@eminent337/aery-ai 0.67.129 → 0.74.2

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.
@@ -53,6 +53,23 @@ 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
+ },
56
73
  "amazon.nova-pro-v1:0": {
57
74
  id: "amazon.nova-pro-v1:0",
58
75
  name: "Nova Pro",
@@ -70,6 +87,91 @@ export const MODELS = {
70
87
  contextWindow: 300000,
71
88
  maxTokens: 8192,
72
89
  },
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
+ },
73
175
  "anthropic.claude-haiku-4-5-20251001-v1:0": {
74
176
  id: "anthropic.claude-haiku-4-5-20251001-v1:0",
75
177
  name: "Claude Haiku 4.5",
@@ -104,6 +206,23 @@ export const MODELS = {
104
206
  contextWindow: 200000,
105
207
  maxTokens: 32000,
106
208
  },
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
+ },
107
226
  "anthropic.claude-opus-4-5-20251101-v1:0": {
108
227
  id: "anthropic.claude-opus-4-5-20251101-v1:0",
109
228
  name: "Claude Opus 4.5",
@@ -157,9 +276,9 @@ export const MODELS = {
157
276
  contextWindow: 1000000,
158
277
  maxTokens: 128000,
159
278
  },
160
- "anthropic.claude-sonnet-4-5-20250929-v1:0": {
161
- id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
162
- name: "Claude Sonnet 4.5",
279
+ "anthropic.claude-sonnet-4-20250514-v1:0": {
280
+ id: "anthropic.claude-sonnet-4-20250514-v1:0",
281
+ name: "Claude Sonnet 4",
163
282
  api: "bedrock-converse-stream",
164
283
  provider: "amazon-bedrock",
165
284
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -174,9 +293,9 @@ export const MODELS = {
174
293
  contextWindow: 200000,
175
294
  maxTokens: 64000,
176
295
  },
177
- "anthropic.claude-sonnet-4-6": {
178
- id: "anthropic.claude-sonnet-4-6",
179
- name: "Claude Sonnet 4.6",
296
+ "anthropic.claude-sonnet-4-5-20250929-v1:0": {
297
+ id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
298
+ name: "Claude Sonnet 4.5",
180
299
  api: "bedrock-converse-stream",
181
300
  provider: "amazon-bedrock",
182
301
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -188,24 +307,24 @@ export const MODELS = {
188
307
  cacheRead: 0.3,
189
308
  cacheWrite: 3.75,
190
309
  },
191
- contextWindow: 1000000,
310
+ contextWindow: 200000,
192
311
  maxTokens: 64000,
193
312
  },
194
- "au.anthropic.claude-haiku-4-5-20251001-v1:0": {
195
- id: "au.anthropic.claude-haiku-4-5-20251001-v1:0",
196
- name: "Claude Haiku 4.5 (AU)",
313
+ "anthropic.claude-sonnet-4-6": {
314
+ id: "anthropic.claude-sonnet-4-6",
315
+ name: "Claude Sonnet 4.6",
197
316
  api: "bedrock-converse-stream",
198
317
  provider: "amazon-bedrock",
199
318
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
200
319
  reasoning: true,
201
320
  input: ["text", "image"],
202
321
  cost: {
203
- input: 1,
204
- output: 5,
205
- cacheRead: 0.1,
206
- cacheWrite: 1.25,
322
+ input: 3,
323
+ output: 15,
324
+ cacheRead: 0.3,
325
+ cacheWrite: 3.75,
207
326
  },
208
- contextWindow: 200000,
327
+ contextWindow: 1000000,
209
328
  maxTokens: 64000,
210
329
  },
211
330
  "au.anthropic.claude-opus-4-6-v1": {
@@ -226,23 +345,6 @@ export const MODELS = {
226
345
  contextWindow: 1000000,
227
346
  maxTokens: 128000,
228
347
  },
229
- "au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
230
- id: "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
231
- name: "Claude Sonnet 4.5 (AU)",
232
- api: "bedrock-converse-stream",
233
- provider: "amazon-bedrock",
234
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
235
- reasoning: true,
236
- input: ["text", "image"],
237
- cost: {
238
- input: 3,
239
- output: 15,
240
- cacheRead: 0.3,
241
- cacheWrite: 3.75,
242
- },
243
- contextWindow: 200000,
244
- maxTokens: 64000,
245
- },
246
348
  "au.anthropic.claude-sonnet-4-6": {
247
349
  id: "au.anthropic.claude-sonnet-4-6",
248
350
  name: "AU Anthropic Claude Sonnet 4.6",
@@ -381,6 +483,23 @@ export const MODELS = {
381
483
  contextWindow: 1000000,
382
484
  maxTokens: 128000,
383
485
  },
486
+ "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
487
+ id: "eu.anthropic.claude-sonnet-4-20250514-v1:0",
488
+ name: "Claude Sonnet 4 (EU)",
489
+ api: "bedrock-converse-stream",
490
+ provider: "amazon-bedrock",
491
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
492
+ reasoning: true,
493
+ input: ["text", "image"],
494
+ cost: {
495
+ input: 3,
496
+ output: 15,
497
+ cacheRead: 0.3,
498
+ cacheWrite: 3.75,
499
+ },
500
+ contextWindow: 200000,
501
+ maxTokens: 64000,
502
+ },
384
503
  "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
385
504
  id: "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
386
505
  name: "Claude Sonnet 4.5 (EU)",
@@ -485,6 +604,23 @@ export const MODELS = {
485
604
  contextWindow: 1000000,
486
605
  maxTokens: 128000,
487
606
  },
607
+ "global.anthropic.claude-sonnet-4-20250514-v1:0": {
608
+ id: "global.anthropic.claude-sonnet-4-20250514-v1:0",
609
+ name: "Claude Sonnet 4 (Global)",
610
+ api: "bedrock-converse-stream",
611
+ provider: "amazon-bedrock",
612
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
613
+ reasoning: true,
614
+ input: ["text", "image"],
615
+ cost: {
616
+ input: 3,
617
+ output: 15,
618
+ cacheRead: 0.3,
619
+ cacheWrite: 3.75,
620
+ },
621
+ contextWindow: 200000,
622
+ maxTokens: 64000,
623
+ },
488
624
  "global.anthropic.claude-sonnet-4-5-20250929-v1:0": {
489
625
  id: "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
490
626
  name: "Claude Sonnet 4.5 (Global)",
@@ -553,86 +689,119 @@ export const MODELS = {
553
689
  contextWindow: 128000,
554
690
  maxTokens: 4096,
555
691
  },
556
- "jp.anthropic.claude-opus-4-7": {
557
- id: "jp.anthropic.claude-opus-4-7",
558
- name: "Claude Opus 4.7 (JP)",
692
+ "meta.llama3-1-405b-instruct-v1:0": {
693
+ id: "meta.llama3-1-405b-instruct-v1:0",
694
+ name: "Llama 3.1 405B Instruct",
559
695
  api: "bedrock-converse-stream",
560
696
  provider: "amazon-bedrock",
561
697
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
562
- reasoning: true,
563
- thinkingLevelMap: { "xhigh": "xhigh" },
564
- input: ["text", "image"],
698
+ reasoning: false,
699
+ input: ["text"],
565
700
  cost: {
566
- input: 5,
567
- output: 25,
568
- cacheRead: 0.5,
569
- cacheWrite: 6.25,
701
+ input: 2.4,
702
+ output: 2.4,
703
+ cacheRead: 0,
704
+ cacheWrite: 0,
570
705
  },
571
- contextWindow: 1000000,
572
- maxTokens: 128000,
706
+ contextWindow: 128000,
707
+ maxTokens: 4096,
573
708
  },
574
- "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
575
- id: "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
576
- name: "Claude Sonnet 4.5 (JP)",
709
+ "meta.llama3-1-70b-instruct-v1:0": {
710
+ id: "meta.llama3-1-70b-instruct-v1:0",
711
+ name: "Llama 3.1 70B Instruct",
577
712
  api: "bedrock-converse-stream",
578
713
  provider: "amazon-bedrock",
579
714
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
580
- reasoning: true,
581
- input: ["text", "image"],
715
+ reasoning: false,
716
+ input: ["text"],
582
717
  cost: {
583
- input: 3,
584
- output: 15,
585
- cacheRead: 0.3,
586
- cacheWrite: 3.75,
718
+ input: 0.72,
719
+ output: 0.72,
720
+ cacheRead: 0,
721
+ cacheWrite: 0,
587
722
  },
588
- contextWindow: 200000,
589
- maxTokens: 64000,
723
+ contextWindow: 128000,
724
+ maxTokens: 4096,
590
725
  },
591
- "jp.anthropic.claude-sonnet-4-6": {
592
- id: "jp.anthropic.claude-sonnet-4-6",
593
- name: "Claude Sonnet 4.6 (JP)",
726
+ "meta.llama3-1-8b-instruct-v1:0": {
727
+ id: "meta.llama3-1-8b-instruct-v1:0",
728
+ name: "Llama 3.1 8B Instruct",
594
729
  api: "bedrock-converse-stream",
595
730
  provider: "amazon-bedrock",
596
731
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
597
- reasoning: true,
732
+ reasoning: false,
733
+ input: ["text"],
734
+ cost: {
735
+ input: 0.22,
736
+ output: 0.22,
737
+ cacheRead: 0,
738
+ cacheWrite: 0,
739
+ },
740
+ contextWindow: 128000,
741
+ maxTokens: 4096,
742
+ },
743
+ "meta.llama3-2-11b-instruct-v1:0": {
