096,
684
548
  },
685
- "meta.llama3-1-405b-instruct-v1:0": {
686
- id: "meta.llama3-1-405b-instruct-v1:0",
687
- name: "Llama 3.1 405B Instruct",
688
- api: "bedrock-converse-stream",
689
- provider: "amazon-bedrock",
690
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
691
- reasoning: false,
692
- input: ["text"],
693
- cost: {
694
- input: 2.4,
695
- output: 2.4,
696
- cacheRead: 0,
697
- cacheWrite: 0,
698
- },
699
- contextWindow: 128000,
700
- maxTokens: 4096,
701
- },
702
- "meta.llama3-1-70b-instruct-v1:0": {
703
- id: "meta.llama3-1-70b-instruct-v1:0",
704
- name: "Llama 3.1 70B Instruct",
549
+ "jp.anthropic.claude-opus-4-7": {
550
+ id: "jp.anthropic.claude-opus-4-7",
551
+ name: "Claude Opus 4.7 (JP)",
705
552
  api: "bedrock-converse-stream",
706
553
  provider: "amazon-bedrock",
707
554
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
708
- reasoning: false,
709
- input: ["text"],
555
+ reasoning: true,
556
+ input: ["text", "image"],
710
557
  cost: {
711
- input: 0.72,
712
- output: 0.72,
713
- cacheRead: 0,
714
- cacheWrite: 0,
558
+ input: 5,
559
+ output: 25,
560
+ cacheRead: 0.5,
561
+ cacheWrite: 6.25,
715
562
  },
716
- contextWindow: 128000,
717
- maxTokens: 4096,
563
+ contextWindow: 1000000,
564
+ maxTokens: 128000,
718
565
  },
719
- "meta.llama3-1-8b-instruct-v1:0": {
720
- id: "meta.llama3-1-8b-instruct-v1:0",
721
- name: "Llama 3.1 8B Instruct",
566
+ "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
567
+ id: "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
568
+ name: "Claude Sonnet 4.5 (JP)",
722
569
  api: "bedrock-converse-stream",
723
570
  provider: "amazon-bedrock",
724
571
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
725
- reasoning: false,
726
- input: ["text"],
572
+ reasoning: true,
573
+ input: ["text", "image"],
727
574
  cost: {
728
- input: 0.22,
729
- output: 0.22,
730
- cacheRead: 0,
731
- cacheWrite: 0,
575
+ input: 3,
576
+ output: 15,
577
+ cacheRead: 0.3,
578
+ cacheWrite: 3.75,
732
579
  },
733
- contextWindow: 128000,
734
- maxTokens: 4096,
580
+ contextWindow: 200000,
581
+ maxTokens: 64000,
735
582
  },
736
- "meta.llama3-2-11b-instruct-v1:0": {
737
- id: "meta.llama3-2-11b-instruct-v1:0",
738
- name: "Llama 3.2 11B Instruct",
583
+ "jp.anthropic.claude-sonnet-4-6": {
584
+ id: "jp.anthropic.claude-sonnet-4-6",
585
+ name: "Claude Sonnet 4.6 (JP)",
739
586
  api: "bedrock-converse-stream",
740
587
  provider: "amazon-bedrock",
741
588
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
742
- reasoning: false,
589
+ reasoning: true,
743
590
  input: ["text", "image"],
744
591
  cost: {
745
- input: 0.16,
746
- output: 0.16,
747
- cacheRead: 0,
748
- cacheWrite: 0,
592
+ input: 3,
593
+ output: 15,
594
+ cacheRead: 0.3,
595
+ cacheWrite: 3.75,
749
596
  },
750
- contextWindow: 128000,
751
- maxTokens: 4096,
597
+ contextWindow: 1000000,
598
+ maxTokens: 64000,
752
599
  },
753
- "meta.llama3-2-1b-instruct-v1:0": {
754
- id: "meta.llama3-2-1b-instruct-v1:0",
755
- name: "Llama 3.2 1B Instruct",
600
+ "meta.llama3-1-70b-instruct-v1:0": {
601
+ id: "meta.llama3-1-70b-instruct-v1:0",
602
+ name: "Llama 3.1 70B Instruct",
756
603
  api: "bedrock-converse-stream",
757
604
  provider: "amazon-bedrock",
758
605
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
759
606
  reasoning: false,
760
607
  input: ["text"],
761
608
  cost: {
762
- input: 0.1,
763
- output: 0.1,
609
+ input: 0.72,
610
+ output: 0.72,
764
611
  cacheRead: 0,
765
612
  cacheWrite: 0,
766
613
  },
767
- contextWindow: 131000,
614
+ contextWindow: 128000,
768
615
  maxTokens: 4096,
769
616
  },
770
- "meta.llama3-2-3b-instruct-v1:0": {
771
- id: "meta.llama3-2-3b-instruct-v1:0",
772
- name: "Llama 3.2 3B Instruct",
617
+ "meta.llama3-1-8b-instruct-v1:0": {
618
+ id: "meta.llama3-1-8b-instruct-v1:0",
619
+ name: "Llama 3.1 8B Instruct",
773
620
  api: "bedrock-converse-stream",
774
621
  provider: "amazon-bedrock",
775
622
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
776
623
  reasoning: false,
777
624
  input: ["text"],
778
625
  cost: {
779
- input: 0.15,
780
- output: 0.15,
781
- cacheRead: 0,
782
- cacheWrite: 0,
783
- },
784
- contextWindow: 131000,
785
- maxTokens: 4096,
786
- },
787
- "meta.llama3-2-90b-instruct-v1:0": {
788
- id: "meta.llama3-2-90b-instruct-v1:0",
789
- name: "Llama 3.2 90B Instruct",
790
- api: "bedrock-converse-stream",
791
- provider: "amazon-bedrock",
792
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
793
- reasoning: false,
794
- input: ["text", "image"],
795
- cost: {
796
- input: 0.72,
797
- output: 0.72,
626
+ input: 0.22,
627
+ output: 0.22,
798
628
  cacheRead: 0,
799
629
  cacheWrite: 0,
800
630
  },
@@ -1379,23 +1209,6 @@ export const MODELS = {
1379
1209
  contextWindow: 200000,
1380
1210
  maxTokens: 32000,
1381
1211
  },
1382
- "us.anthropic.claude-opus-4-20250514-v1:0": {
1383
- id: "us.anthropic.claude-opus-4-20250514-v1:0",
1384
- name: "Claude Opus 4 (US)",
1385
- api: "bedrock-converse-stream",
1386
- provider: "amazon-bedrock",
1387
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1388
- reasoning: true,
1389
- input: ["text", "image"],
1390
- cost: {
1391
- input: 15,
1392
- output: 75,
1393
- cacheRead: 1.5,
1394
- cacheWrite: 18.75,
1395
- },
1396
- contextWindow: 200000,
1397
- maxTokens: 32000,
1398
- },
1399
1212
  "us.anthropic.claude-opus-4-5-20251101-v1:0": {
1400
1213
  id: "us.anthropic.claude-opus-4-5-20251101-v1:0",
1401
1214
  name: "Claude Opus 4.5 (US)",
@@ -1447,9 +1260,9 @@ export const MODELS = {
1447
1260
  contextWindow: 1000000,
1448
1261
  maxTokens: 128000,
1449
1262
  },
1450
- "us.anthropic.claude-sonnet-4-20250514-v1:0": {
1451
- id: "us.anthropic.claude-sonnet-4-20250514-v1:0",
1452
- name: "Claude Sonnet 4 (US)",
1263
+ "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
1264
+ id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
1265
+ name: "Claude Sonnet 4.5 (US)",
1453
1266
  api: "bedrock-converse-stream",
1454
1267
  provider: "amazon-bedrock",
1455
1268
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1464,9 +1277,9 @@ export const MODELS = {
1464
1277
  contextWindow: 200000,
1465
1278
  maxTokens: 64000,
1466
1279
  },
1467
- "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
1468
- id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
1469
- name: "Claude Sonnet 4.5 (US)",
1280
+ "us.anthropic.claude-sonnet-4-6": {
1281
+ id: "us.anthropic.claude-sonnet-4-6",
1282
+ name: "Claude Sonnet 4.6 (US)",
1470
1283
  api: "bedrock-converse-stream",
1471
1284
  provider: "amazon-bedrock",
1472
1285
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1478,25 +1291,59 @@ export const MODELS = {
1478
1291
  cacheRead: 0.3,
1479
1292
  cacheWrite: 3.75,
1480
1293
  },
1481
- contextWindow: 200000,
1294
+ contextWindow: 1000000,
1482
1295
  maxTokens: 64000,
1483
1296
  },
1484
- "us.anthropic.claude-sonnet-4-6": {
1485
- id: "us.anthropic.claude-sonnet-4-6",
1486
- name: "Claude Sonnet 4.6 (US)",
1297
+ "us.deepseek.r1-v1:0": {
1298
+ id: "us.deepseek.r1-v1:0",
1299
+ name: "DeepSeek-R1 (US)",
1487
1300
  api: "bedrock-converse-stream",
1488
1301
  provider: "amazon-bedrock",
1489
1302
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1490
1303
  reasoning: true,
1304
+ input: ["text"],
1305
+ cost: {
1306
+ input: 1.35,
1307
+ output: 5.4,
1308
+ cacheRead: 0,
1309
+ cacheWrite: 0,
1310
+ },
1311
+ contextWindow: 128000,
1312
+ maxTokens: 32768,
1313
+ },
1314
+ "us.meta.llama4-maverick-17b-instruct-v1:0": {
1315
+ id: "us.meta.llama4-maverick-17b-instruct-v1:0",
1316
+ name: "Llama 4 Maverick 17B Instruct (US)",
1317
+ api: "bedrock-converse-stream",
1318
+ provider: "amazon-bedrock",
1319
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1320
+ reasoning: false,
1491
1321
  input: ["text", "image"],
1492
1322
  cost: {
1493
- input: 3,
1494
- output: 15,
1495
- cacheRead: 0.3,
1496
- cacheWrite: 3.75,
1323
+ input: 0.24,
1324
+ output: 0.97,
1325
+ cacheRead: 0,
1326
+ cacheWrite: 0,
1497
1327
  },
1498
1328
  contextWindow: 1000000,
1499
- maxTokens: 64000,
1329
+ maxTokens: 16384,
1330
+ },
1331
+ "us.meta.llama4-scout-17b-instruct-v1:0": {
1332
+ id: "us.meta.llama4-scout-17b-instruct-v1:0",
1333
+ name: "Llama 4 Scout 17B Instruct (US)",
1334
+ api: "bedrock-converse-stream",
1335
+ provider: "amazon-bedrock",
1336
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1337
+ reasoning: false,
1338
+ input: ["text", "image"],
1339
+ cost: {
1340
+ input: 0.17,
1341
+ output: 0.66,
1342
+ cacheRead: 0,
1343
+ cacheWrite: 0,
1344
+ },
1345
+ contextWindow: 3500000,
1346
+ maxTokens: 16384,
1500
1347
  },
1501
1348
  "writer.palmyra-x4-v1:0": {
1502
1349
  id: "writer.palmyra-x4-v1:0",
@@ -2537,7 +2384,24 @@ export const MODELS = {
2537
2384
  cacheWrite: 0,
2538
2385
  },
2539
2386
  contextWindow: 1050000,
2540
- maxTokens: 130000,
2387
+ maxTokens: 128000,
2388
+ },
2389
+ "gpt-5.5-pro": {