744
+ id: "meta.llama3-2-11b-instruct-v1:0",
745
+ name: "Llama 3.2 11B Instruct",
746
+ api: "bedrock-converse-stream",
747
+ provider: "amazon-bedrock",
748
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
749
+ reasoning: false,
598
750
  input: ["text", "image"],
599
751
  cost: {
600
- input: 3,
601
- output: 15,
602
- cacheRead: 0.3,
603
- cacheWrite: 3.75,
752
+ input: 0.16,
753
+ output: 0.16,
754
+ cacheRead: 0,
755
+ cacheWrite: 0,
604
756
  },
605
- contextWindow: 1000000,
606
- maxTokens: 64000,
757
+ contextWindow: 128000,
758
+ maxTokens: 4096,
607
759
  },
608
- "meta.llama3-1-70b-instruct-v1:0": {
609
- id: "meta.llama3-1-70b-instruct-v1:0",
610
- name: "Llama 3.1 70B Instruct",
760
+ "meta.llama3-2-1b-instruct-v1:0": {
761
+ id: "meta.llama3-2-1b-instruct-v1:0",
762
+ name: "Llama 3.2 1B Instruct",
611
763
  api: "bedrock-converse-stream",
612
764
  provider: "amazon-bedrock",
613
765
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
614
766
  reasoning: false,
615
767
  input: ["text"],
616
768
  cost: {
617
- input: 0.72,
618
- output: 0.72,
769
+ input: 0.1,
770
+ output: 0.1,
619
771
  cacheRead: 0,
620
772
  cacheWrite: 0,
621
773
  },
622
- contextWindow: 128000,
774
+ contextWindow: 131000,
623
775
  maxTokens: 4096,
624
776
  },
625
- "meta.llama3-1-8b-instruct-v1:0": {
626
- id: "meta.llama3-1-8b-instruct-v1:0",
627
- name: "Llama 3.1 8B Instruct",
777
+ "meta.llama3-2-3b-instruct-v1:0": {
778
+ id: "meta.llama3-2-3b-instruct-v1:0",
779
+ name: "Llama 3.2 3B Instruct",
628
780
  api: "bedrock-converse-stream",
629
781
  provider: "amazon-bedrock",
630
782
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
631
783
  reasoning: false,
632
784
  input: ["text"],
633
785
  cost: {
634
- input: 0.22,
635
- output: 0.22,
786
+ input: 0.15,
787
+ output: 0.15,
788
+ cacheRead: 0,
789
+ cacheWrite: 0,
790
+ },
791
+ contextWindow: 131000,
792
+ maxTokens: 4096,
793
+ },
794
+ "meta.llama3-2-90b-instruct-v1:0": {
795
+ id: "meta.llama3-2-90b-instruct-v1:0",
796
+ name: "Llama 3.2 90B Instruct",
797
+ api: "bedrock-converse-stream",
798
+ provider: "amazon-bedrock",
799
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
800
+ reasoning: false,
801
+ input: ["text", "image"],
802
+ cost: {
803
+ input: 0.72,
804
+ output: 0.72,
636
805
  cacheRead: 0,
637
806
  cacheWrite: 0,
638
807
  },
@@ -1011,7 +1180,7 @@ export const MODELS = {
1011
1180
  cacheWrite: 0,
1012
1181
  },
1013
1182
  contextWindow: 128000,
1014
- maxTokens: 16384,
1183
+ maxTokens: 4096,
1015
1184
  },
1016
1185
  "openai.gpt-oss-20b-1:0": {
1017
1186
  id: "openai.gpt-oss-20b-1:0",
@@ -1028,7 +1197,7 @@ export const MODELS = {
1028
1197
  cacheWrite: 0,
1029
1198
  },
1030
1199
  contextWindow: 128000,
1031
- maxTokens: 16384,
1200
+ maxTokens: 4096,
1032
1201
  },
1033
1202
  "openai.gpt-oss-safeguard-120b": {
1034
1203
  id: "openai.gpt-oss-safeguard-120b",
@@ -1045,7 +1214,7 @@ export const MODELS = {
1045
1214
  cacheWrite: 0,
1046
1215
  },
1047
1216
  contextWindow: 128000,
1048
- maxTokens: 16384,
1217
+ maxTokens: 4096,
1049
1218
  },
1050
1219
  "openai.gpt-oss-safeguard-20b": {
1051
1220
  id: "openai.gpt-oss-safeguard-20b",
@@ -1062,7 +1231,7 @@ export const MODELS = {
1062
1231
  cacheWrite: 0,
1063
1232
  },
1064
1233
  contextWindow: 128000,
1065
- maxTokens: 16384,
1234
+ maxTokens: 4096,
1066
1235
  },
1067
1236
  "qwen.qwen3-235b-a22b-2507-v1:0": {
1068
1237
  id: "qwen.qwen3-235b-a22b-2507-v1:0",
@@ -1217,6 +1386,23 @@ export const MODELS = {
1217
1386
  contextWindow: 200000,
1218
1387
  maxTokens: 32000,
1219
1388
  },
1389
+ "us.anthropic.claude-opus-4-20250514-v1:0": {
1390
+ id: "us.anthropic.claude-opus-4-20250514-v1:0",
1391
+ name: "Claude Opus 4 (US)",
1392
+ api: "bedrock-converse-stream",
1393
+ provider: "amazon-bedrock",
1394
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1395
+ reasoning: true,
1396
+ input: ["text", "image"],
1397
+ cost: {
1398
+ input: 15,
1399
+ output: 75,
1400
+ cacheRead: 1.5,
1401
+ cacheWrite: 18.75,
1402
+ },
1403
+ contextWindow: 200000,
1404
+ maxTokens: 32000,
1405
+ },
1220
1406
  "us.anthropic.claude-opus-4-5-20251101-v1:0": {
1221
1407
  id: "us.anthropic.claude-opus-4-5-20251101-v1:0",
1222
1408
  name: "Claude Opus 4.5 (US)",
@@ -1270,9 +1456,9 @@ export const MODELS = {
1270
1456
  contextWindow: 1000000,
1271
1457
  maxTokens: 128000,
1272
1458
  },
1273
- "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
1274
- id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
1275
- name: "Claude Sonnet 4.5 (US)",
1459
+ "us.anthropic.claude-sonnet-4-20250514-v1:0": {
1460
+ id: "us.anthropic.claude-sonnet-4-20250514-v1:0",
1461
+ name: "Claude Sonnet 4 (US)",
1276
1462
  api: "bedrock-converse-stream",
1277
1463
  provider: "amazon-bedrock",
1278
1464
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1287,9 +1473,9 @@ export const MODELS = {
1287
1473
  contextWindow: 200000,
1288
1474
  maxTokens: 64000,
1289
1475
  },
1290
- "us.anthropic.claude-sonnet-4-6": {
1291
- id: "us.anthropic.claude-sonnet-4-6",
1292
- name: "Claude Sonnet 4.6 (US)",
1476
+ "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
1477
+ id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
1478
+ name: "Claude Sonnet 4.5 (US)",
1293
1479
  api: "bedrock-converse-stream",
1294
1480
  provider: "amazon-bedrock",
1295
1481
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1301,59 +1487,25 @@ export const MODELS = {
1301
1487
  cacheRead: 0.3,
1302
1488
  cacheWrite: 3.75,
1303
1489
  },
1304
- contextWindow: 1000000,
1490
+ contextWindow: 200000,
1305
1491
  maxTokens: 64000,
1306
1492
  },
1307
- "us.deepseek.r1-v1:0": {
1308
- id: "us.deepseek.r1-v1:0",
1309
- name: "DeepSeek-R1 (US)",
1493
+ "us.anthropic.claude-sonnet-4-6": {
1494
+ id: "us.anthropic.claude-sonnet-4-6",
1495
+ name: "Claude Sonnet 4.6 (US)",
1310
1496
  api: "bedrock-converse-stream",
1311
1497
  provider: "amazon-bedrock",
1312
1498
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1313
1499
  reasoning: true,
1314
- input: ["text"],
1315
- cost: {
1316
- input: 1.35,
1317
- output: 5.4,
1318
- cacheRead: 0,
1319
- cacheWrite: 0,
1320
- },
1321
- contextWindow: 128000,
1322
- maxTokens: 32768,
1323
- },
1324
- "us.meta.llama4-maverick-17b-instruct-v1:0": {
1325
- id: "us.meta.llama4-maverick-17b-instruct-v1:0",
1326
- name: "Llama 4 Maverick 17B Instruct (US)",
1327
- api: "bedrock-converse-stream",
1328
- provider: "amazon-bedrock",
1329
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1330
- reasoning: false,
1331
1500
  input: ["text", "image"],
1332
1501
  cost: {
1333
- input: 0.24,
1334
- output: 0.97,
1335
- cacheRead: 0,
1336
- cacheWrite: 0,
1502
+ input: 3,
1503
+ output: 15,
1504
+ cacheRead: 0.3,
1505
+ cacheWrite: 3.75,
1337
1506
  },
1338
1507
  contextWindow: 1000000,
1339
- maxTokens: 16384,
1340
- },
1341
- "us.meta.llama4-scout-17b-instruct-v1:0": {
1342
- id: "us.meta.llama4-scout-17b-instruct-v1:0",
1343
- name: "Llama 4 Scout 17B Instruct (US)",
1344
- api: "bedrock-converse-stream",
1345
- provider: "amazon-bedrock",
1346
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1347
- reasoning: false,
1348
- input: ["text", "image"],
1349
- cost: {
1350
- input: 0.17,
1351
- output: 0.66,
1352
- cacheRead: 0,
1353
- cacheWrite: 0,
1354
- },
1355
- contextWindow: 3500000,
1356
- maxTokens: 16384,
1508
+ maxTokens: 64000,
1357
1509
  },
1358
1510
  "writer.palmyra-x4-v1:0": {
1359
1511
  id: "writer.palmyra-x4-v1:0",
@@ -3449,7 +3601,6 @@ export const MODELS = {
3449
3601
  api: "anthropic-messages",
3450
3602
  provider: "fireworks",
3451
3603
  baseUrl: "https://api.fireworks.ai/inference",
3452
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3453
3604
  reasoning: true,
3454
3605
  input: ["text"],
3455
3606
  cost: {