2390
+ id: "gpt-5.5-pro",
2391
+ name: "GPT-5.5 Pro",
2392
+ api: "azure-openai-responses",
2393
+ provider: "azure-openai-responses",
2394
+ baseUrl: "",
2395
+ reasoning: true,
2396
+ input: ["text", "image"],
2397
+ cost: {
2398
+ input: 30,
2399
+ output: 180,
2400
+ cacheRead: 0,
2401
+ cacheWrite: 0,
2402
+ },
2403
+ contextWindow: 1050000,
2404
+ maxTokens: 128000,
2541
2405
  },
2542
2406
  "o1": {
2543
2407
  id: "o1",
@@ -2819,24 +2683,6 @@ export const MODELS = {
2819
2683
  contextWindow: 144000,
2820
2684
  maxTokens: 64000,
2821
2685
  },
2822
- "claude-sonnet-4": {
2823
- id: "claude-sonnet-4",
2824
- name: "Claude Sonnet 4",
2825
- api: "anthropic-messages",
2826
- provider: "github-copilot",
2827
- baseUrl: "https://api.individual.githubcopilot.com",
2828
- headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
2829
- reasoning: true,
2830
- input: ["text", "image"],
2831
- cost: {
2832
- input: 0,
2833
- output: 0,
2834
- cacheRead: 0,
2835
- cacheWrite: 0,
2836
- },
2837
- contextWindow: 216000,
2838
- maxTokens: 16000,
2839
- },
2840
2686
  "claude-sonnet-4.5": {
2841
2687
  id: "claude-sonnet-4.5",
2842
2688
  name: "Claude Sonnet 4.5",
@@ -2911,25 +2757,6 @@ export const MODELS = {
2911
2757
  contextWindow: 128000,
2912
2758
  maxTokens: 64000,
2913
2759
  },
2914
- "gemini-3-pro-preview": {
2915
- id: "gemini-3-pro-preview",
2916
- name: "Gemini 3 Pro Preview",
2917
- api: "openai-completions",
2918
- provider: "github-copilot",
2919
- baseUrl: "https://api.individual.githubcopilot.com",
2920
- headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
2921
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2922
- reasoning: true,
2923
- input: ["text", "image"],
2924
- cost: {
2925
- input: 0,
2926
- output: 0,
2927
- cacheRead: 0,
2928
- cacheWrite: 0,
2929
- },
2930
- contextWindow: 128000,
2931
- maxTokens: 64000,
2932
- },
2933
2760
  "gemini-3.1-pro-preview": {
2934
2761
  id: "gemini-3.1-pro-preview",
2935
2762
  name: "Gemini 3.1 Pro Preview",
@@ -2987,24 +2814,6 @@ export const MODELS = {
2987
2814
  contextWindow: 128000,
2988
2815
  maxTokens: 4096,
2989
2816
  },
2990
- "gpt-5": {
2991
- id: "gpt-5",
2992
- name: "GPT-5",
2993
- api: "openai-responses",
2994
- provider: "github-copilot",
2995
- baseUrl: "https://api.individual.githubcopilot.com",
2996
- headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
2997
- reasoning: true,
2998
- input: ["text", "image"],
2999
- cost: {
3000
- input: 0,
3001
- output: 0,
3002
- cacheRead: 0,
3003
- cacheWrite: 0,
3004
- },
3005
- contextWindow: 128000,
3006
- maxTokens: 128000,
3007
- },
3008
2817
  "gpt-5-mini": {
3009
2818
  id: "gpt-5-mini",
3010
2819
  name: "GPT-5-mini",
@@ -3020,80 +2829,8 @@ export const MODELS = {
3020
2829
  cacheRead: 0,
3021
2830
  cacheWrite: 0,
3022
2831
  },
3023
- contextWindow: 264000,
3024
- maxTokens: 64000,
3025
- },
3026
- "gpt-5.1": {
3027
- id: "gpt-5.1",
3028
- name: "GPT-5.1",
3029
- api: "openai-responses",
3030
- provider: "github-copilot",
3031
- baseUrl: "https://api.individual.githubcopilot.com",
3032
- headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3033
- reasoning: true,
3034
- input: ["text", "image"],
3035
- cost: {
3036
- input: 0,
3037
- output: 0,
3038
- cacheRead: 0,
3039
- cacheWrite: 0,
3040
- },
3041
- contextWindow: 264000,
3042
- maxTokens: 64000,
3043
- },
3044
- "gpt-5.1-codex": {
3045
- id: "gpt-5.1-codex",
3046
- name: "GPT-5.1-Codex",
3047
- api: "openai-responses",
3048
- provider: "github-copilot",
3049
- baseUrl: "https://api.individual.githubcopilot.com",
3050
- headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3051
- reasoning: true,
3052
- input: ["text", "image"],
3053
- cost: {
3054
- input: 0,
3055
- output: 0,
3056
- cacheRead: 0,
3057
- cacheWrite: 0,
3058
- },
3059
- contextWindow: 400000,
3060
- maxTokens: 128000,
3061
- },
3062
- "gpt-5.1-codex-max": {
3063
- id: "gpt-5.1-codex-max",
3064
- name: "GPT-5.1-Codex-max",
3065
- api: "openai-responses",
3066
- provider: "github-copilot",
3067
- baseUrl: "https://api.individual.githubcopilot.com",
3068
- headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3069
- reasoning: true,
3070
- input: ["text", "image"],
3071
- cost: {
3072
- input: 0,
3073
- output: 0,
3074
- cacheRead: 0,
3075
- cacheWrite: 0,
3076
- },
3077
- contextWindow: 400000,
3078
- maxTokens: 128000,
3079
- },
3080
- "gpt-5.1-codex-mini": {
3081
- id: "gpt-5.1-codex-mini",
3082
- name: "GPT-5.1-Codex-mini",
3083
- api: "openai-responses",
3084
- provider: "github-copilot",
3085
- baseUrl: "https://api.individual.githubcopilot.com",
3086
- headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3087
- reasoning: true,
3088
- input: ["text", "image"],
3089
- cost: {
3090
- input: 0,
3091
- output: 0,
3092
- cacheRead: 0,
3093
- cacheWrite: 0,
3094
- },
3095
- contextWindow: 400000,
3096
- maxTokens: 128000,
2832
+ contextWindow: 264000,
2833
+ maxTokens: 64000,
3097
2834
  },
3098
2835
  "gpt-5.2": {
3099
2836
  id: "gpt-5.2",
@@ -3513,6 +3250,23 @@ export const MODELS = {
3513
3250
  contextWindow: 1000000,
3514
3251
  maxTokens: 64000,
3515
3252
  },
3253
+ "gemini-3.1-flash-lite": {
3254
+ id: "gemini-3.1-flash-lite",
3255
+ name: "Gemini 3.1 Flash Lite",
3256
+ api: "google-generative-ai",
3257
+ provider: "google",
3258
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3259
+ reasoning: true,
3260
+ input: ["text", "image"],
3261
+ cost: {
3262
+ input: 0.25,
3263
+ output: 1.5,
3264
+ cacheRead: 0.025,
3265
+ cacheWrite: 1,
3266
+ },
3267
+ contextWindow: 1048576,
3268
+ maxTokens: 65536,
3269
+ },
3516
3270
  "gemini-3.1-flash-lite-preview": {
3517
3271
  id: "gemini-3.1-flash-lite-preview",
3518
3272
  name: "Gemini 3.1 Flash Lite Preview",
@@ -4691,6 +4445,24 @@ export const MODELS = {
4691
4445
  contextWindow: 163840,
4692
4446
  maxTokens: 65536,
4693
4447
  },
4448
+ "deepseek-ai/DeepSeek-V4-Pro": {
4449
+ id: "deepseek-ai/DeepSeek-V4-Pro",
4450
+ name: "DeepSeek V4 Pro",
4451
+ api: "openai-completions",
4452
+ provider: "huggingface",
4453
+ baseUrl: "https://router.huggingface.co/v1",
4454
+ compat: { "supportsDeveloperRole": false },
4455
+ reasoning: true,
4456
+ input: ["text"],
4457
+ cost: {
4458
+ input: 1.74,
4459
+ output: 3.48,
4460
+ cacheRead: 0.145,
4461
+ cacheWrite: 0,
4462
+ },
4463
+ contextWindow: 1048576,
4464
+ maxTokens: 393216,
4465
+ },
4694
4466
  "moonshotai/Kimi-K2-Instruct": {
4695
4467
  id: "moonshotai/Kimi-K2-Instruct",
4696
4468
  name: "Kimi-K2-Instruct",
@@ -5252,22 +5024,39 @@ export const MODELS = {
5252
5024
  contextWindow: 262144,
5253
5025
  maxTokens: 262144,
5254
5026
  },
5027
+ "mistral-medium-2604": {
5028
+ id: "mistral-medium-2604",
5029
+ name: "Mistral Medium 3.5",
5030
+ api: "openai-completions",
5031
+ provider: "mistral",
5032
+ baseUrl: "https://api.mistral.ai/v1",
5033
+ reasoning: true,
5034
+ input: ["text", "image"],
5035
+ cost: {
5036
+ input: 1.5,
5037
+ output: 7.5,
5038
+ cacheRead: 0,
5039
+ cacheWrite: 0,
5040
+ },
5041
+ contextWindow: 262144,
5042
+ maxTokens: 262144,
5043
+ },
5255
5044
  "mistral-medium-latest": {
5256
5045
  id: "mistral-medium-latest",
5257
5046
  name: "Mistral Medium (latest)",
5258
5047
  api: "openai-completions",
5259
5048
  provider: "mistral",
5260
5049
  baseUrl: "https://api.mistral.ai/v1",
5261
- reasoning: false,
5050
+ reasoning: true,
5262
5051
  input: ["text", "image"],
5263
5052
  cost: {
5264
- input: 0.4,
5265
- output: 2,
5053
+ input: 1.5,
5054
+ output: 7.5,
5266
5055
  cacheRead: 0,
5267
5056
  cacheWrite: 0,
5268
5057
  },
5269
- contextWindow: 128000,
5270
- maxTokens: 16384,
5058
+ contextWindow: 262144,
5059
+ maxTokens: 262144,
5271
5060
  },
5272
5061
  "mistral-nemo": {
5273
5062
  id: "mistral-nemo",
@@ -5983,7 +5772,24 @@ export const MODELS = {
5983
5772
  cacheWrite: 0,
5984
5773
  },
5985
5774
  contextWindow: 1050000,
5986
- maxTokens: 130000,
5775
+ maxTokens: 128000,
5776
+ },
5777
+ "gpt-5.5-pro": {
5778
+ id: "gpt-5.5-pro",
5779
+ name: "GPT-5.5 Pro",
5780
+ api: "openai-responses",
5781
+ provider: "openai",
5782
+ baseUrl: "https://api.openai.com/v1",
5783
+ reasoning: true,
5784
+ input: ["text", "image"],
5785
+ cost: {
5786
+ input: 30,
5787
+ output: 180,
5788
+ cacheRead: 0,
5789
+ cacheWrite: 0,
5790
+ },
5791
+ contextWindow: 1050000,
5792
+ maxTokens: 128000,
5987
5793
  },
5988
5794
  "o1": {
5989
5795
  id: "o1",
@@ -6281,9 +6087,9 @@ export const MODELS = {
6281
6087
  "big-pickle": {
6282
6088
  id: "big-pickle",
6283
6089
  name: "Big Pickle",
6284
- api: "anthropic-messages",
6090
+ api: "openai-completions",
6285
6091
  provider: "opencode",
6286
- baseUrl: "https://opencode.ai/zen",
6092
+ baseUrl: "https://opencode.ai/zen/v1",
6287
6093
  reasoning: true,
6288
6094
  input: ["text"],
6289
6095
  cost: {
@@ -6295,23 +6101,6 @@ export const MODELS = {
6295
6101
  contextWindow: 200000,
6296
6102
  maxTokens: 128000,
6297
6103
  },
6298
- "claude-3-5-haiku": {
6299
- id: "claude-3-5-haiku",
6300
- name: "Claude Haiku 3.5",
6301
- api: "anthropic-messages",
6302
- provider: "opencode",
6303
- baseUrl: "https://opencode.ai/zen",
6304
- reasoning: false,
6305
- input: ["text", "image"],
6306
- cost: {
6307
- input: 0.8,
6308
- output: 4,
6309
- cacheRead: 0.08,
6310
- cacheWrite: 1,
6311
- },
6312
- contextWindow: 200000,
6313
- maxTokens: 8192,
6314
- },
6315
6104
  "claude-haiku-4-5": {
6316
6105
  id: "claude-haiku-4-5",
6317
6106
  name: "Claude Haiku 4.5",
@@ -6448,6 +6237,23 @@ export const MODELS = {
6448
6237
  contextWindow: 1000000,
6449
6238
  maxTokens: 64000,
6450
6239
  },
6240
+ "deepseek-v4-flash-free": {
6241
+ id: "deepseek-v4-flash-free",
6242
+ name: "DeepSeek V4 Flash Free",
6243
+ api: "openai-completions",
6244
+ provider: "opencode",
6245
+ baseUrl: "https://opencode.ai/zen/v1",
6246
+ reasoning: true,
6247
+ input: ["text"],
6248
+ cost: {
6249
+ input: 0,
6250
+ output: 0,
6251
+ cacheRead: 0,
6252
+ cacheWrite: 0,
6253
+ },
6254
+ contextWindow: 1000000,
6255
+ maxTokens: 384000,
6256
+ },
6451
6257
  "gemini-3-flash": {
6452
6258
  id: "gemini-3-flash",
6453
6259
  name: "Gemini 3 Flash",
@@ -6559,9 +6365,9 @@ export const MODELS = {
6559
6365
  reasoning: true,
6560
6366
  input: ["text", "image"],
6561
6367
  cost: {
6562
- input: 0,
6563
- output: 0,
6564
- cacheRead: 0,
6368
+ input: 0.05,
6369
+ output: 0.4,
6370
+ cacheRead: 0.005,
6565
6371
  cacheWrite: 0,
6566
6372
  },
6567
6373
  contextWindow: 400000,
@@ -6769,7 +6575,7 @@ export const MODELS = {
6769
6575
  cacheWrite: 0,
6770
6576
  },
6771
6577
  contextWindow: 1050000,
6772
- maxTokens: 130000,
6578
+ maxTokens: 128000,
6773
6579
  },
6774
6580
  "gpt-5.5-pro": {
6775
6581
  id: "gpt-5.5-pro",
@@ -6788,23 +6594,6 @@ export const MODELS = {
6788
6594
  contextWindow: 1050000,
6789
6595
  maxTokens: 128000,
6790
6596
  },
6791
- "hy3-preview-free": {
6792
- id: "hy3-preview-free",
6793
- name: "Hy3 preview Free",
6794
- api: "openai-completions",
6795
- provider: "opencode",
6796
- baseUrl: "https://opencode.ai/zen/v1",
6797
- reasoning: true,
6798
- input: ["text"],
6799
- cost: {
6800
- input: 0,
6801
- output: 0,
6802
- cacheRead: 0,
6803
- cacheWrite: 0,
6804
- },
6805
- contextWindow: 256000,
6806
- maxTokens: 64000,
6807
- },
6808
6597
  "kimi-k2.5": {
6809
6598
  id: "kimi-k2.5",
6810
6599
  name: "Kimi K2.5",
@@ -6839,23 +6628,6 @@ export const MODELS = {
6839
6628
  contextWindow: 262144,
6840
6629
  maxTokens: 65536,
6841
6630
  },
6842
- "ling-2.6-flash-free": {
6843
- id: "ling-2.6-flash-free",
6844
- name: "Ling 2.6 Flash Free",
6845
- api: "openai-completions",
6846
- provider: "opencode",
6847
- baseUrl: "https://opencode.ai/zen/v1",
6848
- reasoning: false,
6849
- input: ["text"],
6850
- cost: {
6851
- input: 0,
6852
- output: 0,
6853
- cacheRead: 0,
6854
- cacheWrite: 0,
6855
- },
6856
- contextWindow: 262100,
6857
- maxTokens: 32800,
6858
- },
6859
6631
  "minimax-m2.5": {
6860
6632
  id: "minimax-m2.5",
6861
6633
  name: "MiniMax M2.5",
@@ -6958,6 +6730,23 @@ export const MODELS = {
6958
6730
  contextWindow: 262144,
6959
6731
  maxTokens: 65536,
6960
6732
  },
6733
+ "ring-2.6-1t-free": {
6734
+ id: "ring-2.6-1t-free",
6735
+ name: "Ring 2.6 1T Free",
6736
+ api: "openai-completions",
6737
+ provider: "opencode",
6738
+ baseUrl: "https://opencode.ai/zen/v1",
6739
+ reasoning: true,
6740
+ input: ["text"],
6741
+ cost: {
6742
+ input: 0,
6743
+ output: 0,
6744
+ cacheRead: 0,
6745
+ cacheWrite: 0,
6746
+ },
6747
+ contextWindow: 262000,
6748
+ maxTokens: 66000,
6749
+ },
6961
6750
  },
6962
6751
  "opencode-go": {
6963
6752
  "deepseek-v4-flash": {
@@ -6971,7 +6760,7 @@ export const MODELS = {
6971
6760
  cost: {
6972
6761
  input: 0.14,
6973
6762
  output: 0.28,
6974
- cacheRead: 0.028,
6763
+ cacheRead: 0.0028,
6975
6764
  cacheWrite: 0,
6976
6765
  },
6977
6766
  contextWindow: 1000000,
@@ -6988,7 +6777,7 @@ export const MODELS = {
6988
6777
  cost: {
6989
6778
  input: 1.74,
6990
6779
  output: 3.48,
6991
- cacheRead: 0.145,
6780
+ cacheRead: 0.0145,
6992
6781
  cacheWrite: 0,
6993
6782
  },
6994
6783
  contextWindow: 1000000,
@@ -7008,8 +6797,8 @@ export const MODELS = {
7008
6797
  cacheRead: 0.2,
7009
6798
  cacheWrite: 0,
7010
6799
  },
7011
- contextWindow: 204800,
7012
- maxTokens: 131072,
6800
+ contextWindow: 202752,
6801
+ maxTokens: 32768,
7013
6802
  },
7014
6803
  "glm-5.1": {
7015
6804
  id: "glm-5.1",
@@ -7025,8 +6814,8 @@ export const MODELS = {
7025
6814
  cacheRead: 0.26,
7026
6815
  cacheWrite: 0,
7027
6816
  },
7028
- contextWindow: 204800,
7029
- maxTokens: 131072,
6817
+ contextWindow: 202752,
6818
+ maxTokens: 32768,
7030
6819
  },
7031
6820
  "kimi-k2.5": {
7032
6821
  id: "kimi-k2.5",
@@ -7047,55 +6836,21 @@ export const MODELS = {
7047
6836
  },
7048
6837
  "kimi-k2.6": {
7049
6838
  id: "kimi-k2.6",
7050
- name: "Kimi K2.6 (3x limits)",
6839
+ name: "Kimi K2.6",
7051
6840
  api: "openai-completions",
7052
6841
  provider: "opencode-go",
7053
6842
  baseUrl: "https://opencode.ai/zen/go/v1",
7054
6843
  reasoning: true,
7055
6844
  input: ["text", "image"],
7056
6845
  cost: {
7057
- input: 0.32,
7058
- output: 1.34,
7059
- cacheRead: 0.054,
6846
+ input: 0.95,
6847
+ output: 4,
6848
+ cacheRead: 0.16,
7060
6849
  cacheWrite: 0,
7061
6850
  },
7062
6851
  contextWindow: 262144,
7063
6852
  maxTokens: 65536,
7064
6853
  },
7065
- "mimo-v2-omni": {
7066
- id: "mimo-v2-omni",
7067
- name: "MiMo V2 Omni",
7068
- api: "openai-completions",
7069
- provider: "opencode-go",
7070
- baseUrl: "https://opencode.ai/zen/go/v1",
7071
- reasoning: true,
7072
- input: ["text", "image"],
7073
- cost: {
7074
- input: 0.4,
7075
- output: 2,
7076
- cacheRead: 0.08,
7077
- cacheWrite: 0,
7078
- },
7079
- contextWindow: 262144,
7080
- maxTokens: 128000,
7081
- },
7082
- "mimo-v2-pro": {
7083
- id: "mimo-v2-pro",
7084
- name: "MiMo V2 Pro",
7085
- api: "openai-completions",
7086
- provider: "opencode-go",
7087
- baseUrl: "https://opencode.ai/zen/go/v1",
7088
- reasoning: true,
7089
- input: ["text"],
7090
- cost: {
7091
- input: 1,
7092
- output: 3,
7093
- cacheRead: 0.2,
7094
- cacheWrite: 0,
7095
- },
7096
- contextWindow: 1048576,
7097
- maxTokens: 128000,
7098
- },
7099
6854
  "mimo-v2.5": {
7100
6855
  id: "mimo-v2.5",
7101
6856
  name: "MiMo V2.5",
@@ -7110,7 +6865,7 @@ export const MODELS = {
7110
6865
  cacheRead: 0.08,
7111
6866
  cacheWrite: 0,
7112
6867
  },
7113
- contextWindow: 262144,
6868
+ contextWindow: 1000000,
7114
6869
  maxTokens: 128000,
7115
6870
  },
7116
6871
  "mimo-v2.5-pro": {
@@ -7234,23 +6989,6 @@ export const MODELS = {
7234
6989
  contextWindow: 131072,
7235
6990
  maxTokens: 131072,
7236
6991
  },
7237
- "allenai/olmo-3.1-32b-instruct": {
7238
- id: "allenai/olmo-3.1-32b-instruct",
7239
- name: "AllenAI: Olmo 3.1 32B Instruct",
7240
- api: "openai-completions",
7241
- provider: "openrouter",
7242
- baseUrl: "https://openrouter.ai/api/v1",
7243
- reasoning: false,
7244
- input: ["text"],
7245
- cost: {
7246
- input: 0.19999999999999998,
7247
- output: 0.6,
7248
- cacheRead: 0,
7249
- cacheWrite: 0,
7250
- },
7251
- contextWindow: 65536,
7252
- maxTokens: 16384,
7253
- },
7254
6992
  "amazon/nova-2-lite-v1": {
7255
6993
  id: "amazon/nova-2-lite-v1",
7256
6994
  name: "Amazon: Nova 2 Lite",
@@ -7370,40 +7108,6 @@ export const MODELS = {
7370
7108
  contextWindow: 200000,
7371
7109
  maxTokens: 8192,
7372
7110
  },
7373
- "anthropic/claude-3.7-sonnet": {
7374
- id: "anthropic/claude-3.7-sonnet",
7375
- name: "Anthropic: Claude 3.7 Sonnet",
7376
- api: "openai-completions",
7377
- provider: "openrouter",
7378
- baseUrl: "https://openrouter.ai/api/v1",
7379
- reasoning: true,
7380
- input: ["text", "image"],
7381
- cost: {
7382
- input: 3,
7383
- output: 15,
7384
- cacheRead: 0.3,
7385
- cacheWrite: 3.75,
7386
- },
7387
- contextWindow: 200000,
7388
- maxTokens: 128000,
7389
- },
7390
- "anthropic/claude-3.7-sonnet:thinking": {
7391
- id: "anthropic/claude-3.7-sonnet:thinking",
7392
- name: "Anthropic: Claude 3.7 Sonnet (thinking)",
7393
- api: "openai-completions",
7394
- provider: "openrouter",
7395
- baseUrl: "https://openrouter.ai/api/v1",
7396
- reasoning: true,
7397
- input: ["text", "image"],
7398
- cost: {
7399
- input: 3,
7400
- output: 15,
7401
- cacheRead: 0.3,
7402
- cacheWrite: 3.75,
7403
- },
7404
- contextWindow: 200000,
7405
- maxTokens: 64000,
7406
- },
7407
7111
  "anthropic/claude-haiku-4.5": {
7408
7112
  id: "anthropic/claude-haiku-4.5",
7409
7113
  name: "Anthropic: Claude Haiku 4.5",
@@ -7515,10 +7219,27 @@ export const MODELS = {
7515
7219
  reasoning: true,
7516
7220
  input: ["text", "image"],
7517
7221
  cost: {
7518
- input: 5,
7519
- output: 25,
7520
- cacheRead: 0.5,
7521
- cacheWrite: 6.25,
7222
+ input: 5,
7223
+ output: 25,
7224
+ cacheRead: 0.5,
7225
+ cacheWrite: 6.25,
7226
+ },