@@ -3460,6 +3611,12 @@ export const MODELS = {
3460
3611
  },
3461
3612
  contextWindow: 163840,
3462
3613
  maxTokens: 163840,
3614
+ compat: {
3615
+ sendSessionAffinityHeaders: true,
3616
+ supportsEagerToolInputStreaming: false,
3617
+ supportsCacheControlOnTools: false,
3618
+ supportsLongCacheRetention: false,
3619
+ },
3463
3620
  },
3464
3621
  "accounts/fireworks/models/deepseek-v3p2": {
3465
3622
  id: "accounts/fireworks/models/deepseek-v3p2",
@@ -3467,7 +3624,6 @@ export const MODELS = {
3467
3624
  api: "anthropic-messages",
3468
3625
  provider: "fireworks",
3469
3626
  baseUrl: "https://api.fireworks.ai/inference",
3470
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3471
3627
  reasoning: true,
3472
3628
  input: ["text"],
3473
3629
  cost: {
@@ -3478,6 +3634,12 @@ export const MODELS = {
3478
3634
  },
3479
3635
  contextWindow: 160000,
3480
3636
  maxTokens: 160000,
3637
+ compat: {
3638
+ sendSessionAffinityHeaders: true,
3639
+ supportsEagerToolInputStreaming: false,
3640
+ supportsCacheControlOnTools: false,
3641
+ supportsLongCacheRetention: false,
3642
+ },
3481
3643
  },
3482
3644
  "accounts/fireworks/models/deepseek-v4-pro": {
3483
3645
  id: "accounts/fireworks/models/deepseek-v4-pro",
@@ -3485,7 +3647,6 @@ export const MODELS = {
3485
3647
  api: "anthropic-messages",
3486
3648
  provider: "fireworks",
3487
3649
  baseUrl: "https://api.fireworks.ai/inference",
3488
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3489
3650
  reasoning: true,
3490
3651
  input: ["text"],
3491
3652
  cost: {
@@ -3496,6 +3657,12 @@ export const MODELS = {
3496
3657
  },
3497
3658
  contextWindow: 1000000,
3498
3659
  maxTokens: 384000,
3660
+ compat: {
3661
+ sendSessionAffinityHeaders: true,
3662
+ supportsEagerToolInputStreaming: false,
3663
+ supportsCacheControlOnTools: false,
3664
+ supportsLongCacheRetention: false,
3665
+ },
3499
3666
  },
3500
3667
  "accounts/fireworks/models/glm-4p5": {
3501
3668
  id: "accounts/fireworks/models/glm-4p5",
@@ -3503,7 +3670,6 @@ export const MODELS = {
3503
3670
  api: "anthropic-messages",
3504
3671
  provider: "fireworks",
3505
3672
  baseUrl: "https://api.fireworks.ai/inference",
3506
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3507
3673
  reasoning: true,
3508
3674
  input: ["text"],
3509
3675
  cost: {
@@ -3514,6 +3680,12 @@ export const MODELS = {
3514
3680
  },
3515
3681
  contextWindow: 131072,
3516
3682
  maxTokens: 131072,
3683
+ compat: {
3684
+ sendSessionAffinityHeaders: true,
3685
+ supportsEagerToolInputStreaming: false,
3686
+ supportsCacheControlOnTools: false,
3687
+ supportsLongCacheRetention: false,
3688
+ },
3517
3689
  },
3518
3690
  "accounts/fireworks/models/glm-4p5-air": {
3519
3691
  id: "accounts/fireworks/models/glm-4p5-air",
@@ -3521,7 +3693,6 @@ export const MODELS = {
3521
3693
  api: "anthropic-messages",
3522
3694
  provider: "fireworks",
3523
3695
  baseUrl: "https://api.fireworks.ai/inference",
3524
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3525
3696
  reasoning: true,
3526
3697
  input: ["text"],
3527
3698
  cost: {
@@ -3532,6 +3703,12 @@ export const MODELS = {
3532
3703
  },
3533
3704
  contextWindow: 131072,
3534
3705
  maxTokens: 131072,
3706
+ compat: {
3707
+ sendSessionAffinityHeaders: true,
3708
+ supportsEagerToolInputStreaming: false,
3709
+ supportsCacheControlOnTools: false,
3710
+ supportsLongCacheRetention: false,
3711
+ },
3535
3712
  },
3536
3713
  "accounts/fireworks/models/glm-4p7": {
3537
3714
  id: "accounts/fireworks/models/glm-4p7",
@@ -3539,7 +3716,6 @@ export const MODELS = {
3539
3716
  api: "anthropic-messages",
3540
3717
  provider: "fireworks",
3541
3718
  baseUrl: "https://api.fireworks.ai/inference",
3542
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3543
3719
  reasoning: true,
3544
3720
  input: ["text"],
3545
3721
  cost: {
@@ -3550,6 +3726,12 @@ export const MODELS = {
3550
3726
  },
3551
3727
  contextWindow: 198000,
3552
3728
  maxTokens: 198000,
3729
+ compat: {
3730
+ sendSessionAffinityHeaders: true,
3731
+ supportsEagerToolInputStreaming: false,
3732
+ supportsCacheControlOnTools: false,
3733
+ supportsLongCacheRetention: false,
3734
+ },
3553
3735
  },
3554
3736
  "accounts/fireworks/models/glm-5": {
3555
3737
  id: "accounts/fireworks/models/glm-5",
@@ -3557,7 +3739,6 @@ export const MODELS = {
3557
3739
  api: "anthropic-messages",
3558
3740
  provider: "fireworks",
3559
3741
  baseUrl: "https://api.fireworks.ai/inference",
3560
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3561
3742
  reasoning: true,
3562
3743
  input: ["text"],
3563
3744
  cost: {
@@ -3568,6 +3749,12 @@ export const MODELS = {
3568
3749
  },
3569
3750
  contextWindow: 202752,
3570
3751
  maxTokens: 131072,
3752
+ compat: {
3753
+ sendSessionAffinityHeaders: true,
3754
+ supportsEagerToolInputStreaming: false,
3755
+ supportsCacheControlOnTools: false,
3756
+ supportsLongCacheRetention: false,
3757
+ },
3571
3758
  },
3572
3759
  "accounts/fireworks/models/glm-5p1": {
3573
3760
  id: "accounts/fireworks/models/glm-5p1",
@@ -3575,7 +3762,6 @@ export const MODELS = {
3575
3762
  api: "anthropic-messages",
3576
3763
  provider: "fireworks",
3577
3764
  baseUrl: "https://api.fireworks.ai/inference",
3578
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3579
3765
  reasoning: true,
3580
3766
  input: ["text"],
3581
3767
  cost: {
@@ -3586,6 +3772,12 @@ export const MODELS = {
3586
3772
  },
3587
3773
  contextWindow: 202800,
3588
3774
  maxTokens: 131072,
3775
+ compat: {
3776
+ sendSessionAffinityHeaders: true,
3777
+ supportsEagerToolInputStreaming: false,
3778
+ supportsCacheControlOnTools: false,
3779
+ supportsLongCacheRetention: false,
3780
+ },
3589
3781
  },
3590
3782
  "accounts/fireworks/models/gpt-oss-120b": {
3591
3783
  id: "accounts/fireworks/models/gpt-oss-120b",
@@ -3593,7 +3785,6 @@ export const MODELS = {
3593
3785
  api: "anthropic-messages",
3594
3786
  provider: "fireworks",
3595
3787
  baseUrl: "https://api.fireworks.ai/inference",
3596
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3597
3788
  reasoning: true,
3598
3789
  input: ["text"],
3599
3790
  cost: {
@@ -3604,6 +3795,12 @@ export const MODELS = {
3604
3795
  },
3605
3796
  contextWindow: 131072,
3606
3797
  maxTokens: 32768,
3798
+ compat: {
3799
+ sendSessionAffinityHeaders: true,
3800
+ supportsEagerToolInputStreaming: false,
3801
+ supportsCacheControlOnTools: false,
3802
+ supportsLongCacheRetention: false,
3803
+ },
3607
3804
  },
3608
3805
  "accounts/fireworks/models/gpt-oss-20b": {
3609
3806
  id: "accounts/fireworks/models/gpt-oss-20b",
@@ -3611,7 +3808,6 @@ export const MODELS = {
3611
3808
  api: "anthropic-messages",
3612
3809
  provider: "fireworks",
3613
3810
  baseUrl: "https://api.fireworks.ai/inference",
3614
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3615
3811
  reasoning: true,
3616
3812
  input: ["text"],
3617
3813
  cost: {
@@ -3622,6 +3818,12 @@ export const MODELS = {
3622
3818
  },
3623
3819
  contextWindow: 131072,
3624
3820
  maxTokens: 32768,
3821
+ compat: {
3822
+ sendSessionAffinityHeaders: true,
3823
+ supportsEagerToolInputStreaming: false,
3824
+ supportsCacheControlOnTools: false,
3825
+ supportsLongCacheRetention: false,
3826
+ },
3625
3827
  },
3626
3828
  "accounts/fireworks/models/kimi-k2-instruct": {
3627
3829
  id: "accounts/fireworks/models/kimi-k2-instruct",
@@ -3629,7 +3831,6 @@ export const MODELS = {
3629
3831
  api: "anthropic-messages",
3630
3832
  provider: "fireworks",
3631
3833
  baseUrl: "https://api.fireworks.ai/inference",
3632
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3633
3834
  reasoning: false,
3634
3835
  input: ["text"],
3635
3836
  cost: {
@@ -3640,6 +3841,12 @@ export const MODELS = {
3640
3841
  },
3641
3842
  contextWindow: 128000,
3642
3843
  maxTokens: 16384,
3844
+ compat: {
3845
+ sendSessionAffinityHeaders: true,