7227
+ contextWindow: 1000000,
7228
+ maxTokens: 128000,
7229
+ },
7230
+ "anthropic/claude-opus-4.7-fast": {
7231
+ id: "anthropic/claude-opus-4.7-fast",
7232
+ name: "Anthropic: Claude Opus 4.7 (Fast)",
7233
+ api: "openai-completions",
7234
+ provider: "openrouter",
7235
+ baseUrl: "https://openrouter.ai/api/v1",
7236
+ reasoning: true,
7237
+ input: ["text", "image"],
7238
+ cost: {
7239
+ input: 30,
7240
+ output: 150,
7241
+ cacheRead: 3,
7242
+ cacheWrite: 37.5,
7522
7243
  },
7523
7244
  contextWindow: 1000000,
7524
7245
  maxTokens: 128000,
@@ -7608,6 +7329,23 @@ export const MODELS = {
7608
7329
  contextWindow: 262144,
7609
7330
  maxTokens: 262144,
7610
7331
  },
7332
+ "arcee-ai/trinity-large-thinking:free": {
7333
+ id: "arcee-ai/trinity-large-thinking:free",
7334
+ name: "Arcee AI: Trinity Large Thinking (free)",
7335
+ api: "openai-completions",
7336
+ provider: "openrouter",
7337
+ baseUrl: "https://openrouter.ai/api/v1",
7338
+ reasoning: true,
7339
+ input: ["text"],
7340
+ cost: {
7341
+ input: 0,
7342
+ output: 0,
7343
+ cacheRead: 0,
7344
+ cacheWrite: 0,
7345
+ },
7346
+ contextWindow: 262144,
7347
+ maxTokens: 80000,
7348
+ },
7611
7349
  "arcee-ai/trinity-mini": {
7612
7350
  id: "arcee-ai/trinity-mini",
7613
7351
  name: "Arcee AI: Trinity Mini",
@@ -7659,6 +7397,23 @@ export const MODELS = {
7659
7397
  contextWindow: 2000000,
7660
7398
  maxTokens: 30000,
7661
7399
  },
7400
+ "baidu/cobuddy:free": {
7401
+ id: "baidu/cobuddy:free",
7402
+ name: "Baidu Qianfan: CoBuddy (free)",
7403
+ api: "openai-completions",
7404
+ provider: "openrouter",
7405
+ baseUrl: "https://openrouter.ai/api/v1",
7406
+ reasoning: true,
7407
+ input: ["text"],
7408
+ cost: {
7409
+ input: 0,
7410
+ output: 0,
7411
+ cacheRead: 0,
7412
+ cacheWrite: 0,
7413
+ },
7414
+ contextWindow: 131072,
7415
+ maxTokens: 65536,
7416
+ },
7662
7417
  "baidu/ernie-4.5-21b-a3b": {
7663
7418
  id: "baidu/ernie-4.5-21b-a3b",
7664
7419
  name: "Baidu: ERNIE 4.5 21B A3B",
@@ -7838,13 +7593,13 @@ export const MODELS = {
7838
7593
  reasoning: true,
7839
7594
  input: ["text"],
7840
7595
  cost: {
7841
- input: 0.15,
7842
- output: 0.75,
7843
- cacheRead: 0,
7596
+ input: 0.21,
7597
+ output: 0.7899999999999999,
7598
+ cacheRead: 0.13,
7844
7599
  cacheWrite: 0,
7845
7600
  },
7846
- contextWindow: 32768,
7847
- maxTokens: 7168,
7601
+ contextWindow: 163840,
7602
+ maxTokens: 32768,
7848
7603
  },
7849
7604
  "deepseek/deepseek-r1": {
7850
7605
  id: "deepseek/deepseek-r1",
@@ -7889,8 +7644,8 @@ export const MODELS = {
7889
7644
  reasoning: true,
7890
7645
  input: ["text"],
7891
7646
  cost: {
7892
- input: 0.21,
7893
- output: 0.7899999999999999,
7647
+ input: 0.27,
7648
+ output: 0.95,
7894
7649
  cacheRead: 0.13,
7895
7650
  cacheWrite: 0,
7896
7651
  },
@@ -7942,7 +7697,7 @@ export const MODELS = {
7942
7697
  cost: {
7943
7698
  input: 0.14,
7944
7699
  output: 0.28,
7945
- cacheRead: 0.028,
7700
+ cacheRead: 0.0028,
7946
7701
  cacheWrite: 0,
7947
7702
  },
7948
7703
  contextWindow: 1048576,
@@ -7959,7 +7714,7 @@ export const MODELS = {
7959
7714
  cost: {
7960
7715
  input: 0.435,
7961
7716
  output: 0.87,
7962
- cacheRead: 0.03625,
7717
+ cacheRead: 0.003625,
7963
7718
  cacheWrite: 0,
7964
7719
  },
7965
7720
  contextWindow: 1048576,
@@ -7996,7 +7751,7 @@ export const MODELS = {
7996
7751
  cacheRead: 0.024999999999999998,
7997
7752
  cacheWrite: 0.08333333333333334,
7998
7753
  },
7999
- contextWindow: 1000000,
7754
+ contextWindow: 1048576,
8000
7755
  maxTokens: 8192,
8001
7756
  },
8002
7757
  "google/gemini-2.0-flash-lite-001": {
@@ -8135,6 +7890,23 @@ export const MODELS = {
8135
7890
  contextWindow: 1048576,
8136
7891
  maxTokens: 65536,
8137
7892
  },
7893
+ "google/gemini-3.1-flash-lite": {
7894
+ id: "google/gemini-3.1-flash-lite",
7895
+ name: "Google: Gemini 3.1 Flash Lite",
7896
+ api: "openai-completions",
7897
+ provider: "openrouter",
7898
+ baseUrl: "https://openrouter.ai/api/v1",
7899
+ reasoning: true,
7900
+ input: ["text", "image"],
7901
+ cost: {
7902
+ input: 0.25,
7903
+ output: 1.5,
7904
+ cacheRead: 0.024999999999999998,
7905
+ cacheWrite: 0.08333333333333334,
7906
+ },
7907
+ contextWindow: 1048576,
7908
+ maxTokens: 65536,
7909
+ },
8138
7910
  "google/gemini-3.1-flash-lite-preview": {
8139
7911
  id: "google/gemini-3.1-flash-lite-preview",
8140
7912
  name: "Google: Gemini 3.1 Flash Lite Preview",
@@ -8263,8 +8035,8 @@ export const MODELS = {
8263
8035
  reasoning: true,
8264
8036
  input: ["text", "image"],
8265
8037
  cost: {
8266
- input: 0.13,
8267
- output: 0.38,
8038
+ input: 0.12,
8039
+ output: 0.37,
8268
8040
  cacheRead: 0,
8269
8041
  cacheWrite: 0,
8270
8042
  },
@@ -8288,6 +8060,23 @@ export const MODELS = {
8288
8060
  contextWindow: 262144,
8289
8061
  maxTokens: 32768,
8290
8062
  },
8063
+ "ibm-granite/granite-4.1-8b": {
8064
+ id: "ibm-granite/granite-4.1-8b",
8065
+ name: "IBM: Granite 4.1 8B",
8066
+ api: "openai-completions",
8067
+ provider: "openrouter",
8068
+ baseUrl: "https://openrouter.ai/api/v1",
8069
+ reasoning: false,
8070
+ input: ["text"],
8071
+ cost: {
8072
+ input: 0.049999999999999996,
8073
+ output: 0.09999999999999999,
8074
+ cacheRead: 0.049999999999999996,
8075
+ cacheWrite: 0,
8076
+ },
8077
+ contextWindow: 131072,
8078
+ maxTokens: 131072,
8079
+ },
8291
8080
  "inception/mercury-2": {
8292
8081
  id: "inception/mercury-2",
8293
8082
  name: "Inception: Mercury 2",
@@ -8305,31 +8094,48 @@ export const MODELS = {
8305
8094
  contextWindow: 128000,
8306
8095
  maxTokens: 50000,
8307
8096
  },
8308
- "inclusionai/ling-2.6-1t:free": {
8309
- id: "inclusionai/ling-2.6-1t:free",
8310
- name: "inclusionAI: Ling-2.6-1T (free)",
8097
+ "inclusionai/ling-2.6-1t": {
8098
+ id: "inclusionai/ling-2.6-1t",
8099
+ name: "inclusionAI: Ling-2.6-1T",
8311
8100
  api: "openai-completions",
8312
8101
  provider: "openrouter",
8313
8102
  baseUrl: "https://openrouter.ai/api/v1",
8314
8103
  reasoning: false,
8315
8104
  input: ["text"],
8316
8105
  cost: {
8317
- input: 0,
8318
- output: 0,
8319
- cacheRead: 0,
8106
+ input: 0.3,
8107
+ output: 2.5,
8108
+ cacheRead: 0.06,
8320
8109
  cacheWrite: 0,
8321
8110
  },
8322
8111
  contextWindow: 262144,
8323
8112
  maxTokens: 32768,
8324
8113
  },
8325
- "inclusionai/ling-2.6-flash:free": {
8326
- id: "inclusionai/ling-2.6-flash:free",
8327
- name: "inclusionAI: Ling-2.6-flash (free)",
8114
+ "inclusionai/ling-2.6-flash": {
8115
+ id: "inclusionai/ling-2.6-flash",
8116
+ name: "inclusionAI: Ling-2.6-flash",
8328
8117
  api: "openai-completions",
8329
8118
  provider: "openrouter",
8330
8119
  baseUrl: "https://openrouter.ai/api/v1",
8331
8120
  reasoning: false,
8332
8121
  input: ["text"],
8122
+ cost: {
8123
+ input: 0.08,
8124
+ output: 0.24,
8125
+ cacheRead: 0.016,
8126
+ cacheWrite: 0,
8127
+ },
8128
+ contextWindow: 262144,
8129
+ maxTokens: 32768,
8130
+ },
8131
+ "inclusionai/ring-2.6-1t:free": {
8132
+ id: "inclusionai/ring-2.6-1t:free",
8133
+ name: "inclusionAI: Ring-2.6-1T (free)",
8134
+ api: "openai-completions",
8135
+ provider: "openrouter",
8136
+ baseUrl: "https://openrouter.ai/api/v1",
8137
+ reasoning: true,
8138
+ input: ["text"],
8333
8139
  cost: {
8334
8140
  input: 0,
8335
8141
  output: 0,
@@ -8337,7 +8143,7 @@ export const MODELS = {
8337
8143
  cacheWrite: 0,
8338
8144
  },
8339
8145
  contextWindow: 262144,
8340
- maxTokens: 32768,
8146
+ maxTokens: 65536,
8341
8147
  },
8342
8148
  "kwaipilot/kat-coder-pro-v2": {
8343
8149
  id: "kwaipilot/kat-coder-pro-v2",
@@ -8356,23 +8162,6 @@ export const MODELS = {
8356
8162
  contextWindow: 256000,
8357
8163
  maxTokens: 80000,
8358
8164
  },
8359
- "meta-llama/llama-3-8b-instruct": {
8360
- id: "meta-llama/llama-3-8b-instruct",
8361
- name: "Meta: Llama 3 8B Instruct",
8362
- api: "openai-completions",
8363
- provider: "openrouter",
8364
- baseUrl: "https://openrouter.ai/api/v1",
8365
- reasoning: false,
8366
- input: ["text"],
8367
- cost: {
8368
- input: 0.03,
8369
- output: 0.04,
8370
- cacheRead: 0,
8371
- cacheWrite: 0,
8372
- },
8373
- contextWindow: 8192,
8374
- maxTokens: 16384,
8375
- },
8376
8165
  "meta-llama/llama-3.1-70b-instruct": {
8377
8166
  id: "meta-llama/llama-3.1-70b-instruct",
8378
8167
  name: "Meta: Llama 3.1 70B Instruct",
@@ -8520,11 +8309,11 @@ export const MODELS = {
8520
8309
  cost: {
8521
8310
  input: 0.15,
8522
8311
  output: 1.15,
8523
- cacheRead: 0.03,
8312
+ cacheRead: 0,
8524
8313
  cacheWrite: 0,
8525
8314
  },
8526
8315
  contextWindow: 196608,
8527
- maxTokens: 131072,
8316
+ maxTokens: 196608,
8528
8317
  },
8529
8318
  "minimax/minimax-m2.5:free": {
8530
8319
  id: "minimax/minimax-m2.5:free",
@@ -8552,9 +8341,9 @@ export const MODELS = {
8552
8341
  reasoning: true,
8553
8342
  input: ["text"],
8554
8343
  cost: {
8555
- input: 0.3,
8344
+ input: 0.28,
8556
8345
  output: 1.2,
8557
- cacheRead: 0.059,
8346
+ cacheRead: 0,
8558
8347
  cacheWrite: 0,
8559
8348
  },
8560
8349
  contextWindow: 196608,
@@ -8764,6 +8553,23 @@ export const MODELS = {
8764
8553
  contextWindow: 131072,
8765
8554
  maxTokens: 4096,
8766
8555
  },
8556
+ "mistralai/mistral-medium-3-5": {
8557
+ id: "mistralai/mistral-medium-3-5",
8558
+ name: "Mistral: Mistral Medium 3.5",
8559
+ api: "openai-completions",
8560
+ provider: "openrouter",
8561
+ baseUrl: "https://openrouter.ai/api/v1",
8562
+ reasoning: true,
8563
+ input: ["text", "image"],
8564
+ cost: {
8565
+ input: 1.5,
8566
+ output: 7.5,
8567
+ cacheRead: 0,
8568
+ cacheWrite: 0,
8569
+ },
8570
+ contextWindow: 262144,
8571
+ maxTokens: 4096,
8572
+ },
8767
8573
  "mistralai/mistral-medium-3.1": {
8768
8574
  id: "mistralai/mistral-medium-3.1",
8769
8575
  name: "Mistral: Mistral Medium 3.1",
@@ -8778,7 +8584,7 @@ export const MODELS = {
8778
8584
  cacheRead: 0.04,
8779
8585
  cacheWrite: 0,
8780
8586
  },
8781
- contextWindow: 131072,
8587
+ contextWindow: 262144,
8782
8588
  maxTokens: 4096,
8783
8589
  },
8784
8590
  "mistralai/mistral-nemo": {
@@ -8790,7 +8596,7 @@ export const MODELS = {
8790
8596
  reasoning: false,
8791
8597
  input: ["text"],
8792
8598
  cost: {
8793
- input: 0.01,
8599
+ input: 0.02,
8794
8600
  output: 0.03,
8795
8601
  cacheRead: 0,
8796
8602
  cacheWrite: 0,
@@ -8849,23 +8655,6 @@ export const MODELS = {
8849
8655
  contextWindow: 128000,
8850
8656
  maxTokens: 16384,
8851
8657
  },
8852
- "mistralai/mistral-small-creative": {
8853
- id: "mistralai/mistral-small-creative",
8854
- name: "Mistral: Mistral Small Creative",
8855
- api: "openai-completions",
8856
- provider: "openrouter",
8857
- baseUrl: "https://openrouter.ai/api/v1",
8858
- reasoning: false,
8859
- input: ["text"],
8860
- cost: {
8861
- input: 0.09999999999999999,
8862
- output: 0.3,
8863
- cacheRead: 0.01,
8864
- cacheWrite: 0,
8865
- },
8866
- contextWindow: 32768,
8867
- maxTokens: 4096,
8868
- },
8869
8658
  "mistralai/mixtral-8x22b-instruct": {
8870
8659
  id: "mistralai/mixtral-8x22b-instruct",
8871
8660
  name: "Mistral: Mixtral 8x22B Instruct",
@@ -8883,23 +8672,6 @@ export const MODELS = {
8883
8672
  contextWindow: 65536,
8884
8673
  maxTokens: 4096,
8885
8674
  },
8886
- "mistralai/mixtral-8x7b-instruct": {
8887
- id: "mistralai/mixtral-8x7b-instruct",
8888
- name: "Mistral: Mixtral 8x7B Instruct",
8889
- api: "openai-completions",
8890
- provider: "openrouter",
8891
- baseUrl: "https://openrouter.ai/api/v1",
8892
- reasoning: false,
8893
- input: ["text"],
8894
- cost: {
8895
- input: 0.54,
8896
- output: 0.54,
8897
- cacheRead: 0,
8898
- cacheWrite: 0,
8899
- },
8900
- contextWindow: 32768,
8901
- maxTokens: 16384,
8902
- },
8903
8675
  "mistralai/pixtral-large-2411": {
8904
8676
  id: "mistralai/pixtral-large-2411",
8905
8677
  name: "Mistral: Pixtral Large 2411",
@@ -9011,13 +8783,13 @@ export const MODELS = {
9011
8783
  reasoning: true,
9012
8784
  input: ["text", "image"],
9013
8785
  cost: {
9014
- input: 0.7448,
9015
- output: 4.655,
9016
- cacheRead: 0.1463,
8786
+ input: 0.74,
8787
+ output: 3.5,
8788
+ cacheRead: 0.25,
9017
8789
  cacheWrite: 0,
9018
8790
  },
9019
- contextWindow: 256000,
9020
- maxTokens: 65536,
8791
+ contextWindow: 262142,
8792
+ maxTokens: 262142,
9021
8793
  },
9022
8794
  "nex-agi/deepseek-v3.1-nex-n1": {
9023
8795
  id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -9036,23 +8808,6 @@ export const MODELS = {
9036
8808
  contextWindow: 131072,
9037
8809
  maxTokens: 163840,
9038
8810
  },
9039
- "nvidia/llama-3.1-nemotron-70b-instruct": {
9040
- id: "nvidia/llama-3.1-nemotron-70b-instruct",
9041
- name: "NVIDIA: Llama 3.1 Nemotron 70B Instruct",
9042
- api: "openai-completions",
9043
- provider: "openrouter",
9044
- baseUrl: "https://openrouter.ai/api/v1",
9045
- reasoning: false,
9046
- input: ["text"],
9047
- cost: {
9048
- input: 1.2,
9049
- output: 1.2,
9050
- cacheRead: 0,
9051
- cacheWrite: 0,
9052
- },
9053
- contextWindow: 131072,
9054
- maxTokens: 16384,
9055
- },
9056
8811
  "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
9057
8812
  id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
9058
8813
  name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
@@ -9104,6 +8859,23 @@ export const MODELS = {
9104
8859
  contextWindow: 256000,
9105
8860
  maxTokens: 4096,
9106
8861
  },
8862
+ "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
8863
+ id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
8864
+ name: "NVIDIA: Nemotron 3 Nano Omni (free)",
8865
+ api: "openai-completions",
8866
+ provider: "openrouter",
8867
+ baseUrl: "https://openrouter.ai/api/v1",
8868
+ reasoning: true,
8869
+ input: ["text", "image"],
8870
+ cost: {
8871
+ input: 0,
8872
+ output: 0,
8873
+ cacheRead: 0,
8874
+ cacheWrite: 0,
8875
+ },
8876
+ contextWindow: 256000,
8877
+ maxTokens: 65536,
8878
+ },
9107
8879
  "nvidia/nemotron-3-super-120b-a12b": {
9108
8880
  id: "nvidia/nemotron-3-super-120b-a12b",
9109
8881
  name: "NVIDIA: Nemotron 3 Super",
@@ -9903,6 +9675,23 @@ export const MODELS = {
9903
9675
  contextWindow: 128000,
9904
9676
  maxTokens: 16384,
9905
9677
  },
9678
+ "openai/gpt-chat-latest": {
9679
+ id: "openai/gpt-chat-latest",
9680
+ name: "OpenAI: GPT Chat Latest",
9681
+ api: "openai-completions",
9682
+ provider: "openrouter",
9683
+ baseUrl: "https://openrouter.ai/api/v1",
9684
+ reasoning: false,
9685
+ input: ["text", "image"],
9686
+ cost: {
9687
+ input: 5,
9688
+ output: 30,
9689
+ cacheRead: 0.5,
9690
+ cacheWrite: 0,
9691
+ },
9692
+ contextWindow: 400000,
9693
+ maxTokens: 128000,
9694
+ },
9906
9695
  "openai/gpt-oss-120b": {
9907
9696
  id: "openai/gpt-oss-120b",
9908
9697
  name: "OpenAI: gpt-oss-120b",
@@ -9913,12 +9702,12 @@ export const MODELS = {
9913
9702
  input: ["text"],
9914
9703
  cost: {
9915
9704
  input: 0.039,
9916
- output: 0.19,
9705
+ output: 0.18,
9917
9706
  cacheRead: 0,
9918
9707
  cacheWrite: 0,
9919
9708
  },
9920
9709
  contextWindow: 131072,
9921
- maxTokens: 131072,
9710
+ maxTokens: 4096,
9922
9711
  },
9923
9712
  "openai/gpt-oss-120b:free": {
9924
9713
  id: "openai/gpt-oss-120b:free",
@@ -10175,6 +9964,57 @@ export const MODELS = {
10175
9964
  contextWindow: 200000,
10176
9965
  maxTokens: 4096,
10177
9966
  },
9967
+ "openrouter/owl-alpha": {
9968
+ id: "openrouter/owl-alpha",
9969
+ name: "Owl Alpha",
9970
+ api: "openai-completions",
9971
+ provider: "openrouter",
9972
+ baseUrl: "https://openrouter.ai/api/v1",
9973
+ reasoning: false,
9974
+ input: ["text"],
9975
+ cost: {
9976
+ input: 0,
9977
+ output: 0,
9978
+ cacheRead: 0,
9979
+ cacheWrite: 0,
9980
+ },
9981
+ contextWindow: 1048756,
9982
+ maxTokens: 262144,
9983
+ },
9984
+ "poolside/laguna-m.1:free": {
9985
+ id: "poolside/laguna-m.1:free",
9986
+ name: "Poolside: Laguna M.1 (free)",
9987
+ api: "openai-completions",
9988
+ provider: "openrouter",
9989
+ baseUrl: "https://openrouter.ai/api/v1",
9990
+ reasoning: true,
9991
+ input: ["text"],
9992
+ cost: {
9993
+ input: 0,
9994
+ output: 0,
9995
+ cacheRead: 0,
9996
+ cacheWrite: 0,
9997
+ },
9998
+ contextWindow: 131072,
9999
+ maxTokens: 8192,
10000
+ },
10001
+ "poolside/laguna-xs.2:free": {
10002
+ id: "poolside/laguna-xs.2:free",
10003
+ name: "Poolside: Laguna XS.2 (free)",
10004
+ api: "openai-completions",
10005
+ provider: "openrouter",
10006
+ baseUrl: "https://openrouter.ai/api/v1",
10007
+ reasoning: true,
10008
+ input: ["text"],
10009
+ cost: {
10010
+ input: 0,
10011
+ output: 0,
10012
+ cacheRead: 0,
10013
+ cacheWrite: 0,
10014
+ },
10015
+ contextWindow: 131072,
10016
+ maxTokens: 8192,
10017
+ },
10178
10018
  "prime-intellect/intellect-3": {
10179
10019
  id: "prime-intellect/intellect-3",
10180
10020
  name: "Prime Intellect: INTELLECT-3",
@@ -10201,8 +10041,8 @@ export const MODELS = {
10201
10041
  reasoning: false,
10202
10042
  input: ["text"],
10203
10043
  cost: {
10204
- input: 0.12,
10205
- output: 0.39,
10044
+ input: 0.36,
10045
+ output: 0.39999999999999997,
10206
10046
  cacheRead: 0,
10207
10047
  cacheWrite: 0,
10208
10048
  },
@@ -10405,13 +10245,13 @@ export const MODELS = {
10405
10245
  reasoning: true,
10406
10246
  input: ["text"],
10407
10247
  cost: {
10408
- input: 0.08,
10409
- output: 0.28,
10248
+ input: 0.09,
10249
+ output: 0.44999999999999996,
10410
10250
  cacheRead: 0,
10411
10251
  cacheWrite: 0,
10412
10252
  },
10413
10253
  contextWindow: 40960,
10414
- maxTokens: 16384,
10254
+ maxTokens: 20000,
10415
10255
  },
10416
10256
  "qwen/qwen3-30b-a3b-instruct-2507": {
10417
10257
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10457,12 +10297,12 @@ export const MODELS = {
10457
10297
  input: ["text"],
10458
10298
  cost: {
10459
10299
  input: 0.08,
10460
- output: 0.24,
10461
- cacheRead: 0.04,
10300
+ output: 0.28,
10301
+ cacheRead: 0,
10462
10302
  cacheWrite: 0,
10463
10303
  },
10464
10304
  contextWindow: 40960,
10465
- maxTokens: 40960,
10305
+ maxTokens: 16384,
10466
10306
  },
10467