3846
+ supportsEagerToolInputStreaming: false,
3847
+ supportsCacheControlOnTools: false,
3848
+ supportsLongCacheRetention: false,
3849
+ },
3643
3850
  },
3644
3851
  "accounts/fireworks/models/kimi-k2-thinking": {
3645
3852
  id: "accounts/fireworks/models/kimi-k2-thinking",
@@ -3647,7 +3854,6 @@ export const MODELS = {
3647
3854
  api: "anthropic-messages",
3648
3855
  provider: "fireworks",
3649
3856
  baseUrl: "https://api.fireworks.ai/inference",
3650
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3651
3857
  reasoning: true,
3652
3858
  input: ["text"],
3653
3859
  cost: {
@@ -3658,6 +3864,12 @@ export const MODELS = {
3658
3864
  },
3659
3865
  contextWindow: 256000,
3660
3866
  maxTokens: 256000,
3867
+ compat: {
3868
+ sendSessionAffinityHeaders: true,
3869
+ supportsEagerToolInputStreaming: false,
3870
+ supportsCacheControlOnTools: false,
3871
+ supportsLongCacheRetention: false,
3872
+ },
3661
3873
  },
3662
3874
  "accounts/fireworks/models/kimi-k2p5": {
3663
3875
  id: "accounts/fireworks/models/kimi-k2p5",
@@ -3665,7 +3877,6 @@ export const MODELS = {
3665
3877
  api: "anthropic-messages",
3666
3878
  provider: "fireworks",
3667
3879
  baseUrl: "https://api.fireworks.ai/inference",
3668
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3669
3880
  reasoning: true,
3670
3881
  input: ["text", "image"],
3671
3882
  cost: {
@@ -3676,6 +3887,12 @@ export const MODELS = {
3676
3887
  },
3677
3888
  contextWindow: 256000,
3678
3889
  maxTokens: 256000,
3890
+ compat: {
3891
+ sendSessionAffinityHeaders: true,
3892
+ supportsEagerToolInputStreaming: false,
3893
+ supportsCacheControlOnTools: false,
3894
+ supportsLongCacheRetention: false,
3895
+ },
3679
3896
  },
3680
3897
  "accounts/fireworks/models/kimi-k2p6": {
3681
3898
  id: "accounts/fireworks/models/kimi-k2p6",
@@ -3683,7 +3900,6 @@ export const MODELS = {
3683
3900
  api: "anthropic-messages",
3684
3901
  provider: "fireworks",
3685
3902
  baseUrl: "https://api.fireworks.ai/inference",
3686
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3687
3903
  reasoning: true,
3688
3904
  input: ["text", "image"],
3689
3905
  cost: {
@@ -3694,6 +3910,12 @@ export const MODELS = {
3694
3910
  },
3695
3911
  contextWindow: 262000,
3696
3912
  maxTokens: 262000,
3913
+ compat: {
3914
+ sendSessionAffinityHeaders: true,
3915
+ supportsEagerToolInputStreaming: false,
3916
+ supportsCacheControlOnTools: false,
3917
+ supportsLongCacheRetention: false,
3918
+ },
3697
3919
  },
3698
3920
  "accounts/fireworks/models/minimax-m2p1": {
3699
3921
  id: "accounts/fireworks/models/minimax-m2p1",
@@ -3701,7 +3923,6 @@ export const MODELS = {
3701
3923
  api: "anthropic-messages",
3702
3924
  provider: "fireworks",
3703
3925
  baseUrl: "https://api.fireworks.ai/inference",
3704
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3705
3926
  reasoning: true,
3706
3927
  input: ["text"],
3707
3928
  cost: {
@@ -3712,6 +3933,12 @@ export const MODELS = {
3712
3933
  },
3713
3934
  contextWindow: 200000,
3714
3935
  maxTokens: 200000,
3936
+ compat: {
3937
+ sendSessionAffinityHeaders: true,
3938
+ supportsEagerToolInputStreaming: false,
3939
+ supportsCacheControlOnTools: false,
3940
+ supportsLongCacheRetention: false,
3941
+ },
3715
3942
  },
3716
3943
  "accounts/fireworks/models/minimax-m2p5": {
3717
3944
  id: "accounts/fireworks/models/minimax-m2p5",
@@ -3719,7 +3946,6 @@ export const MODELS = {
3719
3946
  api: "anthropic-messages",
3720
3947
  provider: "fireworks",
3721
3948
  baseUrl: "https://api.fireworks.ai/inference",
3722
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3723
3949
  reasoning: true,
3724
3950
  input: ["text"],
3725
3951
  cost: {
@@ -3730,6 +3956,12 @@ export const MODELS = {
3730
3956
  },
3731
3957
  contextWindow: 196608,
3732
3958
  maxTokens: 196608,
3959
+ compat: {
3960
+ sendSessionAffinityHeaders: true,
3961
+ supportsEagerToolInputStreaming: false,
3962
+ supportsCacheControlOnTools: false,
3963
+ supportsLongCacheRetention: false,
3964
+ },
3733
3965
  },
3734
3966
  "accounts/fireworks/models/minimax-m2p7": {
3735
3967
  id: "accounts/fireworks/models/minimax-m2p7",
@@ -3737,7 +3969,6 @@ export const MODELS = {
3737
3969
  api: "anthropic-messages",
3738
3970
  provider: "fireworks",
3739
3971
  baseUrl: "https://api.fireworks.ai/inference",
3740
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3741
3972
  reasoning: true,
3742
3973
  input: ["text"],
3743
3974
  cost: {
@@ -3748,6 +3979,12 @@ export const MODELS = {
3748
3979
  },
3749
3980
  contextWindow: 196608,
3750
3981
  maxTokens: 196608,
3982
+ compat: {
3983
+ sendSessionAffinityHeaders: true,
3984
+ supportsEagerToolInputStreaming: false,
3985
+ supportsCacheControlOnTools: false,
3986
+ supportsLongCacheRetention: false,
3987
+ },
3751
3988
  },
3752
3989
  "accounts/fireworks/models/qwen3p6-plus": {
3753
3990
  id: "accounts/fireworks/models/qwen3p6-plus",
@@ -3755,7 +3992,6 @@ export const MODELS = {
3755
3992
  api: "anthropic-messages",
3756
3993
  provider: "fireworks",
3757
3994
  baseUrl: "https://api.fireworks.ai/inference",
3758
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3759
3995
  reasoning: true,
3760
3996
  input: ["text", "image"],
3761
3997
  cost: {
@@ -3766,6 +4002,12 @@ export const MODELS = {
3766
4002
  },
3767
4003
  contextWindow: 128000,
3768
4004
  maxTokens: 8192,
4005
+ compat: {
4006
+ sendSessionAffinityHeaders: true,
4007
+ supportsEagerToolInputStreaming: false,
4008
+ supportsCacheControlOnTools: false,
4009
+ supportsLongCacheRetention: false,
4010
+ },
3769
4011
  },
3770
4012
  "accounts/fireworks/routers/kimi-k2p5-turbo": {
3771
4013
  id: "accounts/fireworks/routers/kimi-k2p5-turbo",
@@ -3773,7 +4015,6 @@ export const MODELS = {
3773
4015
  api: "anthropic-messages",
3774
4016
  provider: "fireworks",
3775
4017
  baseUrl: "https://api.fireworks.ai/inference",
3776
- compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3777
4018
  reasoning: true,
3778
4019
  input: ["text", "image"],
3779
4020
  cost: {
@@ -3784,6 +4025,12 @@ export const MODELS = {
3784
4025
  },
3785
4026
  contextWindow: 256000,
3786
4027
  maxTokens: 256000,
4028
+ compat: {
4029
+ sendSessionAffinityHeaders: true,
4030
+ supportsEagerToolInputStreaming: false,
4031
+ supportsCacheControlOnTools: false,
4032
+ supportsLongCacheRetention: false,
4033
+ },
3787
4034
  },
3788
4035
  },
3789
4036
  "github-copilot": {
@@ -3862,6 +4109,25 @@ export const MODELS = {
3862
4109
  contextWindow: 144000,
3863
4110
  maxTokens: 64000,
3864
4111
  },
4112
+ "claude-sonnet-4": {
4113
+ id: "claude-sonnet-4",
4114
+ name: "Claude Sonnet 4",
4115
+ api: "anthropic-messages",
4116
+ provider: "github-copilot",
4117
+ baseUrl: "https://api.individual.githubcopilot.com",
4118
+ 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" },
4119
+ compat: { "supportsEagerToolInputStreaming": false },
4120
+ reasoning: true,
4121
+ input: ["text", "image"],
4122
+ cost: {
4123
+ input: 0,
4124
+ output: 0,
4125
+ cacheRead: 0,
4126
+ cacheWrite: 0,
4127
+ },
4128
+ contextWindow: 216000,
4129
+ maxTokens: 16000,
4130
+ },
3865
4131
  "claude-sonnet-4.5": {
3866
4132
  id: "claude-sonnet-4.5",
3867
4133
  name: "Claude Sonnet 4.5",
@@ -3937,6 +4203,25 @@ export const MODELS = {
3937
4203
  contextWindow: 128000,
3938
4204
  maxTokens: 64000,
3939
4205
  },
4206
+ "gemini-3-pro-preview": {
4207
+ id: "gemini-3-pro-preview",
4208
+ name: "Gemini 3 Pro Preview",
4209
+ api: "openai-completions",
4210
+ provider: "github-copilot",
4211
+ baseUrl: "https://api.individual.githubcopilot.com",
4212
+ 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" },
4213
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4214
+ reasoning: true,
4215
+ input: ["text", "image"],
4216
+ cost: {
4217
+ input: 0,
4218
+ output: 0,
4219
+ cacheRead: 0,
4220
+ cacheWrite: 0,
4221
+ },
4222
+ contextWindow: 128000,
4223
+ maxTokens: 64000,
4224
+ },
3940
4225
  "gemini-3.1-pro-preview": {
3941
4226
  id: "gemini-3.1-pro-preview",
3942
4227
  name: "Gemini 3.1 Pro Preview",
@@ -3982,8 +4267,103 @@ export const MODELS = {
3982
4267
  provider: "github-copilot",
3983
4268
  baseUrl: "https://api.individual.githubcopilot.com",
3984
4269
  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" },
3985
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3986
- reasoning: false,
4270
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4271
+ reasoning: false,
4272
+ input: ["text", "image"],
4273
+ cost: {
4274
+ input: 0,
4275
+ output: 0,
4276
+ cacheRead: 0,
4277
+ cacheWrite: 0,
4278
+ },
4279
+ contextWindow: 128000,
4280
+ maxTokens: 4096,
4281
+ },
4282
+ "gpt-5": {
4283
+ id: "gpt-5",
4284
+ name: "GPT-5",
4285
+ api: "openai-responses",
4286
+ provider: "github-copilot",
4287
+ baseUrl: "https://api.individual.githubcopilot.com",
4288
+ 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" },
4289
+ reasoning: true,
4290
+ thinkingLevelMap: { "off": null },
4291
+ input: ["text", "image"],
4292
+ cost: {
4293
+ input: 0,
4294
+ output: 0,
4295
+ cacheRead: 0,
4296
+ cacheWrite: 0,
4297
+ },
4298
+ contextWindow: 128000,
4299
+ maxTokens: 128000,
4300
+ },
4301
+ "gpt-5-mini": {
4302
+ id: "gpt-5-mini",
4303
+ name: "GPT-5-mini",
4304
+ api: "openai-responses",
4305
+ provider: "github-copilot",
4306
+ baseUrl: "https://api.individual.githubcopilot.com",
4307
+ 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" },
4308
+ reasoning: true,
4309
+ thinkingLevelMap: { "off": null },
4310
+ input: ["text", "image"],
4311
+ cost: {
4312
+ input: 0,
4313
+ output: 0,
4314
+ cacheRead: 0,
4315
+ cacheWrite: 0,
4316
+ },
4317
+ contextWindow: 264000,
4318
+ maxTokens: 64000,
4319
+ },
4320
+ "gpt-5.1": {
4321
+ id: "gpt-5.1",
4322
+ name: "GPT-5.1",
4323
+ api: "openai-responses",
4324
+ provider: "github-copilot",
4325
+ baseUrl: "https://api.individual.githubcopilot.com",
4326
+ 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" },
4327
+ reasoning: true,
4328
+ thinkingLevelMap: { "off": null },
4329
+ input: ["text", "image"],
4330
+ cost: {
4331
+ input: 0,
4332
+ output: 0,
4333
+ cacheRead: 0,
4334
+ cacheWrite: 0,
4335
+ },
4336
+ contextWindow: 264000,
4337
+ maxTokens: 64000,
4338
+ },
4339
+ "gpt-5.1-codex": {
4340
+ id: "gpt-5.1-codex",
4341
+ name: "GPT-5.1-Codex",
4342
+ api: "openai-responses",
4343
+ provider: "github-copilot",
4344
+ baseUrl: "https://api.individual.githubcopilot.com",
4345
+ 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" },
4346
+ reasoning: true,
4347
+ thinkingLevelMap: { "off": null },
4348
+ input: ["text", "image"],
4349
+ cost: {
4350
+ input: 0,
4351
+ output: 0,
4352
+ cacheRead: 0,
4353
+ cacheWrite: 0,
4354
+ },
4355
+ contextWindow: 400000,
4356
+ maxTokens: 128000,
4357
+ },
4358
+ "gpt-5.1-codex-max": {
4359
+ id: "gpt-5.1-codex-max",
4360
+ name: "GPT-5.1-Codex-max",
4361
+ api: "openai-responses",
4362
+ provider: "github-copilot",
4363
+ baseUrl: "https://api.individual.githubcopilot.com",
4364
+ 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" },
4365
+ reasoning: true,
4366
+ thinkingLevelMap: { "off": null },
3987
4367
  input: ["text", "image"],
3988
4368
  cost: {
3989
4369
  input: 0,
@@ -3991,12 +4371,12 @@ export const MODELS = {
3991
4371
  cacheRead: 0,
3992
4372
  cacheWrite: 0,
3993
4373
  },
3994
- contextWindow: 128000,
3995
- maxTokens: 4096,
4374
+ contextWindow: 400000,
4375
+ maxTokens: 128000,
3996
4376
  },
3997
- "gpt-5-mini": {
3998
- id: "gpt-5-mini",
3999
- name: "GPT-5-mini",
4377
+ "gpt-5.1-codex-mini": {
4378
+ id: "gpt-5.1-codex-mini",
4379
+ name: "GPT-5.1-Codex-mini",
4000
4380
  api: "openai-responses",
4001
4381
  provider: "github-copilot",
4002
4382
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -4010,8 +4390,8 @@ export const MODELS = {
4010
4390
  cacheRead: 0,
4011
4391
  cacheWrite: 0,
4012
4392
  },
4013
- contextWindow: 264000,
4014
- maxTokens: 64000,
4393
+ contextWindow: 400000,
4394
+ maxTokens: 128000,
4015
4395
  },
4016
4396
  "gpt-5.2": {
4017
4397
  id: "gpt-5.2",
@@ -4261,7 +4641,7 @@ export const MODELS = {
4261
4641
  cost: {
4262
4642
  input: 0.1,
4263
4643
  output: 0.4,
4264
- cacheRead: 0.01,
4644
+ cacheRead: 0.025,
4265
4645
  cacheWrite: 0,
4266
4646
  },
4267
4647
  contextWindow: 1048576,
@@ -4452,7 +4832,7 @@ export const MODELS = {
4452
4832
  input: 0.25,
4453
4833
  output: 1.5,
4454
4834
  cacheRead: 0.025,
4455
- cacheWrite: 0,
4835
+ cacheWrite: 1,
4456
4836
  },
4457
4837
  contextWindow: 1048576,
4458
4838
  maxTokens: 65536,
@@ -4470,7 +4850,7 @@ export const MODELS = {
4470
4850
  input: 0.25,
4471
4851
  output: 1.5,
4472
4852
  cacheRead: 0.025,
4473
- cacheWrite: 0,
4853
+ cacheWrite: 1,
4474
4854
  },
4475
4855
  contextWindow: 1048576,
4476
4856
  maxTokens: 65536,
@@ -4633,283 +5013,6 @@ export const MODELS = {
4633
5013
  maxTokens: 8192,
4634
5014
  },
4635
5015
  },
4636
- "google-antigravity": {
4637
- "claude-opus-4-5-thinking": {
4638
- id: "claude-opus-4-5-thinking",
4639
- name: "Claude Opus 4.5 Thinking (Antigravity)",
4640
- api: "google-gemini-cli",
4641
- provider: "google-antigravity",
4642
- baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
4643
- reasoning: true,
4644
- input: ["text", "image"],
4645
- cost: {
4646
- input: 5,
4647
- output: 25,
4648
- cacheRead: 0.5,
4649
- cacheWrite: 6.25,
4650
- },
4651
- contextWindow: 200000,
4652
- maxTokens: 64000,
4653
- },
4654
- "claude-opus-4-6-thinking": {
4655
- id: "claude-opus-4-6-thinking",
4656
- name: "Claude Opus 4.6 Thinking (Antigravity)",
4657
- api: "google-gemini-cli",
4658
- provider: "google-antigravity",
4659
- baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
4660
- reasoning: true,
4661
- thinkingLevelMap: { "xhigh": "max" },
4662
- input: ["text", "image"],
4663
- cost: {
4664
- input: 5,
4665
- output: 25,
4666
- cacheRead: 0.5,
4667
- cacheWrite: 6.25,
4668
- },
4669
- contextWindow: 200000,
4670
- maxTokens: 128000,
4671
- },
4672
- "claude-sonnet-4-5": {
4673
- id: "claude-sonnet-4-5",
4674
- name: "Claude Sonnet 4.5 (Antigravity)",
4675
- api: "google-gemini-cli",
4676
- provider: "google-antigravity",
4677
- baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
4678
- reasoning: false,
4679
- input: ["text", "image"],
4680
- cost: {
4681
- input: 3,
4682
- output: 15,
4683
- cacheRead: 0.3,
4684
- cacheWrite: 3.75,
4685
- },
4686
- contextWindow: 200000,
4687
- maxTokens: 64000,
4688
- },
4689
- "claude-sonnet-4-5-thinking": {
4690
- id: "claude-sonnet-4-5-thinking",
4691
- name: "Claude Sonnet 4.5 Thinking (Antigravity)",
4692
- api: "google-gemini-cli",
4693
- provider: "google-antigravity",
4694
- baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
4695
- reasoning: true,
4696
- input: ["text", "image"],
4697
- cost: {
4698
- input: 3,
4699
- output: 15,
4700
- cacheRead: 0.3,
4701
- cacheWrite: 3.75,
4702
- },
4703
- contextWindow: 200000,
4704
- maxTokens: 64000,
4705
- },
4706
- "claude-sonnet-4-6": {
4707
- id: "claude-sonnet-4-6",
4708
- name: "Claude Sonnet 4.6 (Antigravity)",
4709
- api: "google-gemini-cli",
4710
- provider: "google-antigravity",
4711
- baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
4712
- reasoning: true,
4713
- input: ["text", "image"],
4714
- cost: {
4715
- input: 3,
4716
- output: 15,
4717
- cacheRead: 0.3,
4718
- cacheWrite: 3.75,
4719
- },
4720
- contextWindow: 200000,
4721
- maxTokens: 64000,
4722
- },
4723
- "gemini-3-flash": {
4724
- id: "gemini-3-flash",
4725
- name: "Gemini 3 Flash (Antigravity)",
4726
- api: "google-gemini-cli",
4727
- provider: "google-antigravity",
4728
- baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
4729
- reasoning: true,