10307
  "qwen/qwen3-8b": {
10468
10308
  id: "qwen/qwen3-8b",
@@ -10541,9 +10381,9 @@ export const MODELS = {
10541
10381
  reasoning: false,
10542
10382
  input: ["text"],
10543
10383
  cost: {
10544
- input: 0.14,
10384
+ input: 0.11,
10545
10385
  output: 0.7999999999999999,
10546
- cacheRead: 0.09,
10386
+ cacheRead: 0.07,
10547
10387
  cacheWrite: 0,
10548
10388
  },
10549
10389
  contextWindow: 262144,
@@ -10830,13 +10670,13 @@ export const MODELS = {
10830
10670
  reasoning: true,
10831
10671
  input: ["text", "image"],
10832
10672
  cost: {
10833
- input: 0.1625,
10834
- output: 1.3,
10835
- cacheRead: 0,
10673
+ input: 0.14,
10674
+ output: 1,
10675
+ cacheRead: 0.049999999999999996,
10836
10676
  cacheWrite: 0,
10837
10677
  },
10838
10678
  contextWindow: 262144,
10839
- maxTokens: 65536,
10679
+ maxTokens: 81920,
10840
10680
  },
10841
10681
  "qwen/qwen3.5-397b-a17b": {
10842
10682
  id: "qwen/qwen3.5-397b-a17b",
@@ -10849,7 +10689,7 @@ export const MODELS = {
10849
10689
  cost: {
10850
10690
  input: 0.39,
10851
10691
  output: 2.34,
10852
- cacheRead: 0.195,
10692
+ cacheRead: 0,
10853
10693
  cacheWrite: 0,
10854
10694
  },
10855
10695
  contextWindow: 262144,
@@ -10864,13 +10704,13 @@ export const MODELS = {
10864
10704
  reasoning: true,
10865
10705
  input: ["text", "image"],
10866
10706
  cost: {
10867
- input: 0.09999999999999999,
10707
+ input: 0.04,
10868
10708
  output: 0.15,
10869
10709
  cacheRead: 0,
10870
10710
  cacheWrite: 0,
10871
10711
  },
10872
10712
  contextWindow: 262144,
10873
- maxTokens: 4096,
10713
+ maxTokens: 81920,
10874
10714
  },
10875
10715
  "qwen/qwen3.5-flash-02-23": {
10876
10716
  id: "qwen/qwen3.5-flash-02-23",
@@ -10906,39 +10746,107 @@ export const MODELS = {
10906
10746
  contextWindow: 1000000,
10907
10747
  maxTokens: 65536,
10908
10748
  },
10909
- "qwen/qwen3.6-plus": {
10910
- id: "qwen/qwen3.6-plus",
10911
- name: "Qwen: Qwen3.6 Plus",
10749
+ "qwen/qwen3.5-plus-20260420": {
10750
+ id: "qwen/qwen3.5-plus-20260420",
10751
+ name: "Qwen: Qwen3.5 Plus 2026-04-20",
10912
10752
  api: "openai-completions",
10913
10753
  provider: "openrouter",
10914
10754
  baseUrl: "https://openrouter.ai/api/v1",
10915
10755
  reasoning: true,
10916
10756
  input: ["text", "image"],
10917
10757
  cost: {
10918
- input: 0.325,
10919
- output: 1.95,
10758
+ input: 0.39999999999999997,
10759
+ output: 2.4,
10920
10760
  cacheRead: 0,
10921
- cacheWrite: 0.40625,
10761
+ cacheWrite: 0,
10922
10762
  },
10923
10763
  contextWindow: 1000000,
10924
10764
  maxTokens: 65536,
10925
10765
  },
10926
- "qwen/qwq-32b": {
10927
- id: "qwen/qwq-32b",
10928
- name: "Qwen: QwQ 32B",
10766
+ "qwen/qwen3.6-27b": {
10767
+ id: "qwen/qwen3.6-27b",
10768
+ name: "Qwen: Qwen3.6 27B",
10929
10769
  api: "openai-completions",
10930
10770
  provider: "openrouter",
10931
10771
  baseUrl: "https://openrouter.ai/api/v1",
10932
10772
  reasoning: true,
10933
- input: ["text"],
10773
+ input: ["text", "image"],
10934
10774
  cost: {
10935
- input: 0.15,
10936
- output: 0.58,
10775
+ input: 0.32,
10776
+ output: 3.1999999999999997,
10937
10777
  cacheRead: 0,
10938
10778
  cacheWrite: 0,
10939
10779
  },
10940
- contextWindow: 131072,
10941
- maxTokens: 131072,
10780
+ contextWindow: 262144,
10781
+ maxTokens: 81920,
10782
+ },
10783
+ "qwen/qwen3.6-35b-a3b": {
10784
+ id: "qwen/qwen3.6-35b-a3b",
10785
+ name: "Qwen: Qwen3.6 35B A3B",
10786
+ api: "openai-completions",
10787
+ provider: "openrouter",
10788
+ baseUrl: "https://openrouter.ai/api/v1",
10789
+ reasoning: true,
10790
+ input: ["text", "image"],
10791
+ cost: {
10792
+ input: 0.15,
10793
+ output: 1,
10794
+ cacheRead: 0.049999999999999996,
10795
+ cacheWrite: 0,
10796
+ },
10797
+ contextWindow: 262144,
10798
+ maxTokens: 262144,
10799
+ },
10800
+ "qwen/qwen3.6-flash": {
10801
+ id: "qwen/qwen3.6-flash",
10802
+ name: "Qwen: Qwen3.6 Flash",
10803
+ api: "openai-completions",
10804
+ provider: "openrouter",
10805
+ baseUrl: "https://openrouter.ai/api/v1",
10806
+ reasoning: true,
10807
+ input: ["text", "image"],
10808
+ cost: {
10809
+ input: 0.25,
10810
+ output: 1.5,
10811
+ cacheRead: 0,
10812
+ cacheWrite: 0.3125,
10813
+ },
10814
+ contextWindow: 1000000,
10815
+ maxTokens: 65536,
10816
+ },
10817
+ "qwen/qwen3.6-max-preview": {
10818
+ id: "qwen/qwen3.6-max-preview",
10819
+ name: "Qwen: Qwen3.6 Max Preview",
10820
+ api: "openai-completions",
10821
+ provider: "openrouter",
10822
+ baseUrl: "https://openrouter.ai/api/v1",
10823
+ reasoning: true,
10824
+ input: ["text"],
10825
+ cost: {
10826
+ input: 1.04,
10827
+ output: 6.24,
10828
+ cacheRead: 0,
10829
+ cacheWrite: 1.3,
10830
+ },
10831
+ contextWindow: 262144,
10832
+ maxTokens: 65536,
10833
+ },
10834
+ "qwen/qwen3.6-plus": {
10835
+ id: "qwen/qwen3.6-plus",
10836
+ name: "Qwen: Qwen3.6 Plus",
10837
+ api: "openai-completions",
10838
+ provider: "openrouter",
10839
+ baseUrl: "https://openrouter.ai/api/v1",
10840
+ reasoning: true,
10841
+ input: ["text", "image"],
10842
+ cost: {
10843
+ input: 0.325,
10844
+ output: 1.95,
10845
+ cacheRead: 0,
10846
+ cacheWrite: 0.40625,
10847
+ },
10848
+ contextWindow: 1000000,
10849
+ maxTokens: 65536,
10942
10850
  },
10943
10851
  "rekaai/reka-edge": {
10944
10852
  id: "rekaai/reka-edge",
@@ -11025,18 +10933,18 @@ export const MODELS = {
11025
10933
  contextWindow: 262144,
11026
10934
  maxTokens: 65536,
11027
10935
  },
11028
- "tencent/hy3-preview:free": {
11029
- id: "tencent/hy3-preview:free",
11030
- name: "Tencent: Hy3 preview (free)",
10936
+ "tencent/hy3-preview": {
10937
+ id: "tencent/hy3-preview",
10938
+ name: "Tencent: Hy3 preview",
11031
10939
  api: "openai-completions",
11032
10940
  provider: "openrouter",
11033
10941
  baseUrl: "https://openrouter.ai/api/v1",
11034
10942
  reasoning: true,
11035
10943
  input: ["text"],
11036
10944
  cost: {
11037
- input: 0,
11038
- output: 0,
11039
- cacheRead: 0,
10945
+ input: 0.06599999999999999,
10946
+ output: 0.26,
10947
+ cacheRead: 0.029,
11040
10948
  cacheWrite: 0,
11041
10949
  },
11042
10950
  contextWindow: 262144,
@@ -11076,23 +10984,6 @@ export const MODELS = {
11076
10984
  contextWindow: 32768,
11077
10985
  maxTokens: 32768,
11078
10986
  },
11079
- "tngtech/deepseek-r1t2-chimera": {
11080
- id: "tngtech/deepseek-r1t2-chimera",
11081
- name: "TNG: DeepSeek R1T2 Chimera",
11082
- api: "openai-completions",
11083
- provider: "openrouter",
11084
- baseUrl: "https://openrouter.ai/api/v1",
11085
- reasoning: true,
11086
- input: ["text"],
11087
- cost: {
11088
- input: 0.3,
11089
- output: 1.1,
11090
- cacheRead: 0.15,
11091
- cacheWrite: 0,
11092
- },
11093
- contextWindow: 163840,
11094
- maxTokens: 163840,
11095
- },
11096
10987
  "upstage/solar-pro-3": {
11097
10988
  id: "upstage/solar-pro-3",
11098
10989
  name: "Upstage: Solar Pro 3",
@@ -11238,14 +11129,31 @@ export const MODELS = {
11238
11129
  reasoning: true,
11239
11130
  input: ["text", "image"],
11240
11131
  cost: {
11241
- input: 2,
11242
- output: 6,
11132
+ input: 1.25,
11133
+ output: 2.5,
11243
11134
  cacheRead: 0.19999999999999998,
11244
11135
  cacheWrite: 0,
11245
11136
  },
11246
11137
  contextWindow: 2000000,
11247
11138
  maxTokens: 4096,
11248
11139
  },
11140
+ "x-ai/grok-4.3": {
11141
+ id: "x-ai/grok-4.3",
11142
+ name: "xAI: Grok 4.3",
11143
+ api: "openai-completions",
11144
+ provider: "openrouter",
11145
+ baseUrl: "https://openrouter.ai/api/v1",
11146
+ reasoning: true,
11147
+ input: ["text", "image"],
11148
+ cost: {
11149
+ input: 1.25,
11150
+ output: 2.5,
11151
+ cacheRead: 0.19999999999999998,
11152
+ cacheWrite: 0,
11153
+ },
11154
+ contextWindow: 1000000,
11155
+ maxTokens: 4096,
11156
+ },
11249
11157
  "x-ai/grok-code-fast-1": {
11250
11158
  id: "x-ai/grok-code-fast-1",
11251
11159
  name: "xAI: Grok Code Fast 1",
@@ -11272,9 +11180,9 @@ export const MODELS = {
11272
11180
  reasoning: true,
11273
11181
  input: ["text"],
11274
11182
  cost: {
11275
- input: 0.09,
11276
- output: 0.29,
11277
- cacheRead: 0.045,
11183
+ input: 0.09999999999999999,
11184
+ output: 0.3,
11185
+ cacheRead: 0.01,
11278
11186
  cacheWrite: 0,
11279
11187
  },
11280
11188
  contextWindow: 262144,
@@ -11346,7 +11254,7 @@ export const MODELS = {
11346
11254
  cacheWrite: 0,
11347
11255
  },
11348
11256
  contextWindow: 1048576,
11349
- maxTokens: 131072,
11257
+ maxTokens: 16384,
11350
11258
  },
11351
11259
  "z-ai/glm-4-32b": {
11352
11260
  id: "z-ai/glm-4-32b",
@@ -11476,13 +11384,13 @@ export const MODELS = {
11476
11384
  reasoning: true,
11477
11385
  input: ["text"],
11478
11386
  cost: {
11479
- input: 0.38,
11480
- output: 1.74,
11481
- cacheRead: 0,
11387
+ input: 0.39999999999999997,
11388
+ output: 1.75,
11389
+ cacheRead: 0.08,
11482
11390
  cacheWrite: 0,
11483
11391
  },
11484
11392
  contextWindow: 202752,
11485
- maxTokens: 4096,
11393
+ maxTokens: 131072,
11486
11394
  },
11487
11395
  "z-ai/glm-4.7-flash": {