4730
- input: ["text", "image"],
4731
- cost: {
4732
- input: 0.5,
4733
- output: 3,
4734
- cacheRead: 0.5,
4735
- cacheWrite: 0,
4736
- },
4737
- contextWindow: 1048576,
4738
- maxTokens: 65535,
4739
- },
4740
- "gemini-3.1-pro-high": {
4741
- id: "gemini-3.1-pro-high",
4742
- name: "Gemini 3.1 Pro High (Antigravity)",
4743
- api: "google-gemini-cli",
4744
- provider: "google-antigravity",
4745
- baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
4746
- reasoning: true,
4747
- input: ["text", "image"],
4748
- cost: {
4749
- input: 2,
4750
- output: 12,
4751
- cacheRead: 0.2,
4752
- cacheWrite: 2.375,
4753
- },
4754
- contextWindow: 1048576,
4755
- maxTokens: 65535,
4756
- },
4757
- "gemini-3.1-pro-low": {
4758
- id: "gemini-3.1-pro-low",
4759
- name: "Gemini 3.1 Pro Low (Antigravity)",
4760
- api: "google-gemini-cli",
4761
- provider: "google-antigravity",
4762
- baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
4763
- reasoning: true,
4764
- input: ["text", "image"],
4765
- cost: {
4766
- input: 2,
4767
- output: 12,
4768
- cacheRead: 0.2,
4769
- cacheWrite: 2.375,
4770
- },
4771
- contextWindow: 1048576,
4772
- maxTokens: 65535,
4773
- },
4774
- "gpt-oss-120b-medium": {
4775
- id: "gpt-oss-120b-medium",
4776
- name: "GPT-OSS 120B Medium (Antigravity)",
4777
- api: "google-gemini-cli",
4778
- provider: "google-antigravity",
4779
- baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
4780
- reasoning: false,
4781
- input: ["text"],
4782
- cost: {
4783
- input: 0.09,
4784
- output: 0.36,
4785
- cacheRead: 0,
4786
- cacheWrite: 0,
4787
- },
4788
- contextWindow: 131072,
4789
- maxTokens: 32768,
4790
- },
4791
- },
4792
- "google-gemini-cli": {
4793
- "gemini-2.0-flash": {
4794
- id: "gemini-2.0-flash",
4795
- name: "Gemini 2.0 Flash (Cloud Code Assist)",
4796
- api: "google-gemini-cli",
4797
- provider: "google-gemini-cli",
4798
- baseUrl: "https://cloudcode-pa.googleapis.com",
4799
- reasoning: false,
4800
- input: ["text", "image"],
4801
- cost: {
4802
- input: 0,
4803
- output: 0,
4804
- cacheRead: 0,
4805
- cacheWrite: 0,
4806
- },
4807
- contextWindow: 1048576,
4808
- maxTokens: 8192,
4809
- },
4810
- "gemini-2.5-flash": {
4811
- id: "gemini-2.5-flash",
4812
- name: "Gemini 2.5 Flash (Cloud Code Assist)",
4813
- api: "google-gemini-cli",
4814
- provider: "google-gemini-cli",
4815
- baseUrl: "https://cloudcode-pa.googleapis.com",
4816
- reasoning: true,
4817
- input: ["text", "image"],
4818
- cost: {
4819
- input: 0,
4820
- output: 0,
4821
- cacheRead: 0,
4822
- cacheWrite: 0,
4823
- },
4824
- contextWindow: 1048576,
4825
- maxTokens: 65535,
4826
- },
4827
- "gemini-2.5-pro": {
4828
- id: "gemini-2.5-pro",
4829
- name: "Gemini 2.5 Pro (Cloud Code Assist)",
4830
- api: "google-gemini-cli",
4831
- provider: "google-gemini-cli",
4832
- baseUrl: "https://cloudcode-pa.googleapis.com",
4833
- reasoning: true,
4834
- input: ["text", "image"],
4835
- cost: {
4836
- input: 0,
4837
- output: 0,
4838
- cacheRead: 0,
4839
- cacheWrite: 0,
4840
- },
4841
- contextWindow: 1048576,
4842
- maxTokens: 65535,
4843
- },
4844
- "gemini-3-flash-preview": {
4845
- id: "gemini-3-flash-preview",
4846
- name: "Gemini 3 Flash Preview (Cloud Code Assist)",
4847
- api: "google-gemini-cli",
4848
- provider: "google-gemini-cli",
4849
- baseUrl: "https://cloudcode-pa.googleapis.com",
4850
- reasoning: true,
4851
- input: ["text", "image"],
4852
- cost: {
4853
- input: 0,
4854
- output: 0,
4855
- cacheRead: 0,
4856
- cacheWrite: 0,
4857
- },
4858
- contextWindow: 1048576,
4859
- maxTokens: 65535,
4860
- },
4861
- "gemini-3-pro-preview": {
4862
- id: "gemini-3-pro-preview",
4863
- name: "Gemini 3 Pro Preview (Cloud Code Assist)",
4864
- api: "google-gemini-cli",
4865
- provider: "google-gemini-cli",
4866
- baseUrl: "https://cloudcode-pa.googleapis.com",
4867
- reasoning: true,
4868
- input: ["text", "image"],
4869
- cost: {
4870
- input: 0,
4871
- output: 0,
4872
- cacheRead: 0,
4873
- cacheWrite: 0,
4874
- },
4875
- contextWindow: 1048576,
4876
- maxTokens: 65535,
4877
- },
4878
- "gemini-3.1-flash-lite-preview": {
4879
- id: "gemini-3.1-flash-lite-preview",
4880
- name: "Gemini 3.1 Flash Lite Preview (Cloud Code Assist)",
4881
- api: "google-gemini-cli",
4882
- provider: "google-gemini-cli",
4883
- baseUrl: "https://cloudcode-pa.googleapis.com",
4884
- reasoning: true,
4885
- input: ["text", "image"],
4886
- cost: {
4887
- input: 0,
4888
- output: 0,
4889
- cacheRead: 0,
4890
- cacheWrite: 0,
4891
- },
4892
- contextWindow: 1048576,
4893
- maxTokens: 65535,
4894
- },
4895
- "gemini-3.1-pro-preview": {
4896
- id: "gemini-3.1-pro-preview",
4897
- name: "Gemini 3.1 Pro Preview (Cloud Code Assist)",
4898
- api: "google-gemini-cli",
4899
- provider: "google-gemini-cli",
4900
- baseUrl: "https://cloudcode-pa.googleapis.com",
4901
- reasoning: true,
4902
- input: ["text", "image"],
4903
- cost: {
4904
- input: 0,
4905
- output: 0,
4906
- cacheRead: 0,
4907
- cacheWrite: 0,
4908
- },
4909
- contextWindow: 1048576,
4910
- maxTokens: 65535,
4911
- },
4912
- },
4913
5016
  "google-vertex": {
4914
5017
  "gemini-1.5-flash": {
4915
5018
  id: "gemini-1.5-flash",
@@ -7764,25 +7867,6 @@ export const MODELS = {
7764
7867
  contextWindow: 1000000,
7765
7868
  maxTokens: 64000,
7766
7869
  },
7767
- "deepseek-v4-flash-free": {
7768
- id: "deepseek-v4-flash-free",
7769
- name: "DeepSeek V4 Flash Free",
7770
- api: "openai-completions",
7771
- provider: "opencode",
7772
- baseUrl: "https://opencode.ai/zen/v1",
7773
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
7774
- reasoning: true,
7775
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
7776
- input: ["text"],
7777
- cost: {
7778
- input: 0,
7779
- output: 0,
7780
- cacheRead: 0,
7781
- cacheWrite: 0,
7782
- },
7783
- contextWindow: 1000000,
7784
- maxTokens: 384000,
7785
- },
7786
7870
  "gemini-3-flash": {
7787
7871
  id: "gemini-3-flash",
7788
7872
  name: "Gemini 3 Flash",
@@ -8130,16 +8214,33 @@ export const MODELS = {
8130
8214
  provider: "opencode",
8131
8215
  baseUrl: "https://opencode.ai/zen/v1",
8132
8216
  reasoning: true,
8133
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
8134
- input: ["text", "image"],
8217
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
8218
+ input: ["text", "image"],
8219
+ cost: {
8220
+ input: 30,
8221
+ output: 180,
8222
+ cacheRead: 30,
8223
+ cacheWrite: 0,
8224
+ },
8225
+ contextWindow: 1050000,
8226
+ maxTokens: 128000,
8227
+ },
8228
+ "hy3-preview-free": {
8229
+ id: "hy3-preview-free",
8230
+ name: "Hy3 preview Free",
8231
+ api: "openai-completions",
8232
+ provider: "opencode",
8233
+ baseUrl: "https://opencode.ai/zen/v1",
8234
+ reasoning: true,
8235
+ input: ["text"],
8135
8236
  cost: {
8136
- input: 30,
8137
- output: 180,
8138
- cacheRead: 30,
8237
+ input: 0,
8238
+ output: 0,
8239
+ cacheRead: 0,
8139
8240
  cacheWrite: 0,
8140
8241
  },
8141
- contextWindow: 1050000,
8142
- maxTokens: 128000,
8242
+ contextWindow: 256000,
8243
+ maxTokens: 64000,
8143
8244
  },
8144
8245
  "kimi-k2.5": {
8145
8246
  id: "kimi-k2.5",
@@ -8277,23 +8378,6 @@ export const MODELS = {
8277
8378
  contextWindow: 262144,
8278
8379
  maxTokens: 65536,
8279
8380
  },
8280
- "qwen3.6-plus-free": {
8281
- id: "qwen3.6-plus-free",
8282
- name: "Qwen3.6 Plus Free",
8283
- api: "anthropic-messages",
8284
- provider: "opencode",
8285
- baseUrl: "https://opencode.ai/zen",
8286
- reasoning: true,
8287
- input: ["text", "image"],
8288
- cost: {
8289
- input: 0,
8290
- output: 0,
8291
- cacheRead: 0,
8292
- cacheWrite: 0,
8293
- },
8294
- contextWindow: 262144,
8295
- maxTokens: 65536,
8296
- },
8297
8381
  },
8298
8382
  "opencode-go": {
8299
8383
  "deepseek-v4-flash": {
@@ -8439,9 +8523,9 @@ export const MODELS = {
8439
8523
  "minimax-m2.5": {
8440
8524
  id: "minimax-m2.5",
8441
8525
  name: "MiniMax M2.5",
8442
- api: "anthropic-messages",
8526
+ api: "openai-completions",
8443
8527
  provider: "opencode-go",
8444
- baseUrl: "https://opencode.ai/zen/go",
8528
+ baseUrl: "https://opencode.ai/zen/go/v1",
8445
8529
  reasoning: true,
8446
8530
  input: ["text"],
8447
8531
  cost: {
@@ -8661,6 +8745,40 @@ export const MODELS = {
8661
8745
  contextWindow: 200000,
8662
8746
  maxTokens: 8192,
8663
8747
  },
8748
+ "anthropic/claude-3.7-sonnet": {
8749
+ id: "anthropic/claude-3.7-sonnet",
8750
+ name: "Anthropic: Claude 3.7 Sonnet",
8751
+ api: "openai-completions",
8752
+ provider: "openrouter",
8753
+ baseUrl: "https://openrouter.ai/api/v1",
8754
+ reasoning: true,
8755
+ input: ["text", "image"],
8756
+ cost: {
8757
+ input: 3,
8758
+ output: 15,
8759
+ cacheRead: 0.3,
8760
+ cacheWrite: 3.75,
8761
+ },
8762
+ contextWindow: 200000,
8763
+ maxTokens: 64000,
8764
+ },
8765
+ "anthropic/claude-3.7-sonnet:thinking": {
8766
+ id: "anthropic/claude-3.7-sonnet:thinking",
8767
+ name: "Anthropic: Claude 3.7 Sonnet (thinking)",
8768
+ api: "openai-completions",
8769
+ provider: "openrouter",
8770
+ baseUrl: "https://openrouter.ai/api/v1",
8771
+ reasoning: true,
8772
+ input: ["text", "image"],
8773
+ cost: {
8774
+ input: 3,
8775
+ output: 15,
8776
+ cacheRead: 0.3,
8777
+ cacheWrite: 3.75,
8778
+ },
8779
+ contextWindow: 200000,
8780
+ maxTokens: 64000,
8781
+ },
8664
8782
  "anthropic/claude-haiku-4.5": {
8665
8783
  id: "anthropic/claude-haiku-4.5",
8666
8784
  name: "Anthropic: Claude Haiku 4.5",
@@ -8783,24 +8901,6 @@ export const MODELS = {
8783
8901
  contextWindow: 1000000,
8784
8902
  maxTokens: 128000,
8785
8903
  },
8786
- "anthropic/claude-opus-4.7-fast": {
8787
- id: "anthropic/claude-opus-4.7-fast",
8788
- name: "Anthropic: Claude Opus 4.7 (Fast)",
8789
- api: "openai-completions",
8790
- provider: "openrouter",
8791
- baseUrl: "https://openrouter.ai/api/v1",
8792
- reasoning: true,
8793
- thinkingLevelMap: { "xhigh": "xhigh" },
8794
- input: ["text", "image"],
8795
- cost: {
8796
- input: 30,
8797
- output: 150,
8798
- cacheRead: 3,
8799
- cacheWrite: 37.5,
8800
- },
8801
- contextWindow: 1000000,
8802
- maxTokens: 128000,
8803
- },
8804
8904
  "anthropic/claude-sonnet-4": {
8805
8905
  id: "anthropic/claude-sonnet-4",
8806
8906
  name: "Anthropic: Claude Sonnet 4",
@@ -8886,23 +8986,6 @@ export const MODELS = {
8886
8986
  contextWindow: 262144,
8887
8987
  maxTokens: 262144,
8888
8988
  },
8889
- "arcee-ai/trinity-large-thinking:free": {
8890
- id: "arcee-ai/trinity-large-thinking:free",
8891
- name: "Arcee AI: Trinity Large Thinking (free)",
8892
- api: "openai-completions",
8893
- provider: "openrouter",
8894
- baseUrl: "https://openrouter.ai/api/v1",
8895
- reasoning: true,
8896
- input: ["text"],
8897
- cost: {
8898
- input: 0,
8899
- output: 0,
8900
- cacheRead: 0,
8901
- cacheWrite: 0,
8902
- },
8903
- contextWindow: 262144,
8904
- maxTokens: 80000,
8905
- },
8906
8989
  "arcee-ai/trinity-mini": {
8907
8990
  id: "arcee-ai/trinity-mini",
8908
8991
  name: "Arcee AI: Trinity Mini",
@@ -9150,13 +9233,13 @@ export const MODELS = {
9150
9233
  reasoning: true,
9151
9234
  input: ["text"],
9152
9235
  cost: {
9153
- input: 0.21,
9154
- output: 0.7899999999999999,
9155
- cacheRead: 0.13,
9236
+ input: 0.15,
9237
+ output: 0.75,
9238
+ cacheRead: 0,
9156
9239
  cacheWrite: 0,
9157
9240
  },
9158
- contextWindow: 163840,
9159
- maxTokens: 32768,
9241
+ contextWindow: 32768,
9242
+ maxTokens: 7168,
9160
9243
  },
9161
9244
  "deepseek/deepseek-r1": {
9162
9245
  id: "deepseek/deepseek-r1",
@@ -9254,28 +9337,9 @@ export const MODELS = {
9254
9337
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9255
9338
  input: ["text"],
9256
9339
  cost: {
9257
- input: 0.126,
9258
- output: 0.252,
9259
- cacheRead: 0.0252,
9260
- cacheWrite: 0,
9261
- },
9262
- contextWindow: 1048576,
9263
- maxTokens: 131072,
9264
- },
9265
- "deepseek/deepseek-v4-flash:free": {
9266
- id: "deepseek/deepseek-v4-flash:free",
9267
- name: "DeepSeek: DeepSeek V4 Flash (free)",
9268
- api: "openai-completions",
9269
- provider: "openrouter",
9270
- baseUrl: "https://openrouter.ai/api/v1",
9271
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
9272
- reasoning: true,
9273
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9274
- input: ["text"],
9275
- cost: {
9276
- input: 0,
9277
- output: 0,
9278
- cacheRead: 0,
9340
+ input: 0.14,
9341
+ output: 0.28,
9342
+ cacheRead: 0.0028,
9279
9343
  cacheWrite: 0,
9280
9344
  },
9281
9345
  contextWindow: 1048576,
@@ -9615,8 +9679,8 @@ export const MODELS = {
9615
9679
  reasoning: true,
9616
9680
  input: ["text", "image"],
9617
9681
  cost: {
9618
- input: 0.12,
9619
- output: 0.37,
9682
+ input: 0.13,
9683
+ output: 0.38,
9620
9684
  cacheRead: 0,
9621
9685
  cacheWrite: 0,
9622
9686
  },
@@ -9701,31 +9765,14 @@ export const MODELS = {
9701
9765
  reasoning: false,
9702
9766
  input: ["text"],
9703
9767
  cost: {
9704
- input: 0.01,
9705
- output: 0.03,
9706
- cacheRead: 0.002,
9768
+ input: 0.08,
9769
+ output: 0.24,
9770
+ cacheRead: 0.016,
9707
9771
  cacheWrite: 0,
9708
9772
  },
9709
9773
  contextWindow: 262144,
9710
9774
  maxTokens: 32768,
9711
9775
  },
9712
- "inclusionai/ring-2.6-1t:free": {
9713
- id: "inclusionai/ring-2.6-1t:free",
9714
- name: "inclusionAI: Ring-2.6-1T (free)",
9715
- api: "openai-completions",
9716
- provider: "openrouter",
9717
- baseUrl: "https://openrouter.ai/api/v1",
9718
- reasoning: true,
9719
- input: ["text"],
9720
- cost: {
9721
- input: 0,
9722
- output: 0,
9723
- cacheRead: 0,
9724
- cacheWrite: 0,
9725
- },
9726
- contextWindow: 262144,
9727
- maxTokens: 65536,
9728
- },
9729
9776
  "kwaipilot/kat-coder-pro-v2": {
9730
9777
  id: "kwaipilot/kat-coder-pro-v2",
9731
9778
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -9890,11 +9937,11 @@ export const MODELS = {
9890
9937
  cost: {
9891
9938
  input: 0.15,
9892
9939
  output: 1.15,
9893
- cacheRead: 0,
9940
+ cacheRead: 0.03,
9894
9941
  cacheWrite: 0,
9895
9942
  },
9896
9943
  contextWindow: 196608,
9897
- maxTokens: 196608,
9944
+ maxTokens: 131072,
9898
9945
  },
9899
9946
  "minimax/minimax-m2.5:free": {
9900
9947
  id: "minimax/minimax-m2.5:free",
@@ -9922,13 +9969,13 @@ export const MODELS = {
9922
9969
  reasoning: true,
9923
9970
  input: ["text"],
9924
9971
  cost: {
9925
- input: 0.27899999999999997,
9972
+ input: 0.3,
9926
9973
  output: 1.2,
9927
- cacheRead: 0,
9974
+ cacheRead: 0.059,
9928
9975
  cacheWrite: 0,
9929
9976
  },
9930
9977
  contextWindow: 196608,
9931
- maxTokens: 131072,
9978
+ maxTokens: 4096,
9932
9979
  },
9933
9980
  "mistralai/codestral-2508": {
9934
9981
  id: "mistralai/codestral-2508",
@@ -10313,8 +10360,8 @@ export const MODELS = {
10313
10360
  reasoning: false,
10314
10361
  input: ["text"],
10315
10362
  cost: {
10316
- input: 0.6,
10317
- output: 2.5,
10363
+ input: 0.39999999999999997,
10364
+ output: 2,
10318
10365
  cacheRead: 0,
10319
10366
  cacheWrite: 0,
10320
10367
  },
@@ -10364,13 +10411,13 @@ export const MODELS = {
10364
10411
  reasoning: true,
10365
10412
  input: ["text", "image"],
10366
10413
  cost: {
10367
- input: 0.73,
10368
- output: 3.49,
10369
- cacheRead: 0.25,
10414
+ input: 0.75,
10415
+ output: 3.5,
10416
+ cacheRead: 0.15,
10370
10417
  cacheWrite: 0,
10371
10418
  },
10372
- contextWindow: 262142,
10373
- maxTokens: 262142,
10419
+ contextWindow: 262144,
10420
+ maxTokens: 16384,
10374
10421
  },
10375
10422
  "nex-agi/deepseek-v3.1-nex-n1": {
10376
10423
  id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -11659,6 +11706,23 @@ export const MODELS = {
11659
11706
  contextWindow: 32768,
11660
11707
  maxTokens: 32768,
11661
11708
  },
11709
+ "qwen/qwen-max": {
11710
+ id: "qwen/qwen-max",
11711
+ name: "Qwen: Qwen-Max ",
11712
+ api: "openai-completions",
11713
+ provider: "openrouter",
11714