11488
11396
  id: "z-ai/glm-4.7-flash",
@@ -11515,75 +11423,194 @@ export const MODELS = {
11515
11423
  cacheRead: 0.119,
11516
11424
  cacheWrite: 0,
11517
11425
  },
11518
- contextWindow: 202752,
11519
- maxTokens: 16384,
11426
+ contextWindow: 202752,
11427
+ maxTokens: 4096,
11428
+ },
11429
+ "z-ai/glm-5-turbo": {
11430
+ id: "z-ai/glm-5-turbo",
11431
+ name: "Z.ai: GLM 5 Turbo",
11432
+ api: "openai-completions",
11433
+ provider: "openrouter",
11434
+ baseUrl: "https://openrouter.ai/api/v1",
11435
+ reasoning: true,
11436
+ input: ["text"],
11437
+ cost: {
11438
+ input: 1.2,
11439
+ output: 4,
11440
+ cacheRead: 0.24,
11441
+ cacheWrite: 0,
11442
+ },
11443
+ contextWindow: 202752,
11444
+ maxTokens: 131072,
11445
+ },
11446
+ "z-ai/glm-5.1": {
11447
+ id: "z-ai/glm-5.1",
11448
+ name: "Z.ai: GLM 5.1",
11449
+ api: "openai-completions",
11450
+ provider: "openrouter",
11451
+ baseUrl: "https://openrouter.ai/api/v1",
11452
+ reasoning: true,
11453
+ input: ["text"],
11454
+ cost: {
11455
+ input: 0.98,
11456
+ output: 3.08,
11457
+ cacheRead: 0.182,
11458
+ cacheWrite: 0,
11459
+ },
11460
+ contextWindow: 202752,
11461
+ maxTokens: 4096,
11462
+ },
11463
+ "z-ai/glm-5v-turbo": {
11464
+ id: "z-ai/glm-5v-turbo",
11465
+ name: "Z.ai: GLM 5V Turbo",
11466
+ api: "openai-completions",
11467
+ provider: "openrouter",
11468
+ baseUrl: "https://openrouter.ai/api/v1",
11469
+ reasoning: true,
11470
+ input: ["text", "image"],
11471
+ cost: {
11472
+ input: 1.2,
11473
+ output: 4,
11474
+ cacheRead: 0.24,
11475
+ cacheWrite: 0,
11476
+ },
11477
+ contextWindow: 202752,
11478
+ maxTokens: 131072,
11479
+ },
11480
+ "~anthropic/claude-haiku-latest": {
11481
+ id: "~anthropic/claude-haiku-latest",
11482
+ name: "Anthropic Claude Haiku Latest",
11483
+ api: "openai-completions",
11484
+ provider: "openrouter",
11485
+ baseUrl: "https://openrouter.ai/api/v1",
11486
+ reasoning: true,
11487
+ input: ["text", "image"],
11488
+ cost: {
11489
+ input: 1,
11490
+ output: 5,
11491
+ cacheRead: 0.09999999999999999,
11492
+ cacheWrite: 1.25,
11493
+ },
11494
+ contextWindow: 200000,
11495
+ maxTokens: 64000,
11496
+ },
11497
+ "~anthropic/claude-opus-latest": {
11498
+ id: "~anthropic/claude-opus-latest",
11499
+ name: "Anthropic: Claude Opus Latest",
11500
+ api: "openai-completions",
11501
+ provider: "openrouter",
11502
+ baseUrl: "https://openrouter.ai/api/v1",
11503
+ reasoning: true,
11504
+ input: ["text", "image"],
11505
+ cost: {
11506
+ input: 5,
11507
+ output: 25,
11508
+ cacheRead: 0.5,
11509
+ cacheWrite: 6.25,
11510
+ },
11511
+ contextWindow: 1000000,
11512
+ maxTokens: 128000,
11513
+ },
11514
+ "~anthropic/claude-sonnet-latest": {
11515
+ id: "~anthropic/claude-sonnet-latest",
11516
+ name: "Anthropic Claude Sonnet Latest",
11517
+ api: "openai-completions",
11518
+ provider: "openrouter",
11519
+ baseUrl: "https://openrouter.ai/api/v1",
11520
+ reasoning: true,
11521
+ input: ["text", "image"],
11522
+ cost: {
11523
+ input: 3,
11524
+ output: 15,
11525
+ cacheRead: 0.3,
11526
+ cacheWrite: 3.75,
11527
+ },
11528
+ contextWindow: 1000000,
11529
+ maxTokens: 128000,
11530
+ },
11531
+ "~google/gemini-flash-latest": {
11532
+ id: "~google/gemini-flash-latest",
11533
+ name: "Google Gemini Flash Latest",
11534
+ api: "openai-completions",
11535
+ provider: "openrouter",
11536
+ baseUrl: "https://openrouter.ai/api/v1",
11537
+ reasoning: true,
11538
+ input: ["text", "image"],
11539
+ cost: {
11540
+ input: 0.5,
11541
+ output: 3,
11542
+ cacheRead: 0.049999999999999996,
11543
+ cacheWrite: 0.08333333333333334,
11544
+ },
11545
+ contextWindow: 1048576,
11546
+ maxTokens: 65536,
11520
11547
  },
11521
- "z-ai/glm-5-turbo": {
11522
- id: "z-ai/glm-5-turbo",
11523
- name: "Z.ai: GLM 5 Turbo",
11548
+ "~google/gemini-pro-latest": {
11549
+ id: "~google/gemini-pro-latest",
11550
+ name: "Google Gemini Pro Latest",
11524
11551
  api: "openai-completions",
11525
11552
  provider: "openrouter",
11526
11553
  baseUrl: "https://openrouter.ai/api/v1",
11527
11554
  reasoning: true,
11528
- input: ["text"],
11555
+ input: ["text", "image"],
11529
11556
  cost: {
11530
- input: 1.2,
11531
- output: 4,
11532
- cacheRead: 0.24,
11533
- cacheWrite: 0,
11557
+ input: 2,
11558
+ output: 12,
11559
+ cacheRead: 0.19999999999999998,
11560
+ cacheWrite: 0.375,
11534
11561
  },
11535
- contextWindow: 202752,
11536
- maxTokens: 131072,
11562
+ contextWindow: 1048576,
11563
+ maxTokens: 65536,
11537
11564
  },
11538
- "z-ai/glm-5.1": {
11539
- id: "z-ai/glm-5.1",
11540
- name: "Z.ai: GLM 5.1",
11565
+ "~moonshotai/kimi-latest": {
11566
+ id: "~moonshotai/kimi-latest",
11567
+ name: "MoonshotAI Kimi Latest",
11541
11568
  api: "openai-completions",
11542
11569
  provider: "openrouter",
11543
11570
  baseUrl: "https://openrouter.ai/api/v1",
11544
11571
  reasoning: true,
11545
- input: ["text"],
11572
+ input: ["text", "image"],
11546
11573
  cost: {
11547
- input: 1.0499999999999998,
11574
+ input: 0.74,
11548
11575
  output: 3.5,
11549
- cacheRead: 0.5249999999999999,
11576
+ cacheRead: 0.25,
11550
11577
  cacheWrite: 0,
11551
11578
  },
11552
- contextWindow: 202752,
11553
- maxTokens: 65535,
11579
+ contextWindow: 262142,
11580
+ maxTokens: 262142,
11554
11581
  },
11555
- "z-ai/glm-5v-turbo": {
11556
- id: "z-ai/glm-5v-turbo",
11557
- name: "Z.ai: GLM 5V Turbo",
11582
+ "~openai/gpt-latest": {
11583
+ id: "~openai/gpt-latest",
11584
+ name: "OpenAI GPT Latest",
11558
11585
  api: "openai-completions",
11559
11586
  provider: "openrouter",
11560
11587
  baseUrl: "https://openrouter.ai/api/v1",
11561
11588
  reasoning: true,
11562
11589
  input: ["text", "image"],
11563
11590
  cost: {
11564
- input: 1.2,
11565
- output: 4,
11566
- cacheRead: 0.24,
11591
+ input: 5,
11592
+ output: 30,
11593
+ cacheRead: 0.5,
11567
11594
  cacheWrite: 0,
11568
11595
  },
11569
- contextWindow: 202752,
11570
- maxTokens: 131072,
11596
+ contextWindow: 1050000,
11597
+ maxTokens: 128000,
11571
11598
  },
11572
- "~anthropic/claude-opus-latest": {
11573
- id: "~anthropic/claude-opus-latest",
11574
- name: "Anthropic: Claude Opus Latest",
11599
+ "~openai/gpt-mini-latest": {
11600
+ id: "~openai/gpt-mini-latest",
11601
+ name: "OpenAI GPT Mini Latest",
11575
11602
  api: "openai-completions",
11576
11603
  provider: "openrouter",
11577
11604
  baseUrl: "https://openrouter.ai/api/v1",
11578
11605
  reasoning: true,
11579
11606
  input: ["text", "image"],
11580
11607
  cost: {
11581
- input: 5,
11582
- output: 25,
11583
- cacheRead: 0.5,
11584
- cacheWrite: 6.25,
11608
+ input: 0.75,
11609
+ output: 4.5,
11610
+ cacheRead: 0.075,
11611
+ cacheWrite: 0,
11585
11612
  },
11586
- contextWindow: 1000000,
11613
+ contextWindow: 400000,
11587
11614
  maxTokens: 128000,
11588
11615
  },
11589
11616
  },
@@ -11675,20 +11702,20 @@ export const MODELS = {
11675
11702
  },
11676
11703
  "alibaba/qwen3-235b-a22b-thinking": {
11677
11704
  id: "alibaba/qwen3-235b-a22b-thinking",
11678
- name: "Qwen3 235B A22B Thinking 2507",
11705
+ name: "Qwen3 VL 235B A22B Thinking",
11679
11706
  api: "anthropic-messages",
11680
11707
  provider: "vercel-ai-gateway",
11681
11708
  baseUrl: "https://ai-gateway.vercel.sh",
11682
11709
  reasoning: true,
11683
11710
  input: ["text", "image"],
11684
11711
  cost: {
11685
- input: 0.22999999999999998,
11686
- output: 2.3,
11687
- cacheRead: 0.19999999999999998,
11712
+ input: 0.39999999999999997,
11713
+ output: 4,
11714
+ cacheRead: 0,
11688
11715
  cacheWrite: 0,
11689
11716
  },
11690
- contextWindow: 262114,
11691
- maxTokens: 262114,
11717
+ contextWindow: 131072,
11718
+ maxTokens: 32768,
11692
11719
  },
11693
11720
  "alibaba/qwen3-coder": {
11694
11721
  id: "alibaba/qwen3-coder",
@@ -11860,6 +11887,23 @@ export const MODELS = {
11860
11887
  contextWindow: 1000000,
11861
11888
  maxTokens: 64000,
11862
11889
  },
11890
+ "alibaba/qwen3.6-27b": {
11891
+ id: "alibaba/qwen3.6-27b",
11892
+ name: "Qwen 3.6 27B",
11893
+ api: "anthropic-messages",
11894
+ provider: "vercel-ai-gateway",
11895
+ baseUrl: "https://ai-gateway.vercel.sh",
11896
+ reasoning: true,
11897
+ input: ["text", "image"],
11898
+ cost: {
11899
+ input: 0.6,
11900
+ output: 3.5999999999999996,
11901
+ cacheRead: 0,
11902
+ cacheWrite: 0,
11903
+ },
11904
+ contextWindow: 256000,
11905
+ maxTokens: 256000,
11906
+ },
11863
11907
  "alibaba/qwen3.6-plus": {
11864
11908
  id: "alibaba/qwen3.6-plus",
11865
11909
  name: "Qwen 3.6 Plus",
@@ -11911,23 +11955,6 @@ export const MODELS = {
11911
11955
  contextWindow: 200000,
11912
11956
  maxTokens: 8192,
11913
11957
  },
11914
- "anthropic/claude-3.7-sonnet": {
11915
- id: "anthropic/claude-3.7-sonnet",
11916
- name: "Claude 3.7 Sonnet",
11917
- api: "anthropic-messages",
11918
- provider: "vercel-ai-gateway",
11919
- baseUrl: "https://ai-gateway.vercel.sh",
11920
- reasoning: true,
11921
- input: ["text", "image"],
11922
- cost: {
11923
- input: 3,
11924
- output: 15,
11925
- cacheRead: 0.3,
11926
- cacheWrite: 3.75,
11927
- },
11928
- contextWindow: 200000,
11929
- maxTokens: 8192,
11930
- },
11931
11958
  "anthropic/claude-haiku-4.5": {
11932
11959
  id: "anthropic/claude-haiku-4.5",
11933
11960
  name: "Claude Haiku 4.5",
@@ -12240,16 +12267,16 @@ export const MODELS = {
12240
12267
  api: "anthropic-messages",
12241
12268
  provider: "vercel-ai-gateway",
12242
12269
  baseUrl: "https://ai-gateway.vercel.sh",
12243
- reasoning: true,
12270
+ reasoning: false,
12244
12271
  input: ["text"],
12245
12272
  cost: {
12246
- input: 0.28,
12247
- output: 0.42,
12248
- cacheRead: 0.028,
12273
+ input: 0.62,
12274
+ output: 1.85,
12275
+ cacheRead: 0,
12249
12276
  cacheWrite: 0,
12250
12277
  },
12251
12278
  contextWindow: 128000,
12252
- maxTokens: 64000,
12279
+ maxTokens: 8000,
12253
12280
  },
12254
12281
  "deepseek/deepseek-v4-flash": {
12255
12282
  id: "deepseek/deepseek-v4-flash",
@@ -12262,7 +12289,7 @@ export const MODELS = {
12262
12289
  cost: {
12263
12290
  input: 0.14,
12264
12291
  output: 0.28,
12265
- cacheRead: 0.028,
12292
+ cacheRead: 0.0028,
12266
12293
  cacheWrite: 0,
12267
12294
  },
12268
12295
  contextWindow: 1000000,
@@ -12277,9 +12304,9 @@ export const MODELS = {
12277
12304
  reasoning: true,
12278
12305
  input: ["text"],
12279
12306
  cost: {
12280
- input: 1.74,
12281
- output: 3.48,
12282
- cacheRead: 0.145,
12307
+ input: 0.435,
12308
+ output: 0.87,
12309
+ cacheRead: 0.0036,
12283
12310
  cacheWrite: 0,
12284
12311
  },
12285
12312
  contextWindow: 1000000,
@@ -12404,6 +12431,23 @@ export const MODELS = {
12404
12431
  contextWindow: 1000000,
12405
12432
  maxTokens: 64000,
12406
12433
  },
12434
+ "google/gemini-3.1-flash-lite": {
12435
+ id: "google/gemini-3.1-flash-lite",
12436
+ name: "Gemini 3.1 Flash Lite",
12437
+ api: "anthropic-messages",
12438
+ provider: "vercel-ai-gateway",
12439
+ baseUrl: "https://ai-gateway.vercel.sh",
12440
+ reasoning: true,
12441
+ input: ["text", "image"],
12442
+ cost: {
12443
+ input: 0.25,
12444
+ output: 1.5,
12445
+ cacheRead: 0.03,
12446
+ cacheWrite: 0,
12447
+ },
12448
+ contextWindow: 1000000,
12449
+ maxTokens: 65000,
12450
+ },
12407
12451
  "google/gemini-3.1-flash-lite-preview": {
12408
12452
  id: "google/gemini-3.1-flash-lite-preview",
12409
12453
  name: "Gemini 3.1 Flash Lite Preview",
@@ -12965,23 +13009,6 @@ export const MODELS = {
12965
13009
  contextWindow: 131072,
12966
13010
  maxTokens: 131072,
12967
13011
  },
12968
- "moonshotai/kimi-k2-0905": {
12969
- id: "moonshotai/kimi-k2-0905",
12970
- name: "Kimi K2 0905",
12971
- api: "anthropic-messages",
12972
- provider: "vercel-ai-gateway",
12973
- baseUrl: "https://ai-gateway.vercel.sh",
12974
- reasoning: false,
12975
- input: ["text"],
12976
- cost: {
12977
- input: 0.6,
12978
- output: 2.5,
12979
- cacheRead: 0.3,
12980
- cacheWrite: 0,
12981
- },
12982
- contextWindow: 256000,
12983
- maxTokens: 128000,
12984
- },
12985
13012
  "moonshotai/kimi-k2-thinking": {
12986
13013
  id: "moonshotai/kimi-k2-thinking",
12987
13014
  name: "Kimi K2 Thinking",
@@ -13764,23 +13791,6 @@ export const MODELS = {
13764
13791
  contextWindow: 200000,
13765
13792
  maxTokens: 8000,
13766
13793
  },
13767
- "prime-intellect/intellect-3": {
13768
- id: "prime-intellect/intellect-3",
13769
- name: "INTELLECT 3",
13770
- api: "anthropic-messages",
13771
- provider: "vercel-ai-gateway",
13772
- baseUrl: "https://ai-gateway.vercel.sh",
13773
- reasoning: true,
13774
- input: ["text"],
13775
- cost: {
13776
- input: 0.19999999999999998,
13777
- output: 1.1,
13778
- cacheRead: 0,
13779
- cacheWrite: 0,
13780
- },
13781
- contextWindow: 131072,
13782
- maxTokens: 131072,
13783
- },
13784
13794
  "xai/grok-3": {
13785
13795
  id: "xai/grok-3",
13786
13796
  name: "Grok 3 Beta",
@@ -13943,8 +13953,8 @@ export const MODELS = {
13943
13953
  reasoning: true,
13944
13954
  input: ["text", "image"],
13945
13955
  cost: {
13946
- input: 2,
13947
- output: 6,
13956
+ input: 1.25,
13957
+ output: 2.5,
13948
13958
  cacheRead: 0.19999999999999998,
13949
13959
  cacheWrite: 0,
13950
13960
  },
@@ -13960,8 +13970,8 @@ export const MODELS = {
13960
13970
  reasoning: true,
13961
13971
  input: ["text", "image"],
13962
13972
  cost: {
13963
- input: 2,
13964
- output: 6,
13973
+ input: 1.25,
13974
+ output: 2.5,
13965
13975
  cacheRead: 0.19999999999999998,
13966
13976
  cacheWrite: 0,
13967
13977
  },
@@ -13977,8 +13987,8 @@ export const MODELS = {
13977
13987
  reasoning: false,
13978
13988
  input: ["text", "image"],
13979
13989
  cost: {
13980
- input: 2,
13981
- output: 6,
13990
+ input: 1.25,
13991
+ output: 2.5,
13982
13992
  cacheRead: 0.19999999999999998,
13983
13993
  cacheWrite: 0,
13984
13994
  },
@@ -13994,8 +14004,8 @@ export const MODELS = {
13994
14004
  reasoning: false,
13995
14005
  input: ["text", "image"],
13996
14006
  cost: {
13997
- input: 2,
13998
- output: 6,
14007
+ input: 1.25,
14008
+ output: 2.5,
13999
14009
  cacheRead: 0.19999999999999998,
14000
14010
  cacheWrite: 0,
14001
14011
  },
@@ -14011,8 +14021,8 @@ export const MODELS = {
14011
14021
  reasoning: true,
14012
14022
  input: ["text", "image"],
14013
14023
  cost: {
14014
- input: 2,
14015
- output: 6,
14024
+ input: 1.25,
14025
+ output: 2.5,
14016
14026
  cacheRead: 0.19999999999999998,
14017
14027
  cacheWrite: 0,
14018
14028
  },
@@ -14028,14 +14038,31 @@ export const MODELS = {
14028
14038
  reasoning: true,
14029
14039
  input: ["text", "image"],
14030
14040
  cost: {
14031
- input: 2,
14032
- output: 6,
14041
+ input: 1.25,
14042
+ output: 2.5,
14033
14043
  cacheRead: 0.19999999999999998,
14034
14044
  cacheWrite: 0,
14035
14045
  },
14036
14046
  contextWindow: 2000000,
14037
14047
  maxTokens: 2000000,
14038
14048
  },
14049
+ "xai/grok-4.3": {
14050
+ id: "xai/grok-4.3",
14051
+ name: "Grok 4.3",
14052
+ api: "anthropic-messages",
14053
+ provider: "vercel-ai-gateway",
14054
+ baseUrl: "https://ai-gateway.vercel.sh",
14055
+ reasoning: true,
14056
+ input: ["text", "image"],
14057
+ cost: {
14058
+ input: 1.25,
14059
+ output: 2.5,
14060
+ cacheRead: 0.19999999999999998,
14061
+ cacheWrite: 0,
14062
+ },
14063
+ contextWindow: 1000000,
14064
+ maxTokens: 1000000,
14065
+ },
14039
14066
  "xai/grok-code-fast-1": {
14040
14067
  id: "xai/grok-code-fast-1",
14041
14068
  name: "Grok Code Fast 1",
@@ -14087,6 +14114,40 @@ export const MODELS = {
14087
14114
  contextWindow: 1000000,
14088
14115
  maxTokens: 128000,
14089
14116
  },
14117
+ "xiaomi/mimo-v2.5": {
14118
+ id: "xiaomi/mimo-v2.5",
14119
+ name: "MiMo M2.5",
14120
+ api: "anthropic-messages",
14121
+ provider: "vercel-ai-gateway",
14122
+ baseUrl: "https://ai-gateway.vercel.sh",
14123
+ reasoning: true,
14124
+ input: ["text", "image"],
14125
+ cost: {
14126
+ input: 0.39999999999999997,
14127
+ output: 2,
14128
+ cacheRead: 0.08,
14129
+ cacheWrite: 0,
14130
+ },
14131
+ contextWindow: 1050000,
14132
+ maxTokens: 131100,
14133
+ },
14134
+ "xiaomi/mimo-v2.5-pro": {
14135
+ id: "xiaomi/mimo-v2.5-pro",
14136
+ name: "MiMo V2.5 Pro",
14137
+ api: "anthropic-messages",
14138
+ provider: "vercel-ai-gateway",
14139
+ baseUrl: "https://ai-gateway.vercel.sh",
14140
+ reasoning: true,
14141
+ input: ["text", "image"],
14142
+ cost: {
14143
+ input: 1,
14144
+ output: 3,
14145
+ cacheRead: 0.19999999999999998,
14146
+ cacheWrite: 0,
14147
+ },
14148
+ contextWindow: 1050000,
14149
+ maxTokens: 131000,
14150
+ },
14090
14151
  "zai/glm-4.5": {
14091
14152
  id: "zai/glm-4.5",
14092
14153
  name: "GLM-4.5",
@@ -14667,6 +14728,23 @@ export const MODELS = {
14667
14728
  contextWindow: 2000000,
14668
14729
  maxTokens: 30000,
14669
14730
  },
14731
+ "grok-4.3": {
14732
+ id: "grok-4.3",
14733
+ name: "Grok 4.3",
14734
+ api: "openai-completions",
14735
+ provider: "xai",
14736
+ baseUrl: "https://api.x.ai/v1",
14737
+ reasoning: true,
14738
+ input: ["text", "image"],
14739
+ cost: {
14740
+ input: 1.25,
14741
+ output: 2.5,
14742
+ cacheRead: 0.2,
14743
+ cacheWrite: 0,
14744
+ },
14745
+ contextWindow: 1000000,
14746
+ maxTokens: 30000,
14747
+ },
14670
14748
  "grok-beta": {
14671
14749
  id: "grok-beta",
14672
14750
  name: "Grok Beta",
@@ -14792,6 +14870,24 @@ export const MODELS = {
14792
14870
  contextWindow: 200000,
14793
14871
  maxTokens: 131072,
14794
14872
  },
14873
+ "glm-5v-turbo": {
14874
+ id: "glm-5v-turbo",
14875
+ name: "GLM-5V-Turbo",
14876
+ api: "openai-completions",
14877
+ provider: "zai",
14878
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
14879
+ compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14880
+ reasoning: true,
14881
+ input: ["text", "image"],
14882
+ cost: {
14883
+ input: 0,
14884
+ output: 0,
14885
+ cacheRead: 0,
14886
+ cacheWrite: 0,
14887
+ },
14888
+ contextWindow: 200000,
14889
+ maxTokens: 131072,
14890
+ },
14795
14891
  },
14796
14892
  };
14797
14893
  //# sourceMappingURL=models.generated.js.map