+ baseUrl: "https://openrouter.ai/api/v1",
11715
+ reasoning: false,
11716
+ input: ["text"],
11717
+ cost: {
11718
+ input: 1.04,
11719
+ output: 4.16,
11720
+ cacheRead: 0.20800000000000002,
11721
+ cacheWrite: 0,
11722
+ },
11723
+ contextWindow: 32768,
11724
+ maxTokens: 8192,
11725
+ },
11662
11726
  "qwen/qwen-plus": {
11663
11727
  id: "qwen/qwen-plus",
11664
11728
  name: "Qwen: Qwen-Plus",
@@ -11710,6 +11774,40 @@ export const MODELS = {
11710
11774
  contextWindow: 1000000,
11711
11775
  maxTokens: 32768,
11712
11776
  },
11777
+ "qwen/qwen-turbo": {
11778
+ id: "qwen/qwen-turbo",
11779
+ name: "Qwen: Qwen-Turbo",
11780
+ api: "openai-completions",
11781
+ provider: "openrouter",
11782
+ baseUrl: "https://openrouter.ai/api/v1",
11783
+ reasoning: false,
11784
+ input: ["text"],
11785
+ cost: {
11786
+ input: 0.0325,
11787
+ output: 0.13,
11788
+ cacheRead: 0.006500000000000001,
11789
+ cacheWrite: 0,
11790
+ },
11791
+ contextWindow: 131072,
11792
+ maxTokens: 8192,
11793
+ },
11794
+ "qwen/qwen-vl-max": {
11795
+ id: "qwen/qwen-vl-max",
11796
+ name: "Qwen: Qwen VL Max",
11797
+ api: "openai-completions",
11798
+ provider: "openrouter",
11799
+ baseUrl: "https://openrouter.ai/api/v1",
11800
+ reasoning: false,
11801
+ input: ["text", "image"],
11802
+ cost: {
11803
+ input: 0.52,
11804
+ output: 2.08,
11805
+ cacheRead: 0,
11806
+ cacheWrite: 0,
11807
+ },
11808
+ contextWindow: 131072,
11809
+ maxTokens: 32768,
11810
+ },
11713
11811
  "qwen/qwen3-14b": {
11714
11812
  id: "qwen/qwen3-14b",
11715
11813
  name: "Qwen: Qwen3 14B",
@@ -11719,7 +11817,7 @@ export const MODELS = {
11719
11817
  reasoning: true,
11720
11818
  input: ["text"],
11721
11819
  cost: {
11722
- input: 0.09999999999999999,
11820
+ input: 0.06,
11723
11821
  output: 0.24,
11724
11822
  cacheRead: 0,
11725
11823
  cacheWrite: 0,
@@ -11839,12 +11937,12 @@ export const MODELS = {
11839
11937
  input: ["text"],
11840
11938
  cost: {
11841
11939
  input: 0.08,
11842
- output: 0.28,
11843
- cacheRead: 0,
11940
+ output: 0.24,
11941
+ cacheRead: 0.04,
11844
11942
  cacheWrite: 0,
11845
11943
  },
11846
11944
  contextWindow: 40960,
11847
- maxTokens: 16384,
11945
+ maxTokens: 40960,
11848
11946
  },
11849
11947
  "qwen/qwen3-8b": {
11850
11948
  id: "qwen/qwen3-8b",
@@ -12297,8 +12395,8 @@ export const MODELS = {
12297
12395
  reasoning: true,
12298
12396
  input: ["text", "image"],
12299
12397
  cost: {
12300
- input: 0.3,
12301
- output: 1.7999999999999998,
12398
+ input: 0.39999999999999997,
12399
+ output: 2.4,
12302
12400
  cacheRead: 0,
12303
12401
  cacheWrite: 0,
12304
12402
  },
@@ -12348,10 +12446,10 @@ export const MODELS = {
12348
12446
  reasoning: true,
12349
12447
  input: ["text", "image"],
12350
12448
  cost: {
12351
- input: 0.1875,
12352
- output: 1.125,
12449
+ input: 0.25,
12450
+ output: 1.5,
12353
12451
  cacheRead: 0,
12354
- cacheWrite: 0.234375,
12452
+ cacheWrite: 0.3125,
12355
12453
  },
12356
12454
  contextWindow: 1000000,
12357
12455
  maxTokens: 65536,
@@ -12475,18 +12573,18 @@ export const MODELS = {
12475
12573
  contextWindow: 262144,
12476
12574
  maxTokens: 65536,
12477
12575
  },
12478
- "tencent/hy3-preview": {
12479
- id: "tencent/hy3-preview",
12480
- name: "Tencent: Hy3 preview",
12576
+ "tencent/hy3-preview:free": {
12577
+ id: "tencent/hy3-preview:free",
12578
+ name: "Tencent: Hy3 preview (free)",
12481
12579
  api: "openai-completions",
12482
12580
  provider: "openrouter",
12483
12581
  baseUrl: "https://openrouter.ai/api/v1",
12484
12582
  reasoning: true,
12485
12583
  input: ["text"],
12486
12584
  cost: {
12487
- input: 0.06599999999999999,
12488
- output: 0.26,
12489
- cacheRead: 0.029,
12585
+ input: 0,
12586
+ output: 0,
12587
+ cacheRead: 0,
12490
12588
  cacheWrite: 0,
12491
12589
  },
12492
12590
  contextWindow: 262144,
@@ -12526,6 +12624,23 @@ export const MODELS = {
12526
12624
  contextWindow: 32768,
12527
12625
  maxTokens: 32768,
12528
12626
  },
12627
+ "tngtech/deepseek-r1t2-chimera": {
12628
+ id: "tngtech/deepseek-r1t2-chimera",
12629
+ name: "TNG: DeepSeek R1T2 Chimera",
12630
+ api: "openai-completions",
12631
+ provider: "openrouter",
12632
+ baseUrl: "https://openrouter.ai/api/v1",
12633
+ reasoning: true,
12634
+ input: ["text"],
12635
+ cost: {
12636
+ input: 0.3,
12637
+ output: 1.1,
12638
+ cacheRead: 0.15,
12639
+ cacheWrite: 0,
12640
+ },
12641
+ contextWindow: 163840,
12642
+ maxTokens: 163840,
12643
+ },
12529
12644
  "upstage/solar-pro-3": {
12530
12645
  id: "upstage/solar-pro-3",
12531
12646
  name: "Upstage: Solar Pro 3",
@@ -12722,9 +12837,9 @@ export const MODELS = {
12722
12837
  reasoning: true,
12723
12838
  input: ["text"],
12724
12839
  cost: {
12725
- input: 0.09999999999999999,
12726
- output: 0.3,
12727
- cacheRead: 0.01,
12840
+ input: 0.09,
12841
+ output: 0.29,
12842
+ cacheRead: 0.045,
12728
12843
  cacheWrite: 0,
12729
12844
  },
12730
12845
  contextWindow: 262144,
@@ -12796,7 +12911,7 @@ export const MODELS = {
12796
12911
  cacheWrite: 0,
12797
12912
  },
12798
12913
  contextWindow: 1048576,
12799
- maxTokens: 16384,
12914
+ maxTokens: 131072,
12800
12915
  },
12801
12916
  "z-ai/glm-4-32b": {
12802
12917
  id: "z-ai/glm-4-32b",
@@ -12892,13 +13007,13 @@ export const MODELS = {
12892
13007
  reasoning: true,
12893
13008
  input: ["text"],
12894
13009
  cost: {
12895
- input: 0.43,
12896
- output: 1.74,
12897
- cacheRead: 0.08,
13010
+ input: 0.39,
13011
+ output: 1.9,
13012
+ cacheRead: 0,
12898
13013
  cacheWrite: 0,
12899
13014
  },
12900
- contextWindow: 202752,
12901
- maxTokens: 131072,
13015
+ contextWindow: 204800,
13016
+ maxTokens: 204800,
12902
13017
  },
12903
13018
  "z-ai/glm-4.6v": {
12904
13019
  id: "z-ai/glm-4.6v",
@@ -12994,13 +13109,13 @@ export const MODELS = {
12994
13109
  reasoning: true,
12995
13110
  input: ["text"],
12996
13111
  cost: {
12997
- input: 0.98,
12998
- output: 3.08,
12999
- cacheRead: 0.182,
13112
+ input: 1.0499999999999998,
13113
+ output: 3.5,
13114
+ cacheRead: 0.5249999999999999,
13000
13115
  cacheWrite: 0,
13001
13116
  },
13002
13117
  contextWindow: 202752,
13003
- maxTokens: 4096,
13118
+ maxTokens: 65535,
13004
13119
  },
13005
13120
  "z-ai/glm-5v-turbo": {
13006
13121
  id: "z-ai/glm-5v-turbo",
@@ -13113,13 +13228,13 @@ export const MODELS = {
13113
13228
  reasoning: true,
13114
13229
  input: ["text", "image"],
13115
13230
  cost: {
13116
- input: 0.73,
13117
- output: 3.49,
13118
- cacheRead: 0.25,
13231
+ input: 0.75,
13232
+ output: 3.5,
13233
+ cacheRead: 0.15,
13119
13234
  cacheWrite: 0,
13120
13235
  },
13121
- contextWindow: 262142,
13122
- maxTokens: 262142,
13236
+ contextWindow: 262144,
13237
+ maxTokens: 16384,
13123
13238
  },
13124
13239
  "~openai/gpt-latest": {
13125
13240
  id: "~openai/gpt-latest",
@@ -13819,6 +13934,23 @@ export const MODELS = {
13819
13934
  contextWindow: 200000,
13820
13935
  maxTokens: 8192,
13821
13936
  },
13937
+ "anthropic/claude-3.7-sonnet": {
13938
+ id: "anthropic/claude-3.7-sonnet",
13939
+ name: "Claude 3.7 Sonnet",
13940
+ api: "anthropic-messages",
13941
+ provider: "vercel-ai-gateway",
13942
+ baseUrl: "https://ai-gateway.vercel.sh",
13943
+ reasoning: true,
13944
+ input: ["text", "image"],
13945
+ cost: {
13946
+ input: 3,
13947
+ output: 15,
13948
+ cacheRead: 0.3,
13949
+ cacheWrite: 3.75,
13950
+ },
13951
+ contextWindow: 200000,
13952
+ maxTokens: 8192,
13953
+ },
13822
13954
  "anthropic/claude-haiku-4.5": {
13823
13955
  id: "anthropic/claude-haiku-4.5",
13824
13956
  name: "Claude Haiku 4.5",
@@ -15501,7 +15633,7 @@ export const MODELS = {
15501
15633
  },
15502
15634
  "openai/gpt-oss-20b": {
15503
15635
  id: "openai/gpt-oss-20b",
15504
- name: "GPT OSS 20B",
15636
+ name: "GPT OSS 120B",
15505
15637
  api: "anthropic-messages",
15506
15638
  provider: "vercel-ai-gateway",
15507
15639
  baseUrl: "https://ai-gateway.vercel.sh